Architecture framework has become an effective method recently to describe the system of systems(SoS)architecture,such as the United States(US)Department of Defense Architecture Framework Version 2.0(DoDAF2.0).As a vi...Architecture framework has become an effective method recently to describe the system of systems(SoS)architecture,such as the United States(US)Department of Defense Architecture Framework Version 2.0(DoDAF2.0).As a viewpoint in DoDAF2.0,the operational viewpoint(OV)describes operational activities,nodes,and resource flows.The OV models are important for SoS architecture development.However,as the SoS complexity increases,constructing OV models with traditional methods exposes shortcomings,such as inefficient data collection and low modeling standards.Therefore,we propose an intelligent modeling method for five OV models,including operational resource flow OV-2,organizational relationships OV-4,operational activity hierarchy OV-5a,operational activities model OV-5b,and operational activity sequences OV-6c.The main idea of the method is to extract OV architecture data from text and generate interoperable OV models.First,we construct the OV meta model based on the DoDAF2.0 meta model(DM2).Second,OV architecture named entities is recognized from text based on the bidirectional long short-term memory and conditional random field(BiLSTM-CRF)model.And OV architecture relationships are collected with relationship extraction rules.Finally,we define the generation rules for OV models and develop an OV modeling tool.We use unmanned surface vehicles(USV)swarm target defense SoS architecture as a case to verify the feasibility and effectiveness of the intelligent modeling method.展开更多
Data-driven approaches are extensively employed to model complex chemical engineering processes, such as hydrotreating, to address the challenges of mechanism-based methods demanding deep process understanding. Howeve...Data-driven approaches are extensively employed to model complex chemical engineering processes, such as hydrotreating, to address the challenges of mechanism-based methods demanding deep process understanding. However, the development of such models requires specialized expertise in data science, limiting their broader application. Large language models (LLMs), such as GPT-4, have demonstrated potential in supporting and guiding research efforts. This work presents a novel AI-assisted framework where GPT-4, through well-engineered prompts, facilitates the construction and explanation of multi-objective neural networks. These models predict hydrotreating products properties (such as distillation range), including refined diesel and refined gas oil, using feedstock properties, operating conditions, and recycle hydrogen composition. Gradient-weighted class activation mapping was employed to identify key features influencing the output variables. This work illustrates an innovative AI-guided paradigm for chemical engineering applications, and the designed prompts hold promise for adaptation to other complex processes.展开更多
Dear Editor,This letter deals with automatically constructing an OPC UA information model(IM)aimed at enhancing data interoperability among heterogeneous system components within manufacturing automation systems.Empow...Dear Editor,This letter deals with automatically constructing an OPC UA information model(IM)aimed at enhancing data interoperability among heterogeneous system components within manufacturing automation systems.Empowered by the large language model(LLM),we propose a novel multi-agent collaborative framework to streamline the end-to-end OPC UA IM modeling process.Each agent is equipped with meticulously engineered prompt templates,augmenting their capacity to execute specific tasks.We conduct modeling experiments using real textual data to demonstrate the effectiveness of the proposed method,improving modeling efficiency and reducing the labor workload.展开更多
Machine translation of low-resource languages(LRLs)has long been hindered by limited corpora and linguistic complexity.This review summarizes key developments,from traditional methods to recent progress with large lan...Machine translation of low-resource languages(LRLs)has long been hindered by limited corpora and linguistic complexity.This review summarizes key developments,from traditional methods to recent progress with large language models(LLMs),while highlighting ongoing challenges such as data bottlenecks,biases,fairness,and computational costs.Finally,it discusses future directions,including efficient parameter fine-tuning,multimodal translation,and community-driven corpus construction,providing insights for advancing LRL translation research.展开更多
Short Message Service(SMS)is a widely used and cost-effective communication medium that has unfortunately become a frequent target for unsolicited messages-commonly known as SMS spam.With the rapid adoption of smartph...Short Message Service(SMS)is a widely used and cost-effective communication medium that has unfortunately become a frequent target for unsolicited messages-commonly known as SMS spam.With the rapid adoption of smartphones and increased Internet connectivity,SMS spam has emerged as a prevalent threat.Spammers have recognized the critical role SMS plays in today’s modern communication,making it a prime target for abuse.As cybersecurity threats continue to evolve,the volume of SMS spam has increased substantially in recent years.Moreover,the unstructured format of SMS data creates significant challenges for SMS spam detection,making it more difficult to successfully combat spam attacks.In this paper,we present an optimized and fine-tuned transformer-based Language Model to address the problem of SMS spam detection.We use a benchmark SMS spam dataset to analyze this spam detection model.Additionally,we utilize pre-processing techniques to obtain clean and noise-free data and address class imbalance problem by leveraging text augmentation techniques.The overall experiment showed that our optimized fine-tuned BERT(Bidirectional Encoder Representations from Transformers)variant model RoBERTa obtained high accuracy with 99.84%.To further enhance model transparency,we incorporate Explainable Artificial Intelligence(XAI)techniques that compute positive and negative coefficient scores,offering insight into the model’s decision-making process.Additionally,we evaluate the performance of traditional machine learning models as a baseline for comparison.This comprehensive analysis demonstrates the significant impact language models can have on addressing complex text-based challenges within the cybersecurity landscape.展开更多
Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLM...Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLMs.Therefore,in order to better assess the capability of LLMs in the agricultural domain,Agri-Eval was proposed as a benchmark for assessing the knowledge and reasoning ability of LLMs in agriculture.The assessment dataset used in Agri-Eval covered seven major disciplines in the agricultural domain:crop science,horticulture,plant protection,animal husbandry,forest science,aquaculture science,and grass science,and contained a total of 2283 questions.Among domestic general-purpose LLMs,DeepSeek R1 performed best with an accuracy rate of 75.49%.In the realm of international general-purpose LLMs,Gemini 2.0 pro exp 0205 standed out as the top performer,achieving an accuracy rate of 74.28%.As an LLMs in agriculture vertical,Shennong V2.0 outperformed all the LLMs in China,and the answer accuracy rate of agricultural knowledge exceeded that of all the existing general-purpose LLMs.The launch of Agri-Eval helped the LLM developers to comprehensively evaluate the model's capability in the field of agriculture through a variety of tasks and tests to promote the development of the LLMs in the field of agriculture.展开更多
Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interact...Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interactions to predict future items of interest.However,many current methods rely on unique user and item IDs,limiting their ability to represent users and items effectively,especially in zero-shot learning scenarios where training data is scarce.With the rapid development of Large Language Models(LLMs),researchers are exploring their potential to enhance recommendation systems.However,there is a semantic gap between the linguistic semantics of LLMs and the collaborative semantics of recommendation systems,where items are typically indexed by IDs.Moreover,most research focuses on item representations,neglecting personalized user modeling.To address these issues,we propose a sequential recommendation framework using LLMs,called CIT-Rec,a model that integrates Collaborative semantics for user representation and Image and Text information for item representation to enhance Recommendations.Specifically,by aligning intuitive image information with text containing semantic features,we can more accurately represent items,improving item representation quality.We focus not only on item representations but also on user representations.To more precisely capture users’personalized preferences,we use traditional sequential recommendation models to train on users’historical interaction data,effectively capturing behavioral patterns.Finally,by combining LLMs and traditional sequential recommendation models,we allow the LLM to understand linguistic semantics while capturing collaborative semantics.Extensive evaluations on real-world datasets show that our model outperforms baseline methods,effectively combining user interaction history with item visual and textual modalities to provide personalized recommendations.展开更多
The emergence of large language models(LLMs)has brought about revolutionary social value.However,concerns have arisen regarding the generation of deceptive content by LLMs and their potential for misuse.Consequently,a...The emergence of large language models(LLMs)has brought about revolutionary social value.However,concerns have arisen regarding the generation of deceptive content by LLMs and their potential for misuse.Consequently,a crucial research question arises:How can we differentiate between AI-generated and human-authored text?Existing detectors face some challenges,such as operating as black boxes,relying on supervised training,and being vulnerable to manipulation and misinformation.To tackle these challenges,we propose an innovative unsupervised white-box detection method that utilizes a“dual-driven verification mechanism”to achieve high-performance detection,even in the presence of obfuscated attacks in the text content.To be more specific,we initially employ the SpaceInfi strategy to enhance the difficulty of detecting the text content.Subsequently,we randomly select vulnerable spots from the text and perturb them using another pre-trained language model(e.g.,T5).Finally,we apply a dual-driven defense mechanism(D3M)that validates text content with perturbations,whether generated by a model or authored by a human,based on the dimensions of Information TransmissionQuality and Information TransmissionDensity.Through experimental validation,our proposed novelmethod demonstrates state-of-the-art(SOTA)performancewhen exposed to equivalent levels of perturbation intensity across multiple benchmarks,thereby showcasing the effectiveness of our strategies.展开更多
Liver transplantation(LT)remains the optimal life-saving intervention for patients with end-stage liver disease.Despite the recent advances in LT several barriers,including organ allocation,donor-recipient matching,an...Liver transplantation(LT)remains the optimal life-saving intervention for patients with end-stage liver disease.Despite the recent advances in LT several barriers,including organ allocation,donor-recipient matching,and patient education,persist.With the growing progress of artificial intelligence,particularly large language models(LLMs)like ChatGPT,new applications have emerged in the field of LT.Current studies demonstrating usage of ChatGPT in LT include various areas of application,from clinical settings to research and education.ChatGPT usage can benefit both healthcare professionals,by decreasing the time spent on non-clinical work,but also LT recipients by providing accurate information.Future potential applications include the expanding usage of ChatGPT and other LLMs in the field of LT pathology and radiology as well as the automated creation of discharge summaries or other related paperwork.Additionally,the next models of ChatGPT might have the potential to provide more accurate patient education material with increased readability.Although ChatGPT usage presents promising applications,there are certain ethical and practical limitations.Key concerns include patient data privacy,information accuracy,misinformation possibility and lack of legal framework.Healthcare providers and policymakers should collaborate for the establishment of a controlled framework for the safe use of ChatGPT.The aim of this minireview is to summarize current literature on ChatGPT in LT,highlighting both opportunities and limitations,while also providing future possible applications.展开更多
This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to use...This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to user behavior and platform-driven moderation on social media.The proposed methodological framework(1)utilizes large language models for social media post analysis and categorization,(2)employs k-means clustering for content characterization,and(3)incorporates the TODIM(Tomada de Decisão Interativa Multicritério)method to determine moderation strategies based on expert judgments.In general,the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation of large-scale decision problems.When applied in social media moderation,this approach promotes nuanced and context-sensitive self-moderation by taking into account factors such as cultural background and geographic location.The application of this framework is demonstrated within Facebook groups.Eight distinct content clusters encompassing safety,harassment,diversity,and misinformation are identified.Analysis revealed a preference for content removal across all clusters,suggesting a cautious approach towards potentially harmful content.However,the framework also highlights the use of other moderation actions,like account suspension,depending on the content category.These findings contribute to the growing body of research on self-moderation and offer valuable insights for creating safer and more inclusive online spaces within smaller communities.展开更多
Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Re...Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.展开更多
Although Named Entity Recognition(NER)in cybersecurity has historically concentrated on threat intelligence,vital security data can be found in a variety of sources,such as open-source intelligence and unprocessed too...Although Named Entity Recognition(NER)in cybersecurity has historically concentrated on threat intelligence,vital security data can be found in a variety of sources,such as open-source intelligence and unprocessed tool outputs.When dealing with technical language,the coexistence of structured and unstructured data poses serious issues for traditional BERT-based techniques.We introduce a three-phase approach for improved NER inmulti-source cybersecurity data that makes use of large language models(LLMs).To ensure thorough entity coverage,our method starts with an identification module that uses dynamic prompting techniques.To lessen hallucinations,the extraction module uses confidence-based self-assessment and cross-checking using regex validation.The tagging module links to knowledge bases for contextual validation and uses SecureBERT in conjunction with conditional random fields to detect entity boundaries precisely.Our framework creates efficient natural language segments by utilizing decoderbased LLMs with 10B parameters.When compared to baseline SecureBERT implementations,evaluation across four cybersecurity data sources shows notable gains,with a 9.4%–25.21%greater recall and a 6.38%–17.3%better F1-score.Our refined model matches larger models and achieves 2.6%–4.9%better F1-score for technical phrase recognition than the state-of-the-art alternatives Claude 3.5 Sonnet,Llama3-8B,and Mixtral-7B.The three-stage architecture identification-extraction-tagging pipeline tackles important cybersecurity NER issues.Through effective architectures,these developments preserve deployability while setting a new standard for entity extraction in challenging security scenarios.The findings show how specific enhancements in hybrid recognition,validation procedures,and prompt engineering raise NER performance above monolithic LLM approaches in cybersecurity applications,especially for technical entity extraction fromheterogeneous sourceswhere conventional techniques fall short.Because of itsmodular nature,the framework can be upgraded at the component level as new methods are developed.展开更多
