The search for mechanical properties of materials reached a highly acclaimed level, when indentations could be analysed on the basis of elastic theory for hardness and elastic modulus. The mathematical formulas proved...The search for mechanical properties of materials reached a highly acclaimed level, when indentations could be analysed on the basis of elastic theory for hardness and elastic modulus. The mathematical formulas proved to be very complicated, and various trials were published between the 1900s and 2000s. The development of indentation instruments and the wish to make the application in numerous steps easier, led in 1992 to trials with iterations by using relative values instead of absolute ones. Excessive iterations of computers with 3 + 8 free parameters of the loading and unloading curves became possible and were implemented into the instruments and worldwide standards. The physical formula for hardness was defined as force over area. For the conical, pyramidal, and spherical indenters, one simply took the projected area for the calculation of the indentation depth from the projected area, adjusted it later by the iterations with respect to fused quartz or aluminium as standard materials, and called it “contact height”. Continuously measured indentation loading curves were formulated as loading force over depth square. The unloading curves after release of the indenter used the initial steepness of the pressure relief for the calculation of what was (and is) incorrectly called “Young’s modulus”. But it is not unidirectional. And for the spherical indentations’ loading curve, they defined the indentation force over depth raised to 3/2 (but without R/h correction). They till now (2025) violate the energy law, because they use all applied force for the indenter depth and ignore the obvious sidewise force upon indentation (cf. e.g. the wood cleaving). The various refinements led to more and more complicated formulas that could not be reasonably calculated with them. One decided to use 3 + 8 free-parameter iterations for fitting to the (poor) standards of fused quartz or aluminium. The mechanical values of these were considered to be “true”. This is till now the worldwide standard of DIN-ISO-ASTM-14577, avoiding overcomplicated formulas with their complexity. Some of these are shown in the Introduction Section. By doing so, one avoided the understanding of indentation results on a physical basis. However, we open a simple way to obtain absolute values (though still on the blackbox instrument’s unsuitable force calibration). We do not iterate but calculate algebraically on the basis of the correct, physically deduced exponent of the loading force parabolas with h3/2 instead of false “h2” (for the spherical indentation, there is a calotte-radius over depth correction), and we reveal the physical errors taken up in the official worldwide “14577-Standard”. Importantly, we reveal the hitherto fully overlooked phase transitions under load that are not detectable with the false exponent. Phase-transition twinning is even present and falsifies the iteration standards. Instead of elasticity theory, we use the well-defined geometry of these indentations. By doing so, we reach simple algebraically calculable formulas and find the physical indentation hardness of materials with their onset depth, onset force and energy, as well as their phase-transition energy (temperature dependent also its activation energy). The most important phase transitions are our absolute algebraically calculated results. The now most easily obtained phase transitions under load are very dangerous because they produce polymorph interfaces between the changed and the unchanged material. It was found and published by high-enlargement microscopy (5000-fold) that these trouble spots are the sites for the development of stable, 1 to 2 µm long, micro-cracks (stable for months). If however, a force higher than the one of their formation occurs to them, these grow to catastrophic crash. That works equally with turbulences at the pickle fork of airliners. After the publication of these facts and after three fatal crashing had occurred in a short sequence, FAA (Federal Aviation Agency) reacted by rechecking all airplanes for such micro cracks. These were now found in a new fleet of airliners from where the three crashed ones came. These were previously overlooked. FAA became aware of that risk and grounded 290 (certainly all) of them, because the material of these did not have higher phase-transition onset and energy than other airplanes with better material. They did so despite the 14577-Standard that does not find (and thus formally forbids) phase transitions under indenter load with the false exponent on the indentation parabola. However, this “Standard” will, despite the present author’s well-founded petition, not be corrected for the next 5 years.展开更多
Cyber-Physical Networks(CPN)are comprehensive systems that integrate information and physical domains,and are widely used in various fields such as online social networking,smart grids,and the Internet of Vehicles(IoV...Cyber-Physical Networks(CPN)are comprehensive systems that integrate information and physical domains,and are widely used in various fields such as online social networking,smart grids,and the Internet of Vehicles(IoV).With the increasing popularity of digital photography and Internet technology,more and more users are sharing images on CPN.However,many images are shared without any privacy processing,exposing hidden privacy risks and making sensitive content easily accessible to Artificial Intelligence(AI)algorithms.Existing image sharing methods lack fine-grained image sharing policies and cannot protect user privacy.To address this issue,we propose a social relationship-driven privacy customization protection model for publishers and co-photographers.We construct a heterogeneous social information network centered on social relationships,introduce a user intimacy evaluation method with time decay,and evaluate privacy levels considering user interest similarity.To protect user privacy while maintaining image appreciation,we design a lightweight face-swapping algorithm based on Generative Adversarial Network(GAN)to swap faces that need to be protected.Our proposed method minimizes the loss of image utility while satisfying privacy requirements,as shown by extensive theoretical and simulation analyses.展开更多
NCPA Children’s Opera Commission Effendi&His Double.Date:May 23-June 1,2025,Venue:National Center for the Performing Arts.The opera tells a story about a figure named Effendi waging a battle of wits against his d...NCPA Children’s Opera Commission Effendi&His Double.Date:May 23-June 1,2025,Venue:National Center for the Performing Arts.The opera tells a story about a figure named Effendi waging a battle of wits against his double in Sun City.He maintains justice by punishing the fake Effendi,who cheats the citizens of Sun City.展开更多
The rapid development and widespread adoption of massive open online courses(MOOCs)have indeed had a significant impact on China’s education curriculum.However,the problem of fake reviews and ratings on the platform ...The rapid development and widespread adoption of massive open online courses(MOOCs)have indeed had a significant impact on China’s education curriculum.However,the problem of fake reviews and ratings on the platform has seriously affected the authenticity of course evaluations and user trust,requiring effective anomaly detection techniques for screening.The textual characteristics of MOOCs reviews,such as varying lengths and diverse emotional tendencies,have brought complexity to text analysis.Traditional rule-based analysis methods are often inadequate in dealing with such unstructured data.We propose a Differential Privacy-Enabled Text Convolutional Neural Network(DP-TextCNN)framework,aiming to achieve high-precision identification of outliers in MOOCs course reviews and ratings while protecting user privacy.This framework leverages the advantages of Convolutional Neural Networks(CNN)in text feature extraction and combines differential privacy techniques.It balances data privacy protection with model performance by introducing controlled random noise during the data preprocessing stage.By embedding differential privacy into the model training process,we ensure the privacy security of the framework when handling sensitive data,while maintaining a high recognition accuracy.Experimental results indicate that the DP-TextCNN framework achieves an exceptional accuracy of over 95%in identifying fake reviews on the dataset,this outcome not only verifies the applicability of differential privacy techniques in TextCNN but also underscores its potential in handling sensitive educational data.Additionally,we analyze the specific impact of differential privacy parameters on framework performance,offering theoretical support and empirical analysis to strike an optimal balance between privacy protection and framework efficiency.展开更多
