As the use of deepfake facial videos proliferate,the associated threats to social security and integrity cannot be overstated.Effective methods for detecting forged facial videos are thus urgently needed.While many de...As the use of deepfake facial videos proliferate,the associated threats to social security and integrity cannot be overstated.Effective methods for detecting forged facial videos are thus urgently needed.While many deep learning-based facial forgery detection approaches show promise,they often fail to delve deeply into the complex relationships between image features and forgery indicators,limiting their effectiveness to specific forgery techniques.To address this challenge,we propose a dual-branch collaborative deepfake detection network.The network processes video frame images as input,where a specialized noise extraction module initially extracts the noise feature maps.Subsequently,the original facial images and corresponding noise maps are directed into two parallel feature extraction branches to concurrently learn texture and noise forgery clues.An attention mechanism is employed between the two branches to facilitate mutual guidance and enhancement of texture and noise features across four different scales.This dual-modal feature integration enhances sensitivity to forgery artifacts and boosts generalization ability across various forgery techniques.Features from both branches are then effectively combined and processed through a multi-layer perception layer to distinguish between real and forged video.Experimental results on benchmark deepfake detection datasets demonstrate that our approach outperforms existing state-of-the-art methods in terms of detection performance,accuracy,and generalization ability.展开更多
An effective algorithm is proposed to detect copy-move forgery.In this algorithm,first,the PatchMatch algorithm is improved by using a reliable order-statistics-based approximate nearest neighbor search algorithm(ROSA...An effective algorithm is proposed to detect copy-move forgery.In this algorithm,first,the PatchMatch algorithm is improved by using a reliable order-statistics-based approximate nearest neighbor search algorithm(ROSANNA)to modify the propagation process.Then,fractional quaternion Zernike moments(FrQZMs)are considered to be features extracted from color forged images.Finally,the extracted FrQZMs features are matched by the improved PatchMatch algorithm.The experimental results on two publicly available datasets(FAU and GRIP datasets)show that the proposed algorithm performs better than the state-of-the-art algorithms not only in objective criteria F-measure value but also in visual.Moreover,the proposed algorithm is robust to some attacks,such as additive white Gaussian noise,JPEG compression,rotation,and scaling.展开更多
Small or smooth cloned regions are difficult to be detected in image copy-move forgery （CMF） detection. Aiming at this problem, an effective method based on image segmentation and swarm intelligent （SI） algorithm ...Small or smooth cloned regions are difficult to be detected in image copy-move forgery （CMF） detection. Aiming at this problem, an effective method based on image segmentation and swarm intelligent （SI） algorithm is proposed. This method segments image into small nonoverlapping blocks. A calculation of smooth degree is given for each block. Test image is segmented into independent layers according to the smooth degree. SI algorithm is applied in finding the optimal detection parameters for each layer. These parameters are used to detect each layer by scale invariant features transform （SIFT）-based scheme, which can locate a mass of keypoints. The experimental results prove the good performance of the proposed method, which is effective to identify the CMF image with small or smooth cloned region.展开更多
Copy-Move Forgery(CMF) is one of the simple and effective operations to create forged digital images.Recently,techniques based on Scale Invariant Features Transform(SIFT) are widely used to detect CMF.Various approach...Copy-Move Forgery(CMF) is one of the simple and effective operations to create forged digital images.Recently,techniques based on Scale Invariant Features Transform(SIFT) are widely used to detect CMF.Various approaches under the SIFT-based framework are the most acceptable ways to CMF detection due to their robust performance.However,for some CMF images,these approaches cannot produce satisfactory detection results.For instance,the number of the matched keypoints may be too less to prove an image to be a CMF image or to generate an accurate result.Sometimes these approaches may even produce error results.According to our observations,one of the reasons is that detection results produced by the SIFT-based framework depend highly on parameters whose values are often determined with experiences.These values are only applicable to a few images,which limits their application.To solve the problem,a novel approach named as CMF Detection with Particle Swarm Optimization(CMFDPSO) is proposed in this paper.CMFD-PSO integrates the Particle Swarm Optimization(PSO) algorithm into the SIFT-based framework.It utilizes the PSO algorithm to generate customized parameter values for images,which are used for CMF detection under the SIFT-based framework.Experimental results show that CMFD-PSO has good performance.展开更多