BACKGROUND:To provide a comprehensive analysis of the landscape of artifi cial intelligence(AI)applications in cardiac arrest(CA).METHODS:Comprehensive searches were conducted in PubMed,the Cochrane Library,Webof Scie...BACKGROUND:To provide a comprehensive analysis of the landscape of artifi cial intelligence(AI)applications in cardiac arrest(CA).METHODS:Comprehensive searches were conducted in PubMed,the Cochrane Library,Webof Science,and EMBASE from database inception through 10 June 2025.Studies that applied AI inboth in-hospital cardiac arrest(IHCA)and out-of-hospital cardiac arrest(OHCA)populations acrossthe following domains were included:prediction of cardiac arrest occurrence,prognostication ofCA outcomes,applications of large language models(LLMs),and evaluation of cardiopulmonaryresuscitation(CPR)and other AI-driven interventions related to CA.RESULTS:The scoping review included 114 studies,encompassing data from 9,574,462patients in total.AI was most commonly applied to the prediction of CA(overall,n=40;IHCA,n=30;OHCA,n=4;and both,n=6),CPR-related decision support during CA(n=16),and post-arrestprognosis and rehabilitation outcomes(overall,n=38;OHCA,n=21;IHCA,n=3;and both,n=14).Additional application areas included LLM-based applications(n=8),emergency call handling(n=4),wearable device-based detection(n=3),heart rhythm identification(n=2),education(n=2),and extracorporeal cardiopulmonary resuscitation(ECPR)candidate identifi cation(n=1).Across allapplication scenarios,the highest area under the receiver operating characteristic curve(AUROC)value for pre-arrest CA prediction in IHCA patients was 0.998 using a multilayer perceptron(MLP)model,whereas the optimal AUROC for pre-arrest CA prediction in OHCA patients was 0.950 usingextreme gradient boosting(XGBoost)or random forest(RF)models.For CPR-related decisionsupport during CA,the highest AUROC achieved was 0.990 with a convolutional neural network(CNN)model.In prognostic prediction,the optimal AUROC for IHCA patients was 0.960 usingXGBoost,while for OHCA patients it reached 0.976 using an MLP model.CONCLUSION:This review shows that AI is most commonly used for the prediction of CA andCPR-related support,as well as post-arrest and rehabilitation outcomes.Future research directions includedrug discovery,post-resuscitation management,neurorehabilitation,and clinical trial innovation.Furtherstudies should prioritize multicenter clinical trials to evaluate AI models in real-world settings and validatetheir eff ectiveness across diverse patient populations.Overall,AI has signifi cant potential to improve clinicalpractice,and its role in CA application is increasingly important.展开更多
The surge in smishing attacks underscores the urgent need for robust,real-time detection systems powered by advanced deep learning models.This paper introduces PhishNet,a novel ensemble learning framework that integra...The surge in smishing attacks underscores the urgent need for robust,real-time detection systems powered by advanced deep learning models.This paper introduces PhishNet,a novel ensemble learning framework that integrates transformer-based models(RoBERTa)and large language models(LLMs)(GPT-OSS 120B,LLaMA3.370B,and Qwen332B)to enhance smishing detection performance significantly.To mitigate class imbalance,we apply synthetic data augmentation using T5 and leverage various text preprocessing techniques.Our system employs a duallayer voting mechanism:weighted majority voting among LLMs and a final ensemble vote to classify messages as ham,spam,or smishing.Experimental results show an average accuracy improvement from 96%to 98.5%compared to the best standalone transformer,and from 93%to 98.5%when compared to LLMs across datasets.Furthermore,we present a real-time,user-friendly application to operationalize our detection model for practical use.PhishNet demonstrates superior scalability,usability,and detection accuracy,filling critical gaps in current smishing detection methodologies.展开更多
The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness dimin...The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness diminishes in few-shot reasoning scenarios due to the low data efficiency of conventional supervised fine-tuning,which leads to excessive communication overhead.To address this,we propose Language-Empowered Split Fine-Tuning(LESFT),a framework that integrates split architectures with a contrastive-inspired fine-tuning paradigm.LESFT simultaneously learns frommultiple logically equivalent but linguistically diverse reasoning chains,providing richer supervisory signals and improving data efficiency.This process-oriented training allows more effective reasoning adaptation with fewer samples.Extensive experiments demonstrate that LESFT consistently outperforms strong baselines such as SplitLoRA in task accuracy.LESFT consistently outperforms strong baselines on GSM8K,CommonsenseQA,and AQUA_RAT,with the largest gains observed on Qwen2.5-3B.These results indicate that LESFT can effectively adapt large language models for reasoning tasks under the computational and communication constraints of edge environments.展开更多
The rapid advancement of large language models(LLMs)has driven the pervasive adoption of AI-generated content(AIGC),while also raising concerns about misinformation,academic misconduct,biased or harmful content,and ot...The rapid advancement of large language models(LLMs)has driven the pervasive adoption of AI-generated content(AIGC),while also raising concerns about misinformation,academic misconduct,biased or harmful content,and other risks.Detecting AI-generated text has thus become essential to safeguard the authenticity and reliability of digital information.This survey reviews recent progress in detection methods,categorizing approaches into passive and active categories based on their reliance on intrinsic textual features or embedded signals.Passive detection is further divided into surface linguistic feature-based and language model-based methods,whereas active detection encompasses watermarking-based and semantic retrieval-based approaches.This taxonomy enables systematic comparison of methodological differences in model dependency,applicability,and robustness.A key challenge for AI-generated text detection is that existing detectors are highly vulnerable to adversarial attacks,particularly paraphrasing,which substantially compromises their effectiveness.Addressing this gap highlights the need for future research on enhancing robustness and cross-domain generalization.By synthesizing current advances and limitations,this survey provides a structured reference for the field and outlines pathways toward more reliable and scalable detection solutions.展开更多