This article is a part of a larger study called The Abstract Truth of Media focused on the topic of the fictional media content opinions presented and perceived as truth.It will explore the abstract nature of truth in...This article is a part of a larger study called The Abstract Truth of Media focused on the topic of the fictional media content opinions presented and perceived as truth.It will explore the abstract nature of truth in online media and its different forms.These media truths are types of fictional stories with certain effects on the public rather than a truthful presentation of the facts.Thus,the end goal of mass media today is not to tell the truth,but to create moral communities based on common experience and beliefs.Articles,opinions,and news in media are seen as a narrative strategy that can be understood only through storytelling analysis.Here the focus is on the understanding of Truth and Untruth in online media as well as the connection of Internet media technology with the increase of disinformation online.The new media model creates hostile groups instead of generating consent for the nation-state,the new online media model within through,Pseudo-communication,manipulation,delusion,lies,propaganda,and deliberate causing of moral anger.“The end of the truth”means that the truth on the Internet is lost among the vast amount of information and the lack of regulation regarding the correctness of the published data.Instead of truth,media researchers formally talk about post-truth,fake news,and“alternative facts”.Truth on the Internet is more like“Truthiness”or a belief that a statement is true based on the intuition or understanding of individuals,regardless of evidence,logic or facts.The subject of research is the connection between every new technology in mass media and the truth of the information and the effects on the consensus in society.Since the beginning of the 21st century,misinformation on the Internet has increased with the development of online media and social networks,and it is a problem of social peace and consent in every country.展开更多
These days,social media has grown to be an integral part of people’s lives.However,it involves the possibility of exposure to“fake news”,which may contain information that is intentionally or inaccurately false to ...These days,social media has grown to be an integral part of people’s lives.However,it involves the possibility of exposure to“fake news”,which may contain information that is intentionally or inaccurately false to promote particular political or economic interests.The main objective of this work is to use the co-attention mechanism in a Combined Graph neural network model(CMCG)to capture the relationship between user profile features and user preferences in order to detect fake news and examine the influence of various social media features on fake news detection.The proposed approach includes three modules.The first one creates a Graph Neural Network(GNN)based model to learn user profile properties,while the second module encodes news content,user historical posts,and news sharing cascading on social media as user preferences GNN-based model.The inter-dependencies between user profiles and user preferences are handled through the third module using a co-attention mechanism for capturing the relationship between the two GNN-based models.We conducted several experiments on two commonly used fake news datasets,Politifact and Gossipcop,where our approach achieved 98.53%accuracy on the Gossipcop dataset and 96.77%accuracy on the Politifact dataset.These results illustrate the effectiveness of the CMCG approach for fake news detection,as it combines various information from different modalities to achieve relatively high performances.展开更多
Social media has significantly accelerated the rapid dissemination of information,but it also boosts propagation of fake news,posing serious challenges to public awareness and social stability.In real-world contexts,t...Social media has significantly accelerated the rapid dissemination of information,but it also boosts propagation of fake news,posing serious challenges to public awareness and social stability.In real-world contexts,the volume of trustable information far exceeds that of rumors,resulting in a class imbalance that leads models to prioritize the majority class during training.This focus diminishes the model’s ability to recognize minority class samples.Furthermore,models may experience overfitting when encountering these minority samples,further compromising their generalization capabilities.Unlike node-level classification tasks,fake news detection in social networks operates on graph-level samples,where traditional interpolation and oversampling methods struggle to effectively generate high-quality graph-level samples.This challenge complicates the identification of new instances of false information.To address this issue,this paper introduces the FHGraph(Fake News Hunting Graph)framework,which employs a generative data augmentation approach and a latent diffusion model to create graph structures that align with news communication patterns.Using the few-sample learning capabilities of large language models(LLMs),the framework generates diverse texts for minority class nodes.FHGraph comprises a hierarchical multiview graph contrastive learning module,in which two horizontal views and three vertical levels are utilized for self-supervised learning,resulting in more optimized representations.Experimental results show that FHGraph significantly outperforms state-of-the-art(SOTA)graph-level class imbalance methods and SOTA graph-level contrastive learning methods.Specifically,FHGraph has achieved a 2%increase in F1 Micro and a 2.5%increase in F1 Macro in the PHEME dataset,as well as a 3.5%improvement in F1 Micro and a 4.3%improvement in F1 Macro on RumorEval dataset.展开更多
With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant harm.As social media content is often composed of both images and text,the use of...With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant harm.As social media content is often composed of both images and text,the use of multimodal approaches for fake news detection has gained significant attention.To solve the problems existing in previous multi-modal fake news detection algorithms,such as insufficient feature extraction and insufficient use of semantic relations between modes,this paper proposes the MFFFND-Co(Multimodal Feature Fusion Fake News Detection with Co-Attention Block)model.First,the model deeply explores the textual content,image content,and frequency domain features.Then,it employs a Co-Attention mechanism for cross-modal fusion.Additionally,a semantic consistency detectionmodule is designed to quantify semantic deviations,thereby enhancing the performance of fake news detection.Experimentally verified on two commonly used datasets,Twitter and Weibo,the model achieved F1 scores of 90.0% and 94.0%,respectively,significantly outperforming the pre-modified MFFFND(Multimodal Feature Fusion Fake News Detection with Attention Block)model and surpassing other baseline models.This improves the accuracy of detecting fake information in artificial intelligence detection and engineering software detection.展开更多
As social networks become increasingly complex, contemporary fake news often includes textual descriptionsof events accompanied by corresponding images or videos. Fake news in multiple modalities is more likely tocrea...As social networks become increasingly complex, contemporary fake news often includes textual descriptionsof events accompanied by corresponding images or videos. Fake news in multiple modalities is more likely tocreate a misleading perception among users. While early research primarily focused on text-based features forfake news detection mechanisms, there has been relatively limited exploration of learning shared representationsin multimodal (text and visual) contexts. To address these limitations, this paper introduces a multimodal modelfor detecting fake news, which relies on similarity reasoning and adversarial networks. The model employsBidirectional Encoder Representation from Transformers (BERT) and Text Convolutional Neural Network (Text-CNN) for extracting textual features while utilizing the pre-trained Visual Geometry Group 19-layer (VGG-19) toextract visual features. Subsequently, the model establishes similarity representations between the textual featuresextracted by Text-CNN and visual features through similarity learning and reasoning. Finally, these features arefused to enhance the accuracy of fake news detection, and adversarial networks have been employed to investigatethe relationship between fake news and events. This paper validates the proposed model using publicly availablemultimodal datasets from Weibo and Twitter. Experimental results demonstrate that our proposed approachachieves superior performance on Twitter, with an accuracy of 86%, surpassing traditional unimodalmodalmodelsand existing multimodal models. In contrast, the overall better performance of our model on the Weibo datasetsurpasses the benchmark models across multiple metrics. The application of similarity reasoning and adversarialnetworks in multimodal fake news detection significantly enhances detection effectiveness in this paper. However,current research is limited to the fusion of only text and image modalities. Future research directions should aimto further integrate features fromadditionalmodalities to comprehensively represent themultifaceted informationof fake news.展开更多
The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method in...The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the CNN.The customized Convolutional Neural Network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its libraries.We used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were real.Ten seconds were allotted for each video.There were 318 videos used in all,199 of which were fake and 119 of which were real.Our proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and MLP-CNN.Furthermore,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and DST-Net.The novelty of this investigation is the development of a new Convolutional Neural Network(CNN)learning model that can accurately detect deep fake face photos.展开更多