Image forging is the alteration of a digital image to conceal some of the necessary or helpful information.It cannot be easy to distinguish themodified region fromthe original image in somecircumstances.The demand for...Image forging is the alteration of a digital image to conceal some of the necessary or helpful information.It cannot be easy to distinguish themodified region fromthe original image in somecircumstances.The demand for authenticity and the integrity of the image drive the detection of a fabricated image.There have been cases of ownership infringements or fraudulent actions by counterfeiting multimedia files,including re-sampling or copy-moving.This work presents a high-level view of the forensics of digital images and their possible detection approaches.This work presents a thorough analysis of digital image forgery detection techniques with their steps and effectiveness.These methods have identified forgery and its type and compared it with state of the art.This work will help us to find the best forgery detection technique based on the different environments.It also shows the current issues in other methods,which can help researchers find future scope for further research in this field.展开更多
With the growth of digital media data manipulation in today’s era due to the availability of readily handy tampering software,the authenticity of records is at high risk,especially in video.There is a dire need to de...With the growth of digital media data manipulation in today’s era due to the availability of readily handy tampering software,the authenticity of records is at high risk,especially in video.There is a dire need to detect such problem and do the necessary actions.In this work,we propose an approach to detect the interframe video forgery utilizing the deep features obtained from the parallel deep neural network model and thorough analytical computations.The proposed approach only uses the deep features extracted from the CNN model and then applies the conventional mathematical approach to these features to find the forgery in the video.This work calculates the correlation coefficient from the deep features of the adjacent frames rather than calculating directly from the frames.We divide the procedure of forgery detection into two phases–video forgery detection and video forgery classification.In video forgery detection,this approach detect input video is original or tampered.If the video is not original,then the video is checked in the next phase,which is video forgery classification.In the video forgery classification,method review the forged video for insertion forgery,deletion forgery,and also again check for originality.The proposed work is generalized and it is tested on two different datasets.The experimental results of our proposed model show that our approach can detect the forgery with the accuracy of 91%on VIFFD dataset,90%in TDTV dataset and classify the type of forgery–insertion and deletion with the accuracy of 82%on VIFFD dataset,86%on TDTV dataset.This work can helps in the analysis of original and tempered video in various domain.展开更多
In response to the problem of traditional methods ignoring audio modality tampering, this study aims to explore an effective deep forgery video detection technique that improves detection precision and reliability by ...In response to the problem of traditional methods ignoring audio modality tampering, this study aims to explore an effective deep forgery video detection technique that improves detection precision and reliability by fusing lip images and audio signals. The main method used is lip-audio matching detection technology based on the Siamese neural network, combined with MFCC (Mel Frequency Cepstrum Coefficient) feature extraction of band-pass filters, an improved dual-branch Siamese network structure, and a two-stream network structure design. Firstly, the video stream is preprocessed to extract lip images, and the audio stream is preprocessed to extract MFCC features. Then, these features are processed separately through the two branches of the Siamese network. Finally, the model is trained and optimized through fully connected layers and loss functions. The experimental results show that the testing accuracy of the model in this study on the LRW (Lip Reading in the Wild) dataset reaches 92.3%;the recall rate is 94.3%;the F1 score is 93.3%, significantly better than the results of CNN (Convolutional Neural Networks) and LSTM (Long Short-Term Memory) models. In the validation of multi-resolution image streams, the highest accuracy of dual-resolution image streams reaches 94%. Band-pass filters can effectively improve the signal-to-noise ratio of deep forgery video detection when processing different types of audio signals. The real-time processing performance of the model is also excellent, and it achieves an average score of up to 5 in user research. These data demonstrate that the method proposed in this study can effectively fuse visual and audio information in deep forgery video detection, accurately identify inconsistencies between video and audio, and thus verify the effectiveness of lip-audio modality fusion technology in improving detection performance.展开更多
Since different kinds of face forgeries leave similar forgery traces in videos,learning the common features from different kinds of forged faces would achieve promising generalization ability of forgery detection.Ther...Since different kinds of face forgeries leave similar forgery traces in videos,learning the common features from different kinds of forged faces would achieve promising generalization ability of forgery detection.Therefore,to accurately detect known forgeries while ensuring high generalization ability of detecting unknown forgeries,we propose an intra-inter network(IIN)for face forgery detection(FFD)in videos with continual learning.The proposed IIN mainly consists of three modules,i.e.,intra-module,inter-module,and forged trace masking module(FTMM).Specifically,the intra-module is trained for each kind of face forgeries by supervised learning to extract special features,while the inter-module is trained by self-supervised learning to extract the common features.As a result,the common and special features of the different forgeries are decoupled by the two feature learning modules,and then the decoupled common features can be utlized to achieve high generalization ability for FFD.Moreover,the FTMM is deployed for contrastive learning to further improve detection accuracy.The experimental results on FaceForensic++dataset demonstrate that the proposed IIN outperforms the state-of-the-arts in FFD.Also,the generalization ability of the IIN verified on DFDC and Celeb-DF datasets demonstrates that the proposed IIN significantly improves the generalization ability for FFD.展开更多