War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient an...War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient and inflexible,with particularly pronounced limitations in command and decision-making.The overwhelming volume of information and high decision complexity hinder the realization of autonomous and agile command and control.To address this challenge,an intelligent warfare simulation framework named Command-Agent is proposed,which deeply integrates large language models(LLMs)with digital twin battlefields.By constructing a highly realistic battlefield environment through real-time simulation and multi-source data fusion,the natural language interaction capabilities of LLMs are leveraged to lower the command threshold and to enable autonomous command through the Observe-Orient-Decide-Act(OODA)feedback loop.Within the Command-Agent framework,a multimodel collaborative architecture is further adopted to decouple the decision-generation and command-execution functions of LLMs.By combining specialized models such as Deep Seek-R1 and MCTool,the limitations of single-model capabilities are overcome.MCTool is a lightweight execution model fine-tuned for military Function Calling tasks.The framework also introduces a Vector Knowledge Base to mitigate hallucinations commonly exhibited by LLMs.Experimental results demonstrate that Command-Agent not only enables natural language-driven simulation and control but also deeply understands commander intent.Leveraging the multi-model collaborative architecture,during red-blue UAV confrontations involving 2 to 8 UAVs,the integrated score is improved by an average of 41.8%compared to the single-agent system(MCTool),accompanied by a 161.8%optimization in the battle loss ratio.Furthermore,when compared with multi-agent systems lacking the knowledge base,the inclusion of the Vector Knowledge Base further improves overall performance by 16.8%.In comparison with the general model(Qwen2.5-7B),the fine-tuned MCTool leads by 5%in execution efficiency.Therefore,the proposed Command-Agent introduces a novel perspective to the military command system and offers a feasible solution for intelligent battlefield decision-making.展开更多
The problem of fake news detection(FND)is becoming increasingly important in the field of natural language processing(NLP)because of the rapid dissemination of misleading information on the web.Large language models(L...The problem of fake news detection(FND)is becoming increasingly important in the field of natural language processing(NLP)because of the rapid dissemination of misleading information on the web.Large language models(LLMs)such as GPT-4.Zero excels in natural language understanding tasks but can still struggle to distinguish between fact and fiction,particularly when applied in the wild.However,a key challenge of existing FND methods is that they only consider unimodal data(e.g.,images),while more detailed multimodal data(e.g.,user behaviour,temporal dynamics)is neglected,and the latter is crucial for full-context understanding.To overcome these limitations,we introduce M3-FND(Multimodal Misinformation Mitigation for False News Detection),a novel methodological framework that integrates LLMs with multimodal data sources to perform context-aware veracity assessments.Our method proposes a hybrid system that combines image-text alignment,user credibility profiling,and temporal pattern recognition,which is also strengthened through a natural feedback loop that provides real-time feedback for correcting downstream errors.We use contextual reinforcement learning to schedule prompt updating and update the classifier threshold based on the latest multimodal input,which enables the model to better adapt to changing misinformation attack strategies.M3-FND is tested on three diverse datasets,FakeNewsNet,Twitter15,andWeibo,which contain both text and visual socialmedia content.Experiments showthatM3-FND significantly outperforms conventional and LLMbased baselines in terms of accuracy,F1-score,and AUC on all benchmarks.Our results indicate the importance of employing multimodal cues and adaptive learning for effective and timely detection of fake news.展开更多
Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that man...Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that manipulate model behavior through malicious instructions.Following Kitchenham’s guidelines,this systematic review synthesizes 128 peer-reviewed studies from 2022 to 2025 to provide a unified understanding of this rapidly evolving threat landscape.Our findings reveal a swift progression from simple direct injections to sophisticated multimodal attacks,achieving over 90%success rates against unprotected systems.In response,defense mechanisms show varying effectiveness:input preprocessing achieves 60%–80%detection rates and advanced architectural defenses demonstrate up to 95%protection against known patterns,though significant gaps persist against novel attack vectors.We identified 37 distinct defense approaches across three categories,but standardized evaluation frameworks remain limited.Our analysis attributes these vulnerabilities to fundamental LLM architectural limitations,such as the inability to distinguish instructions from data and attention mechanism vulnerabilities.This highlights critical research directions such as formal verification methods,standardized evaluation protocols,and architectural innovations for inherently secure LLM designs.展开更多
In the wireless energy transmission service composition optimization problem,a key challenge is accurately capturing users’preferences for service criteria under complex influencing factors,and optimally selecting a ...In the wireless energy transmission service composition optimization problem,a key challenge is accurately capturing users’preferences for service criteria under complex influencing factors,and optimally selecting a composition solution under their budget constraints.Existing studies typically evaluate satisfaction solely based on energy transmission capacity,while overlooking critical factors such as price and trustworthiness of the provider,leading to a mismatch between optimization outcomes and user needs.To address this gap,we construct a user satisfaction evaluation model for multi-user and multi-provider scenarios,systematically incorporating service price,transmission capacity,and trustworthiness into the satisfaction assessment framework.Furthermore,we propose a Budget-Aware Preference Adjustment Model that predicts users’baseline preference weights from historical data and dynamically adjusts them according to budget levels,thereby reflecting user preferences more realistically under varying budget constraints.In addition,to tackle the composition optimization problem,we develop a ReflectiveEvolutionary Large Language Model—Guided Ant Colony Optimization algorithm,which leverages the reflective evolution capability of large language models to iteratively generate and refine heuristic information that guides the search process.Experimental results demonstrate that the proposed framework effectively integrates personalized preferences with budget sensitivity,accurately predicts users’preferences,and significantly enhances their satisfaction under complex constraints.展开更多
基金National Natural Science Foundation of China(71690233,71971213,71901214)。
文摘Architecture framework has become an effective method recently to describe the system of systems(SoS)architecture,such as the United States(US)Department of Defense Architecture Framework Version 2.0(DoDAF2.0).As a viewpoint in DoDAF2.0,the operational viewpoint(OV)describes operational activities,nodes,and resource flows.The OV models are important for SoS architecture development.However,as the SoS complexity increases,constructing OV models with traditional methods exposes shortcomings,such as inefficient data collection and low modeling standards.Therefore,we propose an intelligent modeling method for five OV models,including operational resource flow OV-2,organizational relationships OV-4,operational activity hierarchy OV-5a,operational activities model OV-5b,and operational activity sequences OV-6c.The main idea of the method is to extract OV architecture data from text and generate interoperable OV models.First,we construct the OV meta model based on the DoDAF2.0 meta model(DM2).Second,OV architecture named entities is recognized from text based on the bidirectional long short-term memory and conditional random field(BiLSTM-CRF)model.And OV architecture relationships are collected with relationship extraction rules.Finally,we define the generation rules for OV models and develop an OV modeling tool.We use unmanned surface vehicles(USV)swarm target defense SoS architecture as a case to verify the feasibility and effectiveness of the intelligent modeling method.