Online review platforms are becoming increasingly popular,encouraging dishonest merchants and service providers to deceive customers by creating fake reviews for their goods or services.Using Sybil accounts,bot farms,...Online review platforms are becoming increasingly popular,encouraging dishonest merchants and service providers to deceive customers by creating fake reviews for their goods or services.Using Sybil accounts,bot farms,and real account purchases,immoral actors demonize rivals and advertise their goods.Most academic and industry efforts have been aimed at detecting fake/fraudulent product or service evaluations for years.The primary hurdle to identifying fraudulent reviews is the lack of a reliable means to distinguish fraudulent reviews from real ones.This paper adopts a semi-supervised machine learning method to detect fake reviews on any website,among other things.Online reviews are classified using a semi-supervised approach(PU-learning)since there is a shortage of labeled data,and they are dynamic.Then,classification is performed using the machine learning techniques Support Vector Machine(SVM)and Nave Bayes.The performance of the suggested system has been compared with standard works,and experimental findings are assessed using several assessment metrics.展开更多
With the rapid spread of Internet information and the spread of fake news,the detection of fake news becomes more and more important.Traditional detection methods often rely on a single emotional or semantic feature t...With the rapid spread of Internet information and the spread of fake news,the detection of fake news becomes more and more important.Traditional detection methods often rely on a single emotional or semantic feature to identify fake news,but these methods have limitations when dealing with news in specific domains.In order to solve the problem of weak feature correlation between data from different domains,a model for detecting fake news by integrating domain-specific emotional and semantic features is proposed.This method makes full use of the attention mechanism,grasps the correlation between different features,and effectively improves the effect of feature fusion.The algorithm first extracts the semantic features of news text through the Bi-LSTM(Bidirectional Long Short-Term Memory)layer to capture the contextual relevance of news text.Senta-BiLSTM is then used to extract emotional features and predict the probability of positive and negative emotions in the text.It then uses domain features as an enhancement feature and attention mechanism to fully capture more fine-grained emotional features associated with that domain.Finally,the fusion features are taken as the input of the fake news detection classifier,combined with the multi-task representation of information,and the MLP and Softmax functions are used for classification.The experimental results show that on the Chinese dataset Weibo21,the F1 value of this model is 0.958,4.9% higher than that of the sub-optimal model;on the English dataset FakeNewsNet,the F1 value of the detection result of this model is 0.845,1.8% higher than that of the sub-optimal model,which is advanced and feasible.展开更多
In recent years,how to efficiently and accurately identify multi-model fake news has become more challenging.First,multi-model data provides more evidence but not all are equally important.Secondly,social structure in...In recent years,how to efficiently and accurately identify multi-model fake news has become more challenging.First,multi-model data provides more evidence but not all are equally important.Secondly,social structure information has proven to be effective in fake news detection and how to combine it while reducing the noise information is critical.Unfortunately,existing approaches fail to handle these problems.This paper proposes a multi-model fake news detection framework based on Tex-modal Dominance and fusing Multiple Multi-model Cues(TD-MMC),which utilizes three valuable multi-model clues:text-model importance,text-image complementary,and text-image inconsistency.TD-MMC is dominated by textural content and assisted by image information while using social network information to enhance text representation.To reduce the irrelevant social structure’s information interference,we use a unidirectional cross-modal attention mechanism to selectively learn the social structure’s features.A cross-modal attention mechanism is adopted to obtain text-image cross-modal features while retaining textual features to reduce the loss of important information.In addition,TD-MMC employs a new multi-model loss to improve the model’s generalization ability.Extensive experiments have been conducted on two public real-world English and Chinese datasets,and the results show that our proposed model outperforms the state-of-the-art methods on classification evaluation metrics.展开更多
Social media has become increasingly significant in modern society,but it has also turned into a breeding ground for the propagation of misleading information,potentially causing a detrimental impact on public opinion...Social media has become increasingly significant in modern society,but it has also turned into a breeding ground for the propagation of misleading information,potentially causing a detrimental impact on public opinion and daily life.Compared to pure text content,multmodal content significantly increases the visibility and share ability of posts.This has made the search for efficient modality representations and cross-modal information interaction methods a key focus in the field of multimodal fake news detection.To effectively address the critical challenge of accurately detecting fake news on social media,this paper proposes a fake news detection model based on crossmodal message aggregation and a gated fusion network(MAGF).MAGF first uses BERT to extract cumulative textual feature representations and word-level features,applies Faster Region-based ConvolutionalNeuralNetwork(Faster R-CNN)to obtain image objects,and leverages ResNet-50 and Visual Geometry Group-19(VGG-19)to obtain image region features and global features.The image region features and word-level text features are then projected into a low-dimensional space to calculate a text-image affinity matrix for cross-modal message aggregation.The gated fusion network combines text and image region features to obtain adaptively aggregated features.The interaction matrix is derived through an attention mechanism and further integrated with global image features using a co-attention mechanism to producemultimodal representations.Finally,these fused features are fed into a classifier for news categorization.Experiments were conducted on two public datasets,Twitter and Weibo.Results show that the proposed model achieves accuracy rates of 91.8%and 88.7%on the two datasets,respectively,significantly outperforming traditional unimodal and existing multimodal models.展开更多
In an era dominated by information dissemination through various channels like newspapers,social media,radio,and television,the surge in content production,especially on social platforms,has amplified the challenge of...In an era dominated by information dissemination through various channels like newspapers,social media,radio,and television,the surge in content production,especially on social platforms,has amplified the challenge of distinguishing between truthful and deceptive information.Fake news,a prevalent issue,particularly on social media,complicates the assessment of news credibility.The pervasive spread of fake news not only misleads the public but also erodes trust in legitimate news sources,creating confusion and polarizing opinions.As the volume of information grows,individuals increasingly struggle to discern credible content from false narratives,leading to widespread misinformation and potentially harmful consequences.Despite numerous methodologies proposed for fake news detection,including knowledge-based,language-based,and machine-learning approaches,their efficacy often diminishes when confronted with high-dimensional datasets and data riddled with noise or inconsistencies.Our study addresses this challenge by evaluating the synergistic benefits of combining feature extraction and feature selection techniques in fake news detection.We employ multiple feature extraction methods,including Count Vectorizer,Bag of Words,Global Vectors for Word Representation(GloVe),Word to Vector(Word2Vec),and Term Frequency-Inverse Document Frequency(TF-IDF),alongside feature selection techniques such as Information Gain,Chi-Square,Principal Component Analysis(PCA),and Document Frequency.This comprehensive approach enhances the model’s ability to identify and analyze relevant features,leading to more accurate and effective fake news detection.Our findings highlight the importance of a multi-faceted approach,offering a significant improvement in model accuracy and reliability.Moreover,the study emphasizes the adaptability of the proposed ensemble model across diverse datasets,reinforcing its potential for broader application in real-world scenarios.We introduce a pioneering ensemble technique that leverages both machine-learning and deep-learning classifiers.To identify the optimal ensemble configuration,we systematically tested various combinations.Experimental evaluations conducted on three diverse datasets related to fake news demonstrate the exceptional performance of our proposed ensemble model.Achieving remarkable accuracy levels of 97%,99%,and 98%on Dataset 1,Dataset 2,and Dataset 3,respectively,our approach showcases robustness and effectiveness in discerning fake news amidst the complexities of contemporary information landscapes.This research contributes to the advancement of fake news detection methodologies and underscores the significance of integrating feature extraction and feature selection strategies for enhanced performance,especially in the context of intricate,high-dimensional datasets.展开更多