With expeditious advancements in AI-driven facial manipulation techniques,particularly deepfake technology,there is growing concern over its potential misuse.Deepfakes pose a significant threat to society,partic-ularl...With expeditious advancements in AI-driven facial manipulation techniques,particularly deepfake technology,there is growing concern over its potential misuse.Deepfakes pose a significant threat to society,partic-ularly by infringing on individuals’privacy.Amid significant endeavors to fabricate systems for identifying deepfake fabrications,existing methodologies often face hurdles in adjusting to innovative forgery techniques and demonstrate increased vulnerability to image and video clarity variations,thereby hindering their broad applicability to images and videos produced by unfamiliar technologies.In this manuscript,we endorse resilient training tactics to amplify generalization capabilities.In adversarial training,models are trained using deliberately crafted samples to deceive classification systems,thereby significantly enhancing their generalization ability.In response to this challenge,we propose an innovative hybrid adversarial training framework integrating Virtual Adversarial Training(VAT)with Two-Generated Blurred Adversarial Training.This combined framework bolsters the model’s resilience in detecting deepfakes made using unfamiliar deep learning technologies.Through such adversarial training,models are prompted to acquire more versatile attributes.Through experimental studies,we demonstrate that our model achieves higher accuracy than existing models.展开更多
With the advent of the 5G Internet of Things era,communication and social interaction in our daily life have changed a lot,and a large amount of social data is transmitted to the Internet.At the same time,with the rap...With the advent of the 5G Internet of Things era,communication and social interaction in our daily life have changed a lot,and a large amount of social data is transmitted to the Internet.At the same time,with the rapid development of deep forgery technology,a new generation of social data trust crisis has also followed.Therefore,how to ensure the trust and credibility of social data in the 5G Internet of Things era is an urgent problem to be solved.This paper proposes a new method for forgery detection based on GANs.We first discover the hidden gradient information in the grayscale image of the forged image and use this gradient information to guide the generation of forged traces.In the classifier,we replace the traditional binary loss with the focal loss that can focus on difficult-to-classify samples,which can achieve accurate classification when the real and fake samples are unbalanced.Experimental results show that the proposed method can achieve high accuracy on the DeeperForensics dataset and with the highest accuracy is 98%.展开更多
Face forgery detection is drawing ever-increasing attention in the academic community owing to security concerns.Despite the considerable progress in existing methods,we note that:Previous works overlooked finegrain f...Face forgery detection is drawing ever-increasing attention in the academic community owing to security concerns.Despite the considerable progress in existing methods,we note that:Previous works overlooked finegrain forgery cues with high transferability.Such cues positively impact the model’s accuracy and generalizability.Moreover,single-modality often causes overfitting of the model,and Red-Green-Blue(RGB)modal-only is not conducive to extracting the more detailed forgery traces.We propose a novel framework for fine-grain forgery cues mining with fusion modality to cope with these issues.First,we propose two functional modules to reveal and locate the deeper forged features.Our method locates deeper forgery cues through a dual-modality progressive fusion module and a noise adaptive enhancement module,which can excavate the association between dualmodal space and channels and enhance the learning of subtle noise features.A sensitive patch branch is introduced on this foundation to enhance the mining of subtle forgery traces under fusion modality.The experimental results demonstrate that our proposed framework can desirably explore the differences between authentic and forged images with supervised learning.Comprehensive evaluations of several mainstream datasets show that our method outperforms the state-of-the-art detection methods with remarkable detection ability and generalizability.展开更多