基金supported by the National Key Research and Development Program of China(2023YFA1507601)the National Natural Science Foundation of China(22278127,22378038)+2 种基金the Fundamental Research Funds for the Central Universities(2022ZFJH004)the Shanghai Pilot Program for Basic Research(22T01400100-18)the Natural Science Foundation of Liaoning Province,China(2024-MSBA-15).
文摘Data-driven approaches are extensively employed to model complex chemical engineering processes, such as hydrotreating, to address the challenges of mechanism-based methods demanding deep process understanding. However, the development of such models requires specialized expertise in data science, limiting their broader application. Large language models (LLMs), such as GPT-4, have demonstrated potential in supporting and guiding research efforts. This work presents a novel AI-assisted framework where GPT-4, through well-engineered prompts, facilitates the construction and explanation of multi-objective neural networks. These models predict hydrotreating products properties (such as distillation range), including refined diesel and refined gas oil, using feedstock properties, operating conditions, and recycle hydrogen composition. Gradient-weighted class activation mapping was employed to identify key features influencing the output variables. This work illustrates an innovative AI-guided paradigm for chemical engineering applications, and the designed prompts hold promise for adaptation to other complex processes.
基金supported supported by the Fundamental Research Funds for the Central Universities(226-2024-00004)the National Natural Science Foundation of China(U23 A20326)Key Research and Development Program of Zhejiang Province(2025C01061).
文摘Dear Editor,This letter deals with automatically constructing an OPC UA information model(IM)aimed at enhancing data interoperability among heterogeneous system components within manufacturing automation systems.Empowered by the large language model(LLM),we propose a novel multi-agent collaborative framework to streamline the end-to-end OPC UA IM modeling process.Each agent is equipped with meticulously engineered prompt templates,augmenting their capacity to execute specific tasks.We conduct modeling experiments using real textual data to demonstrate the effectiveness of the proposed method,improving modeling efficiency and reducing the labor workload.
基金supported by China Undergraduate Innovation Training Program[Grant No.202410699184]Humanities and Social Sciences Research Project funded by the Ministry of Education of China[Grant No.23YJAZH139].
文摘Machine translation of low-resource languages(LRLs)has long been hindered by limited corpora and linguistic complexity.This review summarizes key developments,from traditional methods to recent progress with large language models(LLMs),while highlighting ongoing challenges such as data bottlenecks,biases,fairness,and computational costs.Finally,it discusses future directions,including efficient parameter fine-tuning,multimodal translation,and community-driven corpus construction,providing insights for advancing LRL translation research.
文摘Short Message Service(SMS)is a widely used and cost-effective communication medium that has unfortunately become a frequent target for unsolicited messages-commonly known as SMS spam.With the rapid adoption of smartphones and increased Internet connectivity,SMS spam has emerged as a prevalent threat.Spammers have recognized the critical role SMS plays in today’s modern communication,making it a prime target for abuse.As cybersecurity threats continue to evolve,the volume of SMS spam has increased substantially in recent years.Moreover,the unstructured format of SMS data creates significant challenges for SMS spam detection,making it more difficult to successfully combat spam attacks.In this paper,we present an optimized and fine-tuned transformer-based Language Model to address the problem of SMS spam detection.We use a benchmark SMS spam dataset to analyze this spam detection model.Additionally,we utilize pre-processing techniques to obtain clean and noise-free data and address class imbalance problem by leveraging text augmentation techniques.The overall experiment showed that our optimized fine-tuned BERT(Bidirectional Encoder Representations from Transformers)variant model RoBERTa obtained high accuracy with 99.84%.To further enhance model transparency,we incorporate Explainable Artificial Intelligence(XAI)techniques that compute positive and negative coefficient scores,offering insight into the model’s decision-making process.Additionally,we evaluate the performance of traditional machine learning models as a baseline for comparison.This comprehensive analysis demonstrates the significant impact language models can have on addressing complex text-based challenges within the cybersecurity landscape.
文摘Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLMs.Therefore,in order to better assess the capability of LLMs in the agricultural domain,Agri-Eval was proposed as a benchmark for assessing the knowledge and reasoning ability of LLMs in agriculture.The assessment dataset used in Agri-Eval covered seven major disciplines in the agricultural domain:crop science,horticulture,plant protection,animal husbandry,forest science,aquaculture science,and grass science,and contained a total of 2283 questions.Among domestic general-purpose LLMs,DeepSeek R1 performed best with an accuracy rate of 75.49%.In the realm of international general-purpose LLMs,Gemini 2.0 pro exp 0205 standed out as the top performer,achieving an accuracy rate of 74.28%.As an LLMs in agriculture vertical,Shennong V2.0 outperformed all the LLMs in China,and the answer accuracy rate of agricultural knowledge exceeded that of all the existing general-purpose LLMs.The launch of Agri-Eval helped the LLM developers to comprehensively evaluate the model's capability in the field of agriculture through a variety of tasks and tests to promote the development of the LLMs in the field of agriculture.