Deep learning is a practical and efficient technique that has been used extensively in many domains. Using deep learning technology, deepfakes create fake images of a person that people cannot distinguish from the rea...Deep learning is a practical and efficient technique that has been used extensively in many domains. Using deep learning technology, deepfakes create fake images of a person that people cannot distinguish from the real one. Recently, many researchers have focused on understanding how deepkakes work and detecting using deep learning approaches. This paper introduces an explainable deepfake framework for images creation and classification. The framework consists of three main parts: the first approach is called Instant ID which is used to create deepfacke images from the original one;the second approach called Xception classifies the real and deepfake images;the third approach called Local Interpretable Model (LIME) provides a method for interpreting the predictions of any machine learning model in a local and interpretable manner. Our study proposes deepfake approach that achieves 100% precision and 100% accuracy for deepfake creation and classification. Furthermore, the results highlight the superior performance of the proposed model in deep fake creation and classification.展开更多
Reviews have a significant impact on online businesses.Nowadays,online consumers rely heavily on other people’s reviews before purchasing a product,instead of looking at the product description.With the emergence of ...Reviews have a significant impact on online businesses.Nowadays,online consumers rely heavily on other people’s reviews before purchasing a product,instead of looking at the product description.With the emergence of technology,malicious online actors are using techniques such as Natural Language Processing(NLP)and others to generate a large number of fake reviews to destroy their competitors’markets.To remedy this situation,several researches have been conducted in the last few years.Most of them have applied NLP techniques to preprocess the text before building Machine Learning(ML)or Deep Learning(DL)models to detect and filter these fake reviews.However,with the same NLP techniques,machine-generated fake reviews are increasing exponentially.This work explores a powerful text representation technique called Embedding models to combat the proliferation of fake reviews in online marketplaces.Indeed,these embedding structures can capture much more information from the data compared to other standard text representations.To do this,we tested our hypothesis in two different Recurrent Neural Network(RNN)architectures,namely Long Short-Term Memory(LSTM)and Gated Recurrent Unit(GRU),using fake review data from Amazon and TripAdvisor.Our experimental results show that our best-proposed model can distinguish between real and fake reviews with 91.44%accuracy.Furthermore,our results corroborate with the state-of-the-art research in this area and demonstrate some improvements over other approaches.Therefore,proper text representation improves the accuracy of fake review detection.展开更多
Research integrity has been a focal topic in the global scientific community.Some countries face challenges inherent in the discovery of research misconduct.In recent years,paper mills(Mallapaty,2020),faked peer revie...Research integrity has been a focal topic in the global scientific community.Some countries face challenges inherent in the discovery of research misconduct.In recent years,paper mills(Mallapaty,2020),faked peer reviews(Cyranoski,2017)and retracted papers(Stigbrand,2017)in China have attracted extensive attention.This has overshadowed China's progress in research integrity made by the government and the scientific community.Therefore,the objective demonstration of China's progress in research integrity is necessary to help the Chinese and global scientific communities better understand China's achievements in this endeavour.展开更多
To improve the quality of multimedia services and stimulate secure sensing in Internet of Things applications, such as healthcare and traffic monitoring, mobile crowdsensing(MCS) systems must address security threats ...To improve the quality of multimedia services and stimulate secure sensing in Internet of Things applications, such as healthcare and traffic monitoring, mobile crowdsensing(MCS) systems must address security threats such as jamming, spoofing and faked sensing attacks during both sensing and information exchange processes in large-scale dynamic and heterogeneous networks. In this article, we investigate secure mobile crowdsensing and present ways to use deep learning(DL) methods, such as stacked autoencoder, deep neural networks, convolutional neural networks, and deep reinforcement learning, to improve approaches to MCS security, including authentication, privacy protection, faked sensing countermeasures, intrusion detection and anti-jamming transmissions in MCS. We discuss the performance gain of these DLbased approaches compared to traditional security schemes and identify the challenges that must be addressed to implement these approaches in practical MCS systems.展开更多
Indentations onto crystalline silicon and copper with various indenter geometries, loading forces at room temperature belong to the widest interests in the field, because of the physical detection of structural phase ...Indentations onto crystalline silicon and copper with various indenter geometries, loading forces at room temperature belong to the widest interests in the field, because of the physical detection of structural phase transitions. By using the mathematically deduced F<sub>N</sub>h<sup>3/2 </sup>relation for conical and pyramidal indentations we have a toolbox for deciding between faked and experimental loading curves. Four printed silicon indentation loading curves (labelled with 292 K, 260 K, 240 K and 210 K) proved to be faked and not experimental. This is problematic for the AI (artificial intelligence) that will probably not be able to sort faked data out by itself but must be told to do so. High risks arise, when published faked indentation reports remain unidentified and unreported for the mechanics engineers by reading, or via AI. For example, when AI recommends a faked quality such as “no phase changes” of a technical material that is therefore used, it might break down due to an actually present low force, low transition energy phase-change. This paper thus installed a tool box for the distinction of experimental and faked loading curves of indentations. We found experimental and faked loading curves of the same research group with overall 14 authoring co-workers in three publications where valid and faked ones were next to each other and I can thus only report on the experimental ones. The comparison of Si and Cu with W at 20-fold higher physical hardness shows its enormous influence to the energies of phase transition and of their transition energies. Thus, the commonly preferred ISO14577-ASTM hardness values HISO (these violate the energy law and are simulated!) leads to almost blind characterization and use of mechanically stressed technical materials (e.g. airplanes, windmills, bridges, etc). The reasons are carefully detected and reported to disprove that the coincidence or very close coincidence of all of the published loading curves from 150 K to 298 K are constructed but not experimental. A tool-box for distinction of experimental from faked indentation loading curves (simulations must be indicated) is established in view of protecting the AI from faked data, which it might not be able by itself to sort them out, so that technical materials with wrongly attributed mechanical properties might lead to catastrophic accidents such as all of us know of. There is also the risk that false theories might lead to discourage the design of important research projects or for not getting them granted. This might for example hamper or ill-fame new low temperature indentation projects. The various hints for identifying faked claims are thus presented in great detail. The low-temperature instrumental indentations onto silicon have been faked in two consecutive publications and their reporting in the third one, so that these are not available for the calculation of activation energies. Conversely, the same research group published an indentation loading curve of copper as taken at 150 K that could be tested for its validity with the therefore created tools of validity tests. The physical algebraic calculations provided the epochal detection of two highly exothermic phase transitions of copper that created two polymorphs with negative standard energy content. This is world-wide the second case and the first one far above the 77 K of liquid nitrogen. Its existence poses completely new thoughts for physics chemistry and perhaps techniques but all of them are open and unprepared for our comprehension. The first chemical reactions might be in-situ photolysis and the phase transitions can be calculated from experimental curves. But several further reported low temperature indentation loading curves of silicon were tested for their experimental reality. And the results are compared to new analyses with genuine room temperature results. A lot is to be learned from the differences at room and low temperature.展开更多