With the improvement of image editing technology,the threshold of image tampering technology decreases,which leads to a decrease in the authenticity of image content.This has also driven research on image forgery dete...With the improvement of image editing technology,the threshold of image tampering technology decreases,which leads to a decrease in the authenticity of image content.This has also driven research on image forgery detection techniques.In this paper,a U-Net with multiple sensory field feature extraction(MSCU-Net)for image forgery detection is proposed.The proposed MSCU-Net is an end-to-end image essential attribute segmentation network that can perform image forgery detection without any pre-processing or post-processing.MSCU-Net replaces the single-scale convolution module in the original network with an improved multiple perceptual field convolution module so that the decoder can synthesize the features of different perceptual fields use residual propagation and residual feedback to recall the input feature information and consolidate the input feature information to make the difference in image attributes between the untampered and tampered regions more obvious,and introduce the channel coordinate confusion attention mechanism(CCCA)in skip-connection to further improve the segmentation accuracy of the network.In this paper,extensive experiments are conducted on various mainstream datasets,and the results verify the effectiveness of the proposed method,which outperforms the state-of-the-art image forgery detection methods.展开更多
Offline signature verification(OfSV)is essential in preventing the falsification of documents.Deep learning(DL)based OfSVs require a high number of signature images to attain acceptable performance.However,a limited n...Offline signature verification(OfSV)is essential in preventing the falsification of documents.Deep learning(DL)based OfSVs require a high number of signature images to attain acceptable performance.However,a limited number of signature samples are available to train these models in a real-world scenario.Several researchers have proposed models to augment new signature images by applying various transformations.Others,on the other hand,have used human neuromotor and cognitive-inspired augmentation models to address the demand for more signature samples.Hence,augmenting a sufficient number of signatures with variations is still a challenging task.This study proposed OffSig-SinGAN:a deep learning-based image augmentation model to address the limited number of signatures problem on offline signature verification.The proposed model is capable of augmenting better quality signatures with diversity from a single signature image only.It is empirically evaluated on widely used public datasets;GPDSsyntheticSignature.The quality of augmented signature images is assessed using four metrics like pixel-by-pixel difference,peak signal-to-noise ratio(PSNR),structural similarity index measure(SSIM),and frechet inception distance(FID).Furthermore,various experiments were organised to evaluate the proposed image augmentation model’s performance on selected DL-based OfSV systems and to prove whether it helped to improve the verification accuracy rate.Experiment results showed that the proposed augmentation model performed better on the GPDSsyntheticSignature dataset than other augmentation methods.The improved verification accuracy rate of the selected DL-based OfSV system proved the effectiveness of the proposed augmentation model.展开更多
Passive image forgery detection methods that identify forgeries without prior knowledge have become a key research focus.In copy-move forgery,the assailant intends to hide a portion of an image by pasting other portio...Passive image forgery detection methods that identify forgeries without prior knowledge have become a key research focus.In copy-move forgery,the assailant intends to hide a portion of an image by pasting other portions of the same image.The detection of such manipulations in images has great demand in legal evidence,forensic investigation,and many other fields.The paper aims to present copy-move forgery detection algorithms with the help of advanced feature descriptors,such as local ternary pattern,local phase quantization,local Gabor binary pattern histogram sequence,Weber local descriptor,and local monotonic pattern,and classifiers such as optimized support vector machine and optimized NBC.The proposed algorithms can classify an image efficiently as either copy-move forged or authenticated,even if the test image is subjected to attacks such as JPEG compression,scaling,rotation,and brightness variation.CoMoFoD,CASIA,and MICC datasets and a combination of CoMoFoD and CASIA datasets images are used to quantify the performance of the proposed algorithms.The proposed algorithms are more efficient than state-of-the-art algorithms even though the suspected image is post-processed.展开更多
Manipulated digital image is got interesting in recent years. Digital images can be manipulated more easily with the aid of powerful image editing software. Forensic techniques for authenticating the integrity of digi...Manipulated digital image is got interesting in recent years. Digital images can be manipulated more easily with the aid of powerful image editing software. Forensic techniques for authenticating the integrity of digital images and exposing forgeries are urgently needed. A geometric-based forensic technique which exploits the principle of vanishing points is proposed. By means of edge detection and straight lines extraction, intersection points of the projected parallel lines are computed. The normalized mean value （NMV） and normalized standard deviation （NSD） of the distances between the intersection points are used as evidence for image forensics. The proposed method employs basic rules of linear perspective projection, and makes minimal assumption. The only requirement is that the parallel lines are contained in the image. Unlike other forensic techniques which are based on low-level statistics, this method is less sensitive to image operations that do not alter image content, such as image resampling, color manipulation, and lossy compression. This method is demonstrated with images from York Urban database. It shows that the proposed method has a definite advantage at separating authentic and forged images.展开更多
基金funded by the Ministry of Public Security Science and Technology Program Project(No.2023LL35)the Key Laboratory of Smart Policing and National Security Risk Governance,Sichuan Province(No.ZHZZZD2302).