基金supported by the National Key R&D Program of China[2022YFF0902703]the State Administration for Market Regulation Science and Technology Plan Project(2024MK033).
文摘Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interactions to predict future items of interest.However,many current methods rely on unique user and item IDs,limiting their ability to represent users and items effectively,especially in zero-shot learning scenarios where training data is scarce.With the rapid development of Large Language Models(LLMs),researchers are exploring their potential to enhance recommendation systems.However,there is a semantic gap between the linguistic semantics of LLMs and the collaborative semantics of recommendation systems,where items are typically indexed by IDs.Moreover,most research focuses on item representations,neglecting personalized user modeling.To address these issues,we propose a sequential recommendation framework using LLMs,called CIT-Rec,a model that integrates Collaborative semantics for user representation and Image and Text information for item representation to enhance Recommendations.Specifically,by aligning intuitive image information with text containing semantic features,we can more accurately represent items,improving item representation quality.We focus not only on item representations but also on user representations.To more precisely capture users’personalized preferences,we use traditional sequential recommendation models to train on users’historical interaction data,effectively capturing behavioral patterns.Finally,by combining LLMs and traditional sequential recommendation models,we allow the LLM to understand linguistic semantics while capturing collaborative semantics.Extensive evaluations on real-world datasets show that our model outperforms baseline methods,effectively combining user interaction history with item visual and textual modalities to provide personalized recommendations.
文摘The emergence of large language models(LLMs)has brought about revolutionary social value.However,concerns have arisen regarding the generation of deceptive content by LLMs and their potential for misuse.Consequently,a crucial research question arises:How can we differentiate between AI-generated and human-authored text?Existing detectors face some challenges,such as operating as black boxes,relying on supervised training,and being vulnerable to manipulation and misinformation.To tackle these challenges,we propose an innovative unsupervised white-box detection method that utilizes a“dual-driven verification mechanism”to achieve high-performance detection,even in the presence of obfuscated attacks in the text content.To be more specific,we initially employ the SpaceInfi strategy to enhance the difficulty of detecting the text content.Subsequently,we randomly select vulnerable spots from the text and perturb them using another pre-trained language model(e.g.,T5).Finally,we apply a dual-driven defense mechanism(D3M)that validates text content with perturbations,whether generated by a model or authored by a human,based on the dimensions of Information TransmissionQuality and Information TransmissionDensity.Through experimental validation,our proposed novelmethod demonstrates state-of-the-art(SOTA)performancewhen exposed to equivalent levels of perturbation intensity across multiple benchmarks,thereby showcasing the effectiveness of our strategies.
文摘Liver transplantation(LT)remains the optimal life-saving intervention for patients with end-stage liver disease.Despite the recent advances in LT several barriers,including organ allocation,donor-recipient matching,and patient education,persist.With the growing progress of artificial intelligence,particularly large language models(LLMs)like ChatGPT,new applications have emerged in the field of LT.Current studies demonstrating usage of ChatGPT in LT include various areas of application,from clinical settings to research and education.ChatGPT usage can benefit both healthcare professionals,by decreasing the time spent on non-clinical work,but also LT recipients by providing accurate information.Future potential applications include the expanding usage of ChatGPT and other LLMs in the field of LT pathology and radiology as well as the automated creation of discharge summaries or other related paperwork.Additionally,the next models of ChatGPT might have the potential to provide more accurate patient education material with increased readability.Although ChatGPT usage presents promising applications,there are certain ethical and practical limitations.Key concerns include patient data privacy,information accuracy,misinformation possibility and lack of legal framework.Healthcare providers and policymakers should collaborate for the establishment of a controlled framework for the safe use of ChatGPT.The aim of this minireview is to summarize current literature on ChatGPT in LT,highlighting both opportunities and limitations,while also providing future possible applications.
基金funded by the Office of the Vice-President for Research and Development of Cebu Technological University.
文摘This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to user behavior and platform-driven moderation on social media.The proposed methodological framework(1)utilizes large language models for social media post analysis and categorization,(2)employs k-means clustering for content characterization,and(3)incorporates the TODIM(Tomada de Decisão Interativa Multicritério)method to determine moderation strategies based on expert judgments.In general,the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation of large-scale decision problems.When applied in social media moderation,this approach promotes nuanced and context-sensitive self-moderation by taking into account factors such as cultural background and geographic location.The application of this framework is demonstrated within Facebook groups.Eight distinct content clusters encompassing safety,harassment,diversity,and misinformation are identified.Analysis revealed a preference for content removal across all clusters,suggesting a cautious approach towards potentially harmful content.However,the framework also highlights the use of other moderation actions,like account suspension,depending on the content category.These findings contribute to the growing body of research on self-moderation and offer valuable insights for creating safer and more inclusive online spaces within smaller communities.
文摘Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.
文摘Although Named Entity Recognition(NER)in cybersecurity has historically concentrated on threat intelligence,vital security data can be found in a variety of sources,such as open-source intelligence and unprocessed tool outputs.When dealing with technical language,the coexistence of structured and unstructured data poses serious issues for traditional BERT-based techniques.We introduce a three-phase approach for improved NER inmulti-source cybersecurity data that makes use of large language models(LLMs).To ensure thorough entity coverage,our method starts with an identification module that uses dynamic prompting techniques.To lessen hallucinations,the extraction module uses confidence-based self-assessment and cross-checking using regex validation.The tagging module links to knowledge bases for contextual validation and uses SecureBERT in conjunction with conditional random fields to detect entity boundaries precisely.Our framework creates efficient natural language segments by utilizing decoderbased LLMs with 10B parameters.When compared to baseline SecureBERT implementations,evaluation across four cybersecurity data sources shows notable gains,with a 9.4%–25.21%greater recall and a 6.38%–17.3%better F1-score.Our refined model matches larger models and achieves 2.6%–4.9%better F1-score for technical phrase recognition than the state-of-the-art alternatives Claude 3.5 Sonnet,Llama3-8B,and Mixtral-7B.The three-stage architecture identification-extraction-tagging pipeline tackles important cybersecurity NER issues.Through effective architectures,these developments preserve deployability while setting a new standard for entity extraction in challenging security scenarios.The findings show how specific enhancements in hybrid recognition,validation procedures,and prompt engineering raise NER performance above monolithic LLM approaches in cybersecurity applications,especially for technical entity extraction fromheterogeneous sourceswhere conventional techniques fall short.Because of itsmodular nature,the framework can be upgraded at the component level as new methods are developed.