文摘The search for mechanical properties of materials reached a highly acclaimed level, when indentations could be analysed on the basis of elastic theory for hardness and elastic modulus. The mathematical formulas proved to be very complicated, and various trials were published between the 1900s and 2000s. The development of indentation instruments and the wish to make the application in numerous steps easier, led in 1992 to trials with iterations by using relative values instead of absolute ones. Excessive iterations of computers with 3 + 8 free parameters of the loading and unloading curves became possible and were implemented into the instruments and worldwide standards. The physical formula for hardness was defined as force over area. For the conical, pyramidal, and spherical indenters, one simply took the projected area for the calculation of the indentation depth from the projected area, adjusted it later by the iterations with respect to fused quartz or aluminium as standard materials, and called it “contact height”. Continuously measured indentation loading curves were formulated as loading force over depth square. The unloading curves after release of the indenter used the initial steepness of the pressure relief for the calculation of what was (and is) incorrectly called “Young’s modulus”. But it is not unidirectional. And for the spherical indentations’ loading curve, they defined the indentation force over depth raised to 3/2 (but without R/h correction). They till now (2025) violate the energy law, because they use all applied force for the indenter depth and ignore the obvious sidewise force upon indentation (cf. e.g. the wood cleaving). The various refinements led to more and more complicated formulas that could not be reasonably calculated with them. One decided to use 3 + 8 free-parameter iterations for fitting to the (poor) standards of fused quartz or aluminium. The mechanical values of these were considered to be “true”. This is till now the worldwide standard of DIN-ISO-ASTM-14577, avoiding overcomplicated formulas with their complexity. Some of these are shown in the Introduction Section. By doing so, one avoided the understanding of indentation results on a physical basis. However, we open a simple way to obtain absolute values (though still on the blackbox instrument’s unsuitable force calibration). We do not iterate but calculate algebraically on the basis of the correct, physically deduced exponent of the loading force parabolas with h3/2 instead of false “h2” (for the spherical indentation, there is a calotte-radius over depth correction), and we reveal the physical errors taken up in the official worldwide “14577-Standard”. Importantly, we reveal the hitherto fully overlooked phase transitions under load that are not detectable with the false exponent. Phase-transition twinning is even present and falsifies the iteration standards. Instead of elasticity theory, we use the well-defined geometry of these indentations. By doing so, we reach simple algebraically calculable formulas and find the physical indentation hardness of materials with their onset depth, onset force and energy, as well as their phase-transition energy (temperature dependent also its activation energy). The most important phase transitions are our absolute algebraically calculated results. The now most easily obtained phase transitions under load are very dangerous because they produce polymorph interfaces between the changed and the unchanged material. It was found and published by high-enlargement microscopy (5000-fold) that these trouble spots are the sites for the development of stable, 1 to 2 µm long, micro-cracks (stable for months). If however, a force higher than the one of their formation occurs to them, these grow to catastrophic crash. That works equally with turbulences at the pickle fork of airliners. After the publication of these facts and after three fatal crashing had occurred in a short sequence, FAA (Federal Aviation Agency) reacted by rechecking all airplanes for such micro cracks. These were now found in a new fleet of airliners from where the three crashed ones came. These were previously overlooked. FAA became aware of that risk and grounded 290 (certainly all) of them, because the material of these did not have higher phase-transition onset and energy than other airplanes with better material. They did so despite the 14577-Standard that does not find (and thus formally forbids) phase transitions under indenter load with the false exponent on the indentation parabola. However, this “Standard” will, despite the present author’s well-founded petition, not be corrected for the next 5 years.
基金supported in part by National Natural Science Foundation of China(62271096,U20A20157)Natural Science Foundation of Chongqing,China(cstc2020jcyj-zdxmX0024,CSTB2022NSCQMSX0600)+5 种基金University Innovation Research Group of Chongqing(CXQT20017)Program for Innovation Team Building at Institutions of Higher Education in Chongqing(CXTDX201601020)Science and Technology Research Program of Chongqing Municipal Education Commission(KJQN202000626)Youth Innovation Group Support Program of ICE Discipline of CQUPT(SCIE-QN-2022-04)the Science and Technology Research Program of Chongqing Municipal Education Commission under Grant KJQN202000626Chongqing Municipal Technology Innovation and Application Development Special Key Project(cstc2020jscx-dxwtBX0053)。
文摘Cyber-Physical Networks(CPN)are comprehensive systems that integrate information and physical domains,and are widely used in various fields such as online social networking,smart grids,and the Internet of Vehicles(IoV).With the increasing popularity of digital photography and Internet technology,more and more users are sharing images on CPN.However,many images are shared without any privacy processing,exposing hidden privacy risks and making sensitive content easily accessible to Artificial Intelligence(AI)algorithms.Existing image sharing methods lack fine-grained image sharing policies and cannot protect user privacy.To address this issue,we propose a social relationship-driven privacy customization protection model for publishers and co-photographers.We construct a heterogeneous social information network centered on social relationships,introduce a user intimacy evaluation method with time decay,and evaluate privacy levels considering user interest similarity.To protect user privacy while maintaining image appreciation,we design a lightweight face-swapping algorithm based on Generative Adversarial Network(GAN)to swap faces that need to be protected.Our proposed method minimizes the loss of image utility while satisfying privacy requirements,as shown by extensive theoretical and simulation analyses.
文摘NCPA Children’s Opera Commission Effendi&His Double.Date:May 23-June 1,2025,Venue:National Center for the Performing Arts.The opera tells a story about a figure named Effendi waging a battle of wits against his double in Sun City.He maintains justice by punishing the fake Effendi,who cheats the citizens of Sun City.
文摘The rapid development and widespread adoption of massive open online courses(MOOCs)have indeed had a significant impact on China’s education curriculum.However,the problem of fake reviews and ratings on the platform has seriously affected the authenticity of course evaluations and user trust,requiring effective anomaly detection techniques for screening.The textual characteristics of MOOCs reviews,such as varying lengths and diverse emotional tendencies,have brought complexity to text analysis.Traditional rule-based analysis methods are often inadequate in dealing with such unstructured data.We propose a Differential Privacy-Enabled Text Convolutional Neural Network(DP-TextCNN)framework,aiming to achieve high-precision identification of outliers in MOOCs course reviews and ratings while protecting user privacy.This framework leverages the advantages of Convolutional Neural Networks(CNN)in text feature extraction and combines differential privacy techniques.It balances data privacy protection with model performance by introducing controlled random noise during the data preprocessing stage.By embedding differential privacy into the model training process,we ensure the privacy security of the framework when handling sensitive data,while maintaining a high recognition accuracy.Experimental results indicate that the DP-TextCNN framework achieves an exceptional accuracy of over 95%in identifying fake reviews on the dataset,this outcome not only verifies the applicability of differential privacy techniques in TextCNN but also underscores its potential in handling sensitive educational data.Additionally,we analyze the specific impact of differential privacy parameters on framework performance,offering theoretical support and empirical analysis to strike an optimal balance between privacy protection and framework efficiency.
文摘This article is a part of a larger study called The Abstract Truth of Media focused on the topic of the fictional media content opinions presented and perceived as truth.It will explore the abstract nature of truth in online media and its different forms.These media truths are types of fictional stories with certain effects on the public rather than a truthful presentation of the facts.Thus,the end goal of mass media today is not to tell the truth,but to create moral communities based on common experience and beliefs.Articles,opinions,and news in media are seen as a narrative strategy that can be understood only through storytelling analysis.Here the focus is on the understanding of Truth and Untruth in online media as well as the connection of Internet media technology with the increase of disinformation online.The new media model creates hostile groups instead of generating consent for the nation-state,the new online media model within through,Pseudo-communication,manipulation,delusion,lies,propaganda,and deliberate causing of moral anger.“The end of the truth”means that the truth on the Internet is lost among the vast amount of information and the lack of regulation regarding the correctness of the published data.Instead of truth,media researchers formally talk about post-truth,fake news,and“alternative facts”.Truth on the Internet is more like“Truthiness”or a belief that a statement is true based on the intuition or understanding of individuals,regardless of evidence,logic or facts.The subject of research is the connection between every new technology in mass media and the truth of the information and the effects on the consensus in society.Since the beginning of the 21st century,misinformation on the Internet has increased with the development of online media and social networks,and it is a problem of social peace and consent in every country.