文摘As the use of deepfake facial videos proliferate,the associated threats to social security and integrity cannot be overstated.Effective methods for detecting forged facial videos are thus urgently needed.While many deep learning-based facial forgery detection approaches show promise,they often fail to delve deeply into the complex relationships between image features and forgery indicators,limiting their effectiveness to specific forgery techniques.To address this challenge,we propose a dual-branch collaborative deepfake detection network.The network processes video frame images as input,where a specialized noise extraction module initially extracts the noise feature maps.Subsequently,the original facial images and corresponding noise maps are directed into two parallel feature extraction branches to concurrently learn texture and noise forgery clues.An attention mechanism is employed between the two branches to facilitate mutual guidance and enhancement of texture and noise features across four different scales.This dual-modal feature integration enhances sensitivity to forgery artifacts and boosts generalization ability across various forgery techniques.Features from both branches are then effectively combined and processed through a multi-layer perception layer to distinguish between real and forged video.Experimental results on benchmark deepfake detection datasets demonstrate that our approach outperforms existing state-of-the-art methods in terms of detection performance,accuracy,and generalization ability.
基金The National Natural Science of China(No.61572258,61771231,61772281,61672294)the Priority Academic Program Development of Jiangsu Higher Education Institutionsthe Qing Lan Project of Jiangsu Higher Education Institutions
文摘An effective algorithm is proposed to detect copy-move forgery.In this algorithm,first,the PatchMatch algorithm is improved by using a reliable order-statistics-based approximate nearest neighbor search algorithm(ROSANNA)to modify the propagation process.Then,fractional quaternion Zernike moments(FrQZMs)are considered to be features extracted from color forged images.Finally,the extracted FrQZMs features are matched by the improved PatchMatch algorithm.The experimental results on two publicly available datasets(FAU and GRIP datasets)show that the proposed algorithm performs better than the state-of-the-art algorithms not only in objective criteria F-measure value but also in visual.Moreover,the proposed algorithm is robust to some attacks,such as additive white Gaussian noise,JPEG compression,rotation,and scaling.
基金Supported by the National Natural Science Foundation of China(61472429,61070192,91018008,61303074,61170240)the National High Technology Research Development Program of China(863 Program)(2007AA01Z414)+1 种基金the National Science and Technology Major Project of China(2012ZX01039-004)the Beijing Natural Science Foundation(4122041)
文摘Small or smooth cloned regions are difficult to be detected in image copy-move forgery （CMF） detection. Aiming at this problem, an effective method based on image segmentation and swarm intelligent （SI） algorithm is proposed. This method segments image into small nonoverlapping blocks. A calculation of smooth degree is given for each block. Test image is segmented into independent layers according to the smooth degree. SI algorithm is applied in finding the optimal detection parameters for each layer. These parameters are used to detect each layer by scale invariant features transform （SIFT）-based scheme, which can locate a mass of keypoints. The experimental results prove the good performance of the proposed method, which is effective to identify the CMF image with small or smooth cloned region.
基金supported in part by the National Natural Science Foundation of China under grant No.(61472429,61070192,91018008,61303074,61170240)Beijing Natural Science Foundation under grant No.4122041+1 种基金National High-Tech Research Development Program of China under grant No.2007AA01Z414National Science and Technology Major Project of China under grant No.2012ZX01039-004
文摘Copy-Move Forgery(CMF) is one of the simple and effective operations to create forged digital images.Recently,techniques based on Scale Invariant Features Transform(SIFT) are widely used to detect CMF.Various approaches under the SIFT-based framework are the most acceptable ways to CMF detection due to their robust performance.However,for some CMF images,these approaches cannot produce satisfactory detection results.For instance,the number of the matched keypoints may be too less to prove an image to be a CMF image or to generate an accurate result.Sometimes these approaches may even produce error results.According to our observations,one of the reasons is that detection results produced by the SIFT-based framework depend highly on parameters whose values are often determined with experiences.These values are only applicable to a few images,which limits their application.To solve the problem,a novel approach named as CMF Detection with Particle Swarm Optimization(CMFDPSO) is proposed in this paper.CMFD-PSO integrates the Particle Swarm Optimization(PSO) algorithm into the SIFT-based framework.It utilizes the PSO algorithm to generate customized parameter values for images,which are used for CMF detection under the SIFT-based framework.Experimental results show that CMFD-PSO has good performance.