基金supported by grant from the National Natural Science Foundation of China(82372207).
文摘BACKGROUND:To provide a comprehensive analysis of the landscape of artifi cial intelligence(AI)applications in cardiac arrest(CA).METHODS:Comprehensive searches were conducted in PubMed,the Cochrane Library,Webof Science,and EMBASE from database inception through 10 June 2025.Studies that applied AI inboth in-hospital cardiac arrest(IHCA)and out-of-hospital cardiac arrest(OHCA)populations acrossthe following domains were included:prediction of cardiac arrest occurrence,prognostication ofCA outcomes,applications of large language models(LLMs),and evaluation of cardiopulmonaryresuscitation(CPR)and other AI-driven interventions related to CA.RESULTS:The scoping review included 114 studies,encompassing data from 9,574,462patients in total.AI was most commonly applied to the prediction of CA(overall,n=40;IHCA,n=30;OHCA,n=4;and both,n=6),CPR-related decision support during CA(n=16),and post-arrestprognosis and rehabilitation outcomes(overall,n=38;OHCA,n=21;IHCA,n=3;and both,n=14).Additional application areas included LLM-based applications(n=8),emergency call handling(n=4),wearable device-based detection(n=3),heart rhythm identification(n=2),education(n=2),and extracorporeal cardiopulmonary resuscitation(ECPR)candidate identifi cation(n=1).Across allapplication scenarios,the highest area under the receiver operating characteristic curve(AUROC)value for pre-arrest CA prediction in IHCA patients was 0.998 using a multilayer perceptron(MLP)model,whereas the optimal AUROC for pre-arrest CA prediction in OHCA patients was 0.950 usingextreme gradient boosting(XGBoost)or random forest(RF)models.For CPR-related decisionsupport during CA,the highest AUROC achieved was 0.990 with a convolutional neural network(CNN)model.In prognostic prediction,the optimal AUROC for IHCA patients was 0.960 usingXGBoost,while for OHCA patients it reached 0.976 using an MLP model.CONCLUSION:This review shows that AI is most commonly used for the prediction of CA andCPR-related support,as well as post-arrest and rehabilitation outcomes.Future research directions includedrug discovery,post-resuscitation management,neurorehabilitation,and clinical trial innovation.Furtherstudies should prioritize multicenter clinical trials to evaluate AI models in real-world settings and validatetheir eff ectiveness across diverse patient populations.Overall,AI has signifi cant potential to improve clinicalpractice,and its role in CA application is increasingly important.
基金funded by the Deanship of Scientific Research(DSR)at King Abdulaziz University,Jeddah,under Grant No.(GPIP:1074-612-2024).
文摘The surge in smishing attacks underscores the urgent need for robust,real-time detection systems powered by advanced deep learning models.This paper introduces PhishNet,a novel ensemble learning framework that integrates transformer-based models(RoBERTa)and large language models(LLMs)(GPT-OSS 120B,LLaMA3.370B,and Qwen332B)to enhance smishing detection performance significantly.To mitigate class imbalance,we apply synthetic data augmentation using T5 and leverage various text preprocessing techniques.Our system employs a duallayer voting mechanism:weighted majority voting among LLMs and a final ensemble vote to classify messages as ham,spam,or smishing.Experimental results show an average accuracy improvement from 96%to 98.5%compared to the best standalone transformer,and from 93%to 98.5%when compared to LLMs across datasets.Furthermore,we present a real-time,user-friendly application to operationalize our detection model for practical use.PhishNet demonstrates superior scalability,usability,and detection accuracy,filling critical gaps in current smishing detection methodologies.
基金supported in part by the National Natural Science Foundation of China(NSFC)under Grant 62276109The authors extend their appreciation to the Deanship of Scientific Research at King Saud University for funding this work through the Research Group Project number(ORF-2025-585).
文摘The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness diminishes in few-shot reasoning scenarios due to the low data efficiency of conventional supervised fine-tuning,which leads to excessive communication overhead.To address this,we propose Language-Empowered Split Fine-Tuning(LESFT),a framework that integrates split architectures with a contrastive-inspired fine-tuning paradigm.LESFT simultaneously learns frommultiple logically equivalent but linguistically diverse reasoning chains,providing richer supervisory signals and improving data efficiency.This process-oriented training allows more effective reasoning adaptation with fewer samples.Extensive experiments demonstrate that LESFT consistently outperforms strong baselines such as SplitLoRA in task accuracy.LESFT consistently outperforms strong baselines on GSM8K,CommonsenseQA,and AQUA_RAT,with the largest gains observed on Qwen2.5-3B.These results indicate that LESFT can effectively adapt large language models for reasoning tasks under the computational and communication constraints of edge environments.
基金supported in part by the Science and Technology Innovation Program of Hunan Province under Grant 2025RC3166the National Natural Science Foundation of China under Grant 62572176the National Key R&D Program of China under Grant 2024YFF0618800.
文摘The rapid advancement of large language models(LLMs)has driven the pervasive adoption of AI-generated content(AIGC),while also raising concerns about misinformation,academic misconduct,biased or harmful content,and other risks.Detecting AI-generated text has thus become essential to safeguard the authenticity and reliability of digital information.This survey reviews recent progress in detection methods,categorizing approaches into passive and active categories based on their reliance on intrinsic textual features or embedded signals.Passive detection is further divided into surface linguistic feature-based and language model-based methods,whereas active detection encompasses watermarking-based and semantic retrieval-based approaches.This taxonomy enables systematic comparison of methodological differences in model dependency,applicability,and robustness.A key challenge for AI-generated text detection is that existing detectors are highly vulnerable to adversarial attacks,particularly paraphrasing,which substantially compromises their effectiveness.Addressing this gap highlights the need for future research on enhancing robustness and cross-domain generalization.By synthesizing current advances and limitations,this survey provides a structured reference for the field and outlines pathways toward more reliable and scalable detection solutions.