基金funded by Umm Al-Qura University,Saudi Arabia under grant number:25UQU4300346GSSR05.
文摘These days,social media has grown to be an integral part of people’s lives.However,it involves the possibility of exposure to“fake news”,which may contain information that is intentionally or inaccurately false to promote particular political or economic interests.The main objective of this work is to use the co-attention mechanism in a Combined Graph neural network model(CMCG)to capture the relationship between user profile features and user preferences in order to detect fake news and examine the influence of various social media features on fake news detection.The proposed approach includes three modules.The first one creates a Graph Neural Network(GNN)based model to learn user profile properties,while the second module encodes news content,user historical posts,and news sharing cascading on social media as user preferences GNN-based model.The inter-dependencies between user profiles and user preferences are handled through the third module using a co-attention mechanism for capturing the relationship between the two GNN-based models.We conducted several experiments on two commonly used fake news datasets,Politifact and Gossipcop,where our approach achieved 98.53%accuracy on the Gossipcop dataset and 96.77%accuracy on the Politifact dataset.These results illustrate the effectiveness of the CMCG approach for fake news detection,as it combines various information from different modalities to achieve relatively high performances.
基金supported by the National Key R&D Program of China(Grant No.2022YFB3104601)the Big Data Computing Center of Southeast University.
文摘Social media has significantly accelerated the rapid dissemination of information,but it also boosts propagation of fake news,posing serious challenges to public awareness and social stability.In real-world contexts,the volume of trustable information far exceeds that of rumors,resulting in a class imbalance that leads models to prioritize the majority class during training.This focus diminishes the model’s ability to recognize minority class samples.Furthermore,models may experience overfitting when encountering these minority samples,further compromising their generalization capabilities.Unlike node-level classification tasks,fake news detection in social networks operates on graph-level samples,where traditional interpolation and oversampling methods struggle to effectively generate high-quality graph-level samples.This challenge complicates the identification of new instances of false information.To address this issue,this paper introduces the FHGraph(Fake News Hunting Graph)framework,which employs a generative data augmentation approach and a latent diffusion model to create graph structures that align with news communication patterns.Using the few-sample learning capabilities of large language models(LLMs),the framework generates diverse texts for minority class nodes.FHGraph comprises a hierarchical multiview graph contrastive learning module,in which two horizontal views and three vertical levels are utilized for self-supervised learning,resulting in more optimized representations.Experimental results show that FHGraph significantly outperforms state-of-the-art(SOTA)graph-level class imbalance methods and SOTA graph-level contrastive learning methods.Specifically,FHGraph has achieved a 2%increase in F1 Micro and a 2.5%increase in F1 Macro in the PHEME dataset,as well as a 3.5%improvement in F1 Micro and a 4.3%improvement in F1 Macro on RumorEval dataset.
基金supported by Communication University of China(HG23035)partly supported by the Fundamental Research Funds for the Central Universities(CUC230A013).
文摘With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant harm.As social media content is often composed of both images and text,the use of multimodal approaches for fake news detection has gained significant attention.To solve the problems existing in previous multi-modal fake news detection algorithms,such as insufficient feature extraction and insufficient use of semantic relations between modes,this paper proposes the MFFFND-Co(Multimodal Feature Fusion Fake News Detection with Co-Attention Block)model.First,the model deeply explores the textual content,image content,and frequency domain features.Then,it employs a Co-Attention mechanism for cross-modal fusion.Additionally,a semantic consistency detectionmodule is designed to quantify semantic deviations,thereby enhancing the performance of fake news detection.Experimentally verified on two commonly used datasets,Twitter and Weibo,the model achieved F1 scores of 90.0% and 94.0%,respectively,significantly outperforming the pre-modified MFFFND(Multimodal Feature Fusion Fake News Detection with Attention Block)model and surpassing other baseline models.This improves the accuracy of detecting fake information in artificial intelligence detection and engineering software detection.
基金the National Natural Science Foundation of China(No.62302540)with author F.F.S.For more information,please visit their website at https://www.nsfc.gov.cn/.Additionally,it is also funded by the Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness(No.HNTS2022020)+1 种基金where F.F.S is an author.Further details can be found at http://xt.hnkjt.gov.cn/data/pingtai/.The research is also supported by the Natural Science Foundation of Henan Province Youth Science Fund Project(No.232300420422)for more information,you can visit https://kjt.henan.gov.cn/2022/09-02/2599082.html.Lastly,it receives funding from the Natural Science Foundation of Zhongyuan University of Technology(No.K2023QN018),where F.F.S is an author.You can find more information at https://www.zut.edu.cn/.
文摘As social networks become increasingly complex, contemporary fake news often includes textual descriptionsof events accompanied by corresponding images or videos. Fake news in multiple modalities is more likely tocreate a misleading perception among users. While early research primarily focused on text-based features forfake news detection mechanisms, there has been relatively limited exploration of learning shared representationsin multimodal (text and visual) contexts. To address these limitations, this paper introduces a multimodal modelfor detecting fake news, which relies on similarity reasoning and adversarial networks. The model employsBidirectional Encoder Representation from Transformers (BERT) and Text Convolutional Neural Network (Text-CNN) for extracting textual features while utilizing the pre-trained Visual Geometry Group 19-layer (VGG-19) toextract visual features. Subsequently, the model establishes similarity representations between the textual featuresextracted by Text-CNN and visual features through similarity learning and reasoning. Finally, these features arefused to enhance the accuracy of fake news detection, and adversarial networks have been employed to investigatethe relationship between fake news and events. This paper validates the proposed model using publicly availablemultimodal datasets from Weibo and Twitter. Experimental results demonstrate that our proposed approachachieves superior performance on Twitter, with an accuracy of 86%, surpassing traditional unimodalmodalmodelsand existing multimodal models. In contrast, the overall better performance of our model on the Weibo datasetsurpasses the benchmark models across multiple metrics. The application of similarity reasoning and adversarialnetworks in multimodal fake news detection significantly enhances detection effectiveness in this paper. However,current research is limited to the fusion of only text and image modalities. Future research directions should aimto further integrate features fromadditionalmodalities to comprehensively represent themultifaceted informationof fake news.
基金Science and Technology Funds from the Liaoning Education Department(Serial Number:LJKZ0104).
文摘The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the CNN.The customized Convolutional Neural Network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its libraries.We used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were real.Ten seconds were allotted for each video.There were 318 videos used in all,199 of which were fake and 119 of which were real.Our proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and MLP-CNN.Furthermore,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and DST-Net.The novelty of this investigation is the development of a new Convolutional Neural Network(CNN)learning model that can accurately detect deep fake face photos.