文摘Image forging is the alteration of a digital image to conceal some of the necessary or helpful information.It cannot be easy to distinguish themodified region fromthe original image in somecircumstances.The demand for authenticity and the integrity of the image drive the detection of a fabricated image.There have been cases of ownership infringements or fraudulent actions by counterfeiting multimedia files,including re-sampling or copy-moving.This work presents a high-level view of the forensics of digital images and their possible detection approaches.This work presents a thorough analysis of digital image forgery detection techniques with their steps and effectiveness.These methods have identified forgery and its type and compared it with state of the art.This work will help us to find the best forgery detection technique based on the different environments.It also shows the current issues in other methods,which can help researchers find future scope for further research in this field.
文摘With the growth of digital media data manipulation in today’s era due to the availability of readily handy tampering software,the authenticity of records is at high risk,especially in video.There is a dire need to detect such problem and do the necessary actions.In this work,we propose an approach to detect the interframe video forgery utilizing the deep features obtained from the parallel deep neural network model and thorough analytical computations.The proposed approach only uses the deep features extracted from the CNN model and then applies the conventional mathematical approach to these features to find the forgery in the video.This work calculates the correlation coefficient from the deep features of the adjacent frames rather than calculating directly from the frames.We divide the procedure of forgery detection into two phases–video forgery detection and video forgery classification.In video forgery detection,this approach detect input video is original or tampered.If the video is not original,then the video is checked in the next phase,which is video forgery classification.In the video forgery classification,method review the forged video for insertion forgery,deletion forgery,and also again check for originality.The proposed work is generalized and it is tested on two different datasets.The experimental results of our proposed model show that our approach can detect the forgery with the accuracy of 91%on VIFFD dataset,90%in TDTV dataset and classify the type of forgery–insertion and deletion with the accuracy of 82%on VIFFD dataset,86%on TDTV dataset.This work can helps in the analysis of original and tempered video in various domain.
文摘In response to the problem of traditional methods ignoring audio modality tampering, this study aims to explore an effective deep forgery video detection technique that improves detection precision and reliability by fusing lip images and audio signals. The main method used is lip-audio matching detection technology based on the Siamese neural network, combined with MFCC (Mel Frequency Cepstrum Coefficient) feature extraction of band-pass filters, an improved dual-branch Siamese network structure, and a two-stream network structure design. Firstly, the video stream is preprocessed to extract lip images, and the audio stream is preprocessed to extract MFCC features. Then, these features are processed separately through the two branches of the Siamese network. Finally, the model is trained and optimized through fully connected layers and loss functions. The experimental results show that the testing accuracy of the model in this study on the LRW (Lip Reading in the Wild) dataset reaches 92.3%;the recall rate is 94.3%;the F1 score is 93.3%, significantly better than the results of CNN (Convolutional Neural Networks) and LSTM (Long Short-Term Memory) models. In the validation of multi-resolution image streams, the highest accuracy of dual-resolution image streams reaches 94%. Band-pass filters can effectively improve the signal-to-noise ratio of deep forgery video detection when processing different types of audio signals. The real-time processing performance of the model is also excellent, and it achieves an average score of up to 5 in user research. These data demonstrate that the method proposed in this study can effectively fuse visual and audio information in deep forgery video detection, accurately identify inconsistencies between video and audio, and thus verify the effectiveness of lip-audio modality fusion technology in improving detection performance.