文摘War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient and inflexible,with particularly pronounced limitations in command and decision-making.The overwhelming volume of information and high decision complexity hinder the realization of autonomous and agile command and control.To address this challenge,an intelligent warfare simulation framework named Command-Agent is proposed,which deeply integrates large language models(LLMs)with digital twin battlefields.By constructing a highly realistic battlefield environment through real-time simulation and multi-source data fusion,the natural language interaction capabilities of LLMs are leveraged to lower the command threshold and to enable autonomous command through the Observe-Orient-Decide-Act(OODA)feedback loop.Within the Command-Agent framework,a multimodel collaborative architecture is further adopted to decouple the decision-generation and command-execution functions of LLMs.By combining specialized models such as Deep Seek-R1 and MCTool,the limitations of single-model capabilities are overcome.MCTool is a lightweight execution model fine-tuned for military Function Calling tasks.The framework also introduces a Vector Knowledge Base to mitigate hallucinations commonly exhibited by LLMs.Experimental results demonstrate that Command-Agent not only enables natural language-driven simulation and control but also deeply understands commander intent.Leveraging the multi-model collaborative architecture,during red-blue UAV confrontations involving 2 to 8 UAVs,the integrated score is improved by an average of 41.8%compared to the single-agent system(MCTool),accompanied by a 161.8%optimization in the battle loss ratio.Furthermore,when compared with multi-agent systems lacking the knowledge base,the inclusion of the Vector Knowledge Base further improves overall performance by 16.8%.In comparison with the general model(Qwen2.5-7B),the fine-tuned MCTool leads by 5%in execution efficiency.Therefore,the proposed Command-Agent introduces a novel perspective to the military command system and offers a feasible solution for intelligent battlefield decision-making.
文摘The problem of fake news detection(FND)is becoming increasingly important in the field of natural language processing(NLP)because of the rapid dissemination of misleading information on the web.Large language models(LLMs)such as GPT-4.Zero excels in natural language understanding tasks but can still struggle to distinguish between fact and fiction,particularly when applied in the wild.However,a key challenge of existing FND methods is that they only consider unimodal data(e.g.,images),while more detailed multimodal data(e.g.,user behaviour,temporal dynamics)is neglected,and the latter is crucial for full-context understanding.To overcome these limitations,we introduce M3-FND(Multimodal Misinformation Mitigation for False News Detection),a novel methodological framework that integrates LLMs with multimodal data sources to perform context-aware veracity assessments.Our method proposes a hybrid system that combines image-text alignment,user credibility profiling,and temporal pattern recognition,which is also strengthened through a natural feedback loop that provides real-time feedback for correcting downstream errors.We use contextual reinforcement learning to schedule prompt updating and update the classifier threshold based on the latest multimodal input,which enables the model to better adapt to changing misinformation attack strategies.M3-FND is tested on three diverse datasets,FakeNewsNet,Twitter15,andWeibo,which contain both text and visual socialmedia content.Experiments showthatM3-FND significantly outperforms conventional and LLMbased baselines in terms of accuracy,F1-score,and AUC on all benchmarks.Our results indicate the importance of employing multimodal cues and adaptive learning for effective and timely detection of fake news.
基金supported by 2023 Higher Education Scientific Research Planning Project of China Society of Higher Education(No.23PG0408)2023 Philosophy and Social Science Research Programs in Jiangsu Province(No.2023SJSZ0993)+2 种基金Nantong Science and Technology Project(No.JC2023070)Key Project of Jiangsu Province Education Science 14th Five-Year Plan(Grant No.B-b/2024/02/41)the Open Fund of Advanced Cryptography and System Security Key Laboratory of Sichuan Province(Grant No.SKLACSS-202407).
文摘Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that manipulate model behavior through malicious instructions.Following Kitchenham’s guidelines,this systematic review synthesizes 128 peer-reviewed studies from 2022 to 2025 to provide a unified understanding of this rapidly evolving threat landscape.Our findings reveal a swift progression from simple direct injections to sophisticated multimodal attacks,achieving over 90%success rates against unprotected systems.In response,defense mechanisms show varying effectiveness:input preprocessing achieves 60%–80%detection rates and advanced architectural defenses demonstrate up to 95%protection against known patterns,though significant gaps persist against novel attack vectors.We identified 37 distinct defense approaches across three categories,but standardized evaluation frameworks remain limited.Our analysis attributes these vulnerabilities to fundamental LLM architectural limitations,such as the inability to distinguish instructions from data and attention mechanism vulnerabilities.This highlights critical research directions such as formal verification methods,standardized evaluation protocols,and architectural innovations for inherently secure LLM designs.
基金supported by the National Natural Science Foundation of China under Grant 62472264the Natural Science Distinguished Youth Foundation of Shandong Province under Grant ZR2025QA13。
文摘In the wireless energy transmission service composition optimization problem,a key challenge is accurately capturing users’preferences for service criteria under complex influencing factors,and optimally selecting a composition solution under their budget constraints.Existing studies typically evaluate satisfaction solely based on energy transmission capacity,while overlooking critical factors such as price and trustworthiness of the provider,leading to a mismatch between optimization outcomes and user needs.To address this gap,we construct a user satisfaction evaluation model for multi-user and multi-provider scenarios,systematically incorporating service price,transmission capacity,and trustworthiness into the satisfaction assessment framework.Furthermore,we propose a Budget-Aware Preference Adjustment Model that predicts users’baseline preference weights from historical data and dynamically adjusts them according to budget levels,thereby reflecting user preferences more realistically under varying budget constraints.In addition,to tackle the composition optimization problem,we develop a ReflectiveEvolutionary Large Language Model—Guided Ant Colony Optimization algorithm,which leverages the reflective evolution capability of large language models to iteratively generate and refine heuristic information that guides the search process.Experimental results demonstrate that the proposed framework effectively integrates personalized preferences with budget sensitivity,accurately predicts users’preferences,and significantly enhances their satisfaction under complex constraints.