文摘Online review platforms are becoming increasingly popular,encouraging dishonest merchants and service providers to deceive customers by creating fake reviews for their goods or services.Using Sybil accounts,bot farms,and real account purchases,immoral actors demonize rivals and advertise their goods.Most academic and industry efforts have been aimed at detecting fake/fraudulent product or service evaluations for years.The primary hurdle to identifying fraudulent reviews is the lack of a reliable means to distinguish fraudulent reviews from real ones.This paper adopts a semi-supervised machine learning method to detect fake reviews on any website,among other things.Online reviews are classified using a semi-supervised approach(PU-learning)since there is a shortage of labeled data,and they are dynamic.Then,classification is performed using the machine learning techniques Support Vector Machine(SVM)and Nave Bayes.The performance of the suggested system has been compared with standard works,and experimental findings are assessed using several assessment metrics.
基金The authors are highly thankful to the National Social Science Foundation of China(20BXW101,18XXW015)Innovation Research Project for the Cultivation of High-Level Scientific and Technological Talents(Top-Notch Talents of theDiscipline)(ZZKY2022303)+3 种基金National Natural Science Foundation of China(Nos.62102451,62202496)Basic Frontier Innovation Project of Engineering University of People’s Armed Police(WJX202316)This work is also supported by National Natural Science Foundation of China(No.62172436)Engineering University of PAP’s Funding for Scientific Research Innovation Team,Engineering University of PAP’s Funding for Basic Scientific Research,and Engineering University of PAP’s Funding for Education and Teaching.Natural Science Foundation of Shaanxi Province(No.2023-JCYB-584).
文摘With the rapid spread of Internet information and the spread of fake news,the detection of fake news becomes more and more important.Traditional detection methods often rely on a single emotional or semantic feature to identify fake news,but these methods have limitations when dealing with news in specific domains.In order to solve the problem of weak feature correlation between data from different domains,a model for detecting fake news by integrating domain-specific emotional and semantic features is proposed.This method makes full use of the attention mechanism,grasps the correlation between different features,and effectively improves the effect of feature fusion.The algorithm first extracts the semantic features of news text through the Bi-LSTM(Bidirectional Long Short-Term Memory)layer to capture the contextual relevance of news text.Senta-BiLSTM is then used to extract emotional features and predict the probability of positive and negative emotions in the text.It then uses domain features as an enhancement feature and attention mechanism to fully capture more fine-grained emotional features associated with that domain.Finally,the fusion features are taken as the input of the fake news detection classifier,combined with the multi-task representation of information,and the MLP and Softmax functions are used for classification.The experimental results show that on the Chinese dataset Weibo21,the F1 value of this model is 0.958,4.9% higher than that of the sub-optimal model;on the English dataset FakeNewsNet,the F1 value of the detection result of this model is 0.845,1.8% higher than that of the sub-optimal model,which is advanced and feasible.
基金This research was funded by the General Project of Philosophy and Social Science of Heilongjiang Province,Grant Number:20SHB080.
文摘In recent years,how to efficiently and accurately identify multi-model fake news has become more challenging.First,multi-model data provides more evidence but not all are equally important.Secondly,social structure information has proven to be effective in fake news detection and how to combine it while reducing the noise information is critical.Unfortunately,existing approaches fail to handle these problems.This paper proposes a multi-model fake news detection framework based on Tex-modal Dominance and fusing Multiple Multi-model Cues(TD-MMC),which utilizes three valuable multi-model clues:text-model importance,text-image complementary,and text-image inconsistency.TD-MMC is dominated by textural content and assisted by image information while using social network information to enhance text representation.To reduce the irrelevant social structure’s information interference,we use a unidirectional cross-modal attention mechanism to selectively learn the social structure’s features.A cross-modal attention mechanism is adopted to obtain text-image cross-modal features while retaining textual features to reduce the loss of important information.In addition,TD-MMC employs a new multi-model loss to improve the model’s generalization ability.Extensive experiments have been conducted on two public real-world English and Chinese datasets,and the results show that our proposed model outperforms the state-of-the-art methods on classification evaluation metrics.
基金supported by the National Natural Science Foundation of China(No.62302540)with author Fangfang Shan.For more information,please visit their website at https://www.nsfc.gov.cn/(accessed on 31/05/2024)+3 种基金Additionally,it is also funded by the Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness(No.HNTS2022020)where Fangfang Shan is an author.Further details can be found at http://xt.hnkjt.gov.cn/data/pingtai/(accessed on 31/05/2024)supported by the Natural Science Foundation of Henan Province Youth Science Fund Project(No.232300420422)for more information,you can visit https://kjt.henan.gov.cn/2022/09-02/2599082.html(accessed on 31/05/2024).
文摘Social media has become increasingly significant in modern society,but it has also turned into a breeding ground for the propagation of misleading information,potentially causing a detrimental impact on public opinion and daily life.Compared to pure text content,multmodal content significantly increases the visibility and share ability of posts.This has made the search for efficient modality representations and cross-modal information interaction methods a key focus in the field of multimodal fake news detection.To effectively address the critical challenge of accurately detecting fake news on social media,this paper proposes a fake news detection model based on crossmodal message aggregation and a gated fusion network(MAGF).MAGF first uses BERT to extract cumulative textual feature representations and word-level features,applies Faster Region-based ConvolutionalNeuralNetwork(Faster R-CNN)to obtain image objects,and leverages ResNet-50 and Visual Geometry Group-19(VGG-19)to obtain image region features and global features.The image region features and word-level text features are then projected into a low-dimensional space to calculate a text-image affinity matrix for cross-modal message aggregation.The gated fusion network combines text and image region features to obtain adaptively aggregated features.The interaction matrix is derived through an attention mechanism and further integrated with global image features using a co-attention mechanism to producemultimodal representations.Finally,these fused features are fed into a classifier for news categorization.Experiments were conducted on two public datasets,Twitter and Weibo.Results show that the proposed model achieves accuracy rates of 91.8%and 88.7%on the two datasets,respectively,significantly outperforming traditional unimodal and existing multimodal models.
基金supported by the MSIT(Ministry of Science and ICT),Korea,under the ICT Creative Consilience Program(IITP-2024-2020-0-01819)supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation).
文摘In an era dominated by information dissemination through various channels like newspapers,social media,radio,and television,the surge in content production,especially on social platforms,has amplified the challenge of distinguishing between truthful and deceptive information.Fake news,a prevalent issue,particularly on social media,complicates the assessment of news credibility.The pervasive spread of fake news not only misleads the public but also erodes trust in legitimate news sources,creating confusion and polarizing opinions.As the volume of information grows,individuals increasingly struggle to discern credible content from false narratives,leading to widespread misinformation and potentially harmful consequences.Despite numerous methodologies proposed for fake news detection,including knowledge-based,language-based,and machine-learning approaches,their efficacy often diminishes when confronted with high-dimensional datasets and data riddled with noise or inconsistencies.Our study addresses this challenge by evaluating the synergistic benefits of combining feature extraction and feature selection techniques in fake news detection.We employ multiple feature extraction methods,including Count Vectorizer,Bag of Words,Global Vectors for Word Representation(GloVe),Word to Vector(Word2Vec),and Term Frequency-Inverse Document Frequency(TF-IDF),alongside feature selection techniques such as Information Gain,Chi-Square,Principal Component Analysis(PCA),and Document Frequency.This comprehensive approach enhances the model’s ability to identify and analyze relevant features,leading to more accurate and effective fake news detection.Our findings highlight the importance of a multi-faceted approach,offering a significant improvement in model accuracy and reliability.Moreover,the study emphasizes the adaptability of the proposed ensemble model across diverse datasets,reinforcing its potential for broader application in real-world scenarios.We introduce a pioneering ensemble technique that leverages both machine-learning and deep-learning classifiers.To identify the optimal ensemble configuration,we systematically tested various combinations.Experimental evaluations conducted on three diverse datasets related to fake news demonstrate the exceptional performance of our proposed ensemble model.Achieving remarkable accuracy levels of 97%,99%,and 98%on Dataset 1,Dataset 2,and Dataset 3,respectively,our approach showcases robustness and effectiveness in discerning fake news amidst the complexities of contemporary information landscapes.This research contributes to the advancement of fake news detection methodologies and underscores the significance of integrating feature extraction and feature selection strategies for enhanced performance,especially in the context of intricate,high-dimensional datasets.