文摘Since different kinds of face forgeries leave similar forgery traces in videos,learning the common features from different kinds of forged faces would achieve promising generalization ability of forgery detection.Therefore,to accurately detect known forgeries while ensuring high generalization ability of detecting unknown forgeries,we propose an intra-inter network(IIN)for face forgery detection(FFD)in videos with continual learning.The proposed IIN mainly consists of three modules,i.e.,intra-module,inter-module,and forged trace masking module(FTMM).Specifically,the intra-module is trained for each kind of face forgeries by supervised learning to extract special features,while the inter-module is trained by self-supervised learning to extract the common features.As a result,the common and special features of the different forgeries are decoupled by the two feature learning modules,and then the decoupled common features can be utlized to achieve high generalization ability for FFD.Moreover,the FTMM is deployed for contrastive learning to further improve detection accuracy.The experimental results on FaceForensic++dataset demonstrate that the proposed IIN outperforms the state-of-the-arts in FFD.Also,the generalization ability of the IIN verified on DFDC and Celeb-DF datasets demonstrates that the proposed IIN significantly improves the generalization ability for FFD.
基金supported by King Saud University,Riyadh,Saudi Arabia,through the Researchers Supporting Project under Grant RSP2025R493。
文摘With expeditious advancements in AI-driven facial manipulation techniques,particularly deepfake technology,there is growing concern over its potential misuse.Deepfakes pose a significant threat to society,partic-ularly by infringing on individuals’privacy.Amid significant endeavors to fabricate systems for identifying deepfake fabrications,existing methodologies often face hurdles in adjusting to innovative forgery techniques and demonstrate increased vulnerability to image and video clarity variations,thereby hindering their broad applicability to images and videos produced by unfamiliar technologies.In this manuscript,we endorse resilient training tactics to amplify generalization capabilities.In adversarial training,models are trained using deliberately crafted samples to deceive classification systems,thereby significantly enhancing their generalization ability.In response to this challenge,we propose an innovative hybrid adversarial training framework integrating Virtual Adversarial Training(VAT)with Two-Generated Blurred Adversarial Training.This combined framework bolsters the model’s resilience in detecting deepfakes made using unfamiliar deep learning technologies.Through such adversarial training,models are prompted to acquire more versatile attributes.Through experimental studies,we demonstrate that our model achieves higher accuracy than existing models.
基金results of the research project funded by National Natural Science Foundation of China(No.61871283)the Foundation of Pre-Research on Equipment of China(No.61400010304)Major Civil-Military Integration Project in Tianjin,China(No.18ZXJMTG00170).
文摘With the advent of the 5G Internet of Things era,communication and social interaction in our daily life have changed a lot,and a large amount of social data is transmitted to the Internet.At the same time,with the rapid development of deep forgery technology,a new generation of social data trust crisis has also followed.Therefore,how to ensure the trust and credibility of social data in the 5G Internet of Things era is an urgent problem to be solved.This paper proposes a new method for forgery detection based on GANs.We first discover the hidden gradient information in the grayscale image of the forged image and use this gradient information to guide the generation of forged traces.In the classifier,we replace the traditional binary loss with the focal loss that can focus on difficult-to-classify samples,which can achieve accurate classification when the real and fake samples are unbalanced.Experimental results show that the proposed method can achieve high accuracy on the DeeperForensics dataset and with the highest accuracy is 98%.
基金This study is supported by the Fundamental Research Funds for the Central Universities of PPSUC under Grant 2022JKF02009.
文摘Face forgery detection is drawing ever-increasing attention in the academic community owing to security concerns.Despite the considerable progress in existing methods,we note that:Previous works overlooked finegrain forgery cues with high transferability.Such cues positively impact the model’s accuracy and generalizability.Moreover,single-modality often causes overfitting of the model,and Red-Green-Blue(RGB)modal-only is not conducive to extracting the more detailed forgery traces.We propose a novel framework for fine-grain forgery cues mining with fusion modality to cope with these issues.First,we propose two functional modules to reveal and locate the deeper forged features.Our method locates deeper forgery cues through a dual-modality progressive fusion module and a noise adaptive enhancement module,which can excavate the association between dualmodal space and channels and enhance the learning of subtle noise features.A sensitive patch branch is introduced on this foundation to enhance the mining of subtle forgery traces under fusion modality.The experimental results demonstrate that our proposed framework can desirably explore the differences between authentic and forged images with supervised learning.Comprehensive evaluations of several mainstream datasets show that our method outperforms the state-of-the-art detection methods with remarkable detection ability and generalizability.
基金supported in part by the National Natural Science Foundation of China(Grant Number 61971078)Chongqing University of Technology Graduate Innovation Foundation(Grant Number gzlcx20222064).
文摘With the improvement of image editing technology,the threshold of image tampering technology decreases,which leads to a decrease in the authenticity of image content.This has also driven research on image forgery detection techniques.In this paper,a U-Net with multiple sensory field feature extraction(MSCU-Net)for image forgery detection is proposed.The proposed MSCU-Net is an end-to-end image essential attribute segmentation network that can perform image forgery detection without any pre-processing or post-processing.MSCU-Net replaces the single-scale convolution module in the original network with an improved multiple perceptual field convolution module so that the decoder can synthesize the features of different perceptual fields use residual propagation and residual feedback to recall the input feature information and consolidate the input feature information to make the difference in image attributes between the untampered and tampered regions more obvious,and introduce the channel coordinate confusion attention mechanism(CCCA)in skip-connection to further improve the segmentation accuracy of the network.In this paper,extensive experiments are conducted on various mainstream datasets,and the results verify the effectiveness of the proposed method,which outperforms the state-of-the-art image forgery detection methods.
文摘Offline signature verification(OfSV)is essential in preventing the falsification of documents.Deep learning(DL)based OfSVs require a high number of signature images to attain acceptable performance.However,a limited number of signature samples are available to train these models in a real-world scenario.Several researchers have proposed models to augment new signature images by applying various transformations.Others,on the other hand,have used human neuromotor and cognitive-inspired augmentation models to address the demand for more signature samples.Hence,augmenting a sufficient number of signatures with variations is still a challenging task.This study proposed OffSig-SinGAN:a deep learning-based image augmentation model to address the limited number of signatures problem on offline signature verification.The proposed model is capable of augmenting better quality signatures with diversity from a single signature image only.It is empirically evaluated on widely used public datasets;GPDSsyntheticSignature.The quality of augmented signature images is assessed using four metrics like pixel-by-pixel difference,peak signal-to-noise ratio(PSNR),structural similarity index measure(SSIM),and frechet inception distance(FID).Furthermore,various experiments were organised to evaluate the proposed image augmentation model’s performance on selected DL-based OfSV systems and to prove whether it helped to improve the verification accuracy rate.Experiment results showed that the proposed augmentation model performed better on the GPDSsyntheticSignature dataset than other augmentation methods.The improved verification accuracy rate of the selected DL-based OfSV system proved the effectiveness of the proposed augmentation model.
文摘Passive image forgery detection methods that identify forgeries without prior knowledge have become a key research focus.In copy-move forgery,the assailant intends to hide a portion of an image by pasting other portions of the same image.The detection of such manipulations in images has great demand in legal evidence,forensic investigation,and many other fields.The paper aims to present copy-move forgery detection algorithms with the help of advanced feature descriptors,such as local ternary pattern,local phase quantization,local Gabor binary pattern histogram sequence,Weber local descriptor,and local monotonic pattern,and classifiers such as optimized support vector machine and optimized NBC.The proposed algorithms can classify an image efficiently as either copy-move forged or authenticated,even if the test image is subjected to attacks such as JPEG compression,scaling,rotation,and brightness variation.CoMoFoD,CASIA,and MICC datasets and a combination of CoMoFoD and CASIA datasets images are used to quantify the performance of the proposed algorithms.The proposed algorithms are more efficient than state-of-the-art algorithms even though the suspected image is post-processed.
基金supported by the General Administration of Press and Publication of the People’s Republic of China (GXTC-CZ-1015004/15-1)
文摘Manipulated digital image is got interesting in recent years. Digital images can be manipulated more easily with the aid of powerful image editing software. Forensic techniques for authenticating the integrity of digital images and exposing forgeries are urgently needed. A geometric-based forensic technique which exploits the principle of vanishing points is proposed. By means of edge detection and straight lines extraction, intersection points of the projected parallel lines are computed. The normalized mean value （NMV） and normalized standard deviation （NSD） of the distances between the intersection points are used as evidence for image forensics. The proposed method employs basic rules of linear perspective projection, and makes minimal assumption. The only requirement is that the parallel lines are contained in the image. Unlike other forensic techniques which are based on low-level statistics, this method is less sensitive to image operations that do not alter image content, such as image resampling, color manipulation, and lossy compression. This method is demonstrated with images from York Urban database. It shows that the proposed method has a definite advantage at separating authentic and forged images.