文摘Deep learning is a practical and efficient technique that has been used extensively in many domains. Using deep learning technology, deepfakes create fake images of a person that people cannot distinguish from the real one. Recently, many researchers have focused on understanding how deepkakes work and detecting using deep learning approaches. This paper introduces an explainable deepfake framework for images creation and classification. The framework consists of three main parts: the first approach is called Instant ID which is used to create deepfacke images from the original one;the second approach called Xception classifies the real and deepfake images;the third approach called Local Interpretable Model (LIME) provides a method for interpreting the predictions of any machine learning model in a local and interpretable manner. Our study proposes deepfake approach that achieves 100% precision and 100% accuracy for deepfake creation and classification. Furthermore, the results highlight the superior performance of the proposed model in deep fake creation and classification.
文摘Reviews have a significant impact on online businesses.Nowadays,online consumers rely heavily on other people’s reviews before purchasing a product,instead of looking at the product description.With the emergence of technology,malicious online actors are using techniques such as Natural Language Processing(NLP)and others to generate a large number of fake reviews to destroy their competitors’markets.To remedy this situation,several researches have been conducted in the last few years.Most of them have applied NLP techniques to preprocess the text before building Machine Learning(ML)or Deep Learning(DL)models to detect and filter these fake reviews.However,with the same NLP techniques,machine-generated fake reviews are increasing exponentially.This work explores a powerful text representation technique called Embedding models to combat the proliferation of fake reviews in online marketplaces.Indeed,these embedding structures can capture much more information from the data compared to other standard text representations.To do this,we tested our hypothesis in two different Recurrent Neural Network(RNN)architectures,namely Long Short-Term Memory(LSTM)and Gated Recurrent Unit(GRU),using fake review data from Amazon and TripAdvisor.Our experimental results show that our best-proposed model can distinguish between real and fake reviews with 91.44%accuracy.Furthermore,our results corroborate with the state-of-the-art research in this area and demonstrate some improvements over other approaches.Therefore,proper text representation improves the accuracy of fake review detection.
文摘Research integrity has been a focal topic in the global scientific community.Some countries face challenges inherent in the discovery of research misconduct.In recent years,paper mills(Mallapaty,2020),faked peer reviews(Cyranoski,2017)and retracted papers(Stigbrand,2017)in China have attracted extensive attention.This has overshadowed China's progress in research integrity made by the government and the scientific community.Therefore,the objective demonstration of China's progress in research integrity is necessary to help the Chinese and global scientific communities better understand China's achievements in this endeavour.
基金supported in part by the National Natural Science Foundation of China under Grant 61671396 and 91638204in part by the open research fund of National Mobile Communications Research Laboratory,Southeast University(No.2018D08)in part by Science and Technology Innovation Project of Foshan City,China(Grant No.2015IT100095)
文摘To improve the quality of multimedia services and stimulate secure sensing in Internet of Things applications, such as healthcare and traffic monitoring, mobile crowdsensing(MCS) systems must address security threats such as jamming, spoofing and faked sensing attacks during both sensing and information exchange processes in large-scale dynamic and heterogeneous networks. In this article, we investigate secure mobile crowdsensing and present ways to use deep learning(DL) methods, such as stacked autoencoder, deep neural networks, convolutional neural networks, and deep reinforcement learning, to improve approaches to MCS security, including authentication, privacy protection, faked sensing countermeasures, intrusion detection and anti-jamming transmissions in MCS. We discuss the performance gain of these DLbased approaches compared to traditional security schemes and identify the challenges that must be addressed to implement these approaches in practical MCS systems.
文摘Indentations onto crystalline silicon and copper with various indenter geometries, loading forces at room temperature belong to the widest interests in the field, because of the physical detection of structural phase transitions. By using the mathematically deduced F<sub>N</sub>h<sup>3/2 </sup>relation for conical and pyramidal indentations we have a toolbox for deciding between faked and experimental loading curves. Four printed silicon indentation loading curves (labelled with 292 K, 260 K, 240 K and 210 K) proved to be faked and not experimental. This is problematic for the AI (artificial intelligence) that will probably not be able to sort faked data out by itself but must be told to do so. High risks arise, when published faked indentation reports remain unidentified and unreported for the mechanics engineers by reading, or via AI. For example, when AI recommends a faked quality such as “no phase changes” of a technical material that is therefore used, it might break down due to an actually present low force, low transition energy phase-change. This paper thus installed a tool box for the distinction of experimental and faked loading curves of indentations. We found experimental and faked loading curves of the same research group with overall 14 authoring co-workers in three publications where valid and faked ones were next to each other and I can thus only report on the experimental ones. The comparison of Si and Cu with W at 20-fold higher physical hardness shows its enormous influence to the energies of phase transition and of their transition energies. Thus, the commonly preferred ISO14577-ASTM hardness values HISO (these violate the energy law and are simulated!) leads to almost blind characterization and use of mechanically stressed technical materials (e.g. airplanes, windmills, bridges, etc). The reasons are carefully detected and reported to disprove that the coincidence or very close coincidence of all of the published loading curves from 150 K to 298 K are constructed but not experimental. A tool-box for distinction of experimental from faked indentation loading curves (simulations must be indicated) is established in view of protecting the AI from faked data, which it might not be able by itself to sort them out, so that technical materials with wrongly attributed mechanical properties might lead to catastrophic accidents such as all of us know of. There is also the risk that false theories might lead to discourage the design of important research projects or for not getting them granted. This might for example hamper or ill-fame new low temperature indentation projects. The various hints for identifying faked claims are thus presented in great detail. The low-temperature instrumental indentations onto silicon have been faked in two consecutive publications and their reporting in the third one, so that these are not available for the calculation of activation energies. Conversely, the same research group published an indentation loading curve of copper as taken at 150 K that could be tested for its validity with the therefore created tools of validity tests. The physical algebraic calculations provided the epochal detection of two highly exothermic phase transitions of copper that created two polymorphs with negative standard energy content. This is world-wide the second case and the first one far above the 77 K of liquid nitrogen. Its existence poses completely new thoughts for physics chemistry and perhaps techniques but all of them are open and unprepared for our comprehension. The first chemical reactions might be in-situ photolysis and the phase transitions can be calculated from experimental curves. But several further reported low temperature indentation loading curves of silicon were tested for their experimental reality. And the results are compared to new analyses with genuine room temperature results. A lot is to be learned from the differences at room and low temperature.
