Detecting Deep-Fake Videos from Appearance and Behavior
Open accessAbstract
Synthetically-generated audios and videos - so-called deep fakes - continue to capture the imagination of the computer-graphics and computer-vision communities. At the same time, the democratization of access to technology that can create a sophisticated manipulated video of anybody saying anything continues to be of concern because of its power to disrupt democratic elections, commit small to large-scale fraud, fuel disinformation campaigns, and create non-consensual pornography. We describe a biometric-based forensic technique for detecting face-swap deep fakes. This technique combines a static biometric based on facial recognition with a temporal, behavioral biometric based on facial expressions and head movements, where the behavioral embedding is learned using a CNN with a metric-learning objective function. We show the efficacy of this approach across several large-scale video datasets, as well as in-the-wild deep fakes.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Existing unimodal deepfake detectors are primarily designed to detect a single type of manipulation, such as visual, acoustic, and text.
“Existing unimodal deepfake detectors are primarily designed to detect a single type of manipulation, such as visual, acoustic, and text.”
From Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization (2024) · cites this paper as [2]
Section 2.2 (page not provided) describes visual deepfake detectors aimed at particular artifacts or face-swap manipulations, which supports part of the claim. It does not characterize unimodal detectors generally or establish that acoustic and text detectors are primarily designed for a single type of manipulation. (LLM, conf=0.78)
Experimental — accuracy not yet measuredThe recent common underlying mechanism for deepfake creation is deep learning models such as autoencoders and generative adversarial networks (GANs).
“the re- cent common underlying mechanism for deepfake cre- ation is deep learning models such as autoencoders and generative adversarial networks (GANs)”
From Deep learning for deepfakes creation and detection: A survey (2022) · cites this paper as [2]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1× · see citing works
“We used the ResNet-101 network architecture [24], where the input layer of the network is modified to the size of our feature matrix (256×100).”
MethodGAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,268 · see citing works
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 1× · see citing works
“In the static image domain, highly realistic images of people can now be synthesized using generative adversarial networks (GANs) [2], [3].”
BackgroundTowards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859 · cited 1× · see citing works
“The drawback is that they can be highly sensitive to intentional or unintentional laundering including resizing or trans-coding, as well as adversarial attacks [7] and extrapolation to novel datasets.”
BackgroundAnalyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332 · see citing works
Estimating the Support of a High-Dimensional Distribution
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001) · Neural Computation · doi:10.1162/089976601750264965 · Cited by 6,168 · see citing works
Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.41 · Cited by 5,479 · cited 11× · see citing works
“VGG yields a distinct 4096-”
MethodInfluentialWaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911 · cited 1× · see citing works
“In the audio domain, highly realistic audio synthesis is now possible in which a neural network, with enough sample recordings, can learn to synthesize speech in your voice [25].”
BackgroundFaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314 · cited 1× · see citing works
“The FaceForensics++ dataset (FF) [27] consists of 1000 YouTube videos of 1000 different people, mostly news anchors”
VoxCeleb2: Deep Speaker Recognition
Chung, J. S., Nagrani, A., & Zisserman, A. (2018) · Interspeech 2018 · doi:10.21437/interspeech.2018-1929 · Cited by 2,256 · see citing works
MesoNet: a Compact Facial Video Forgery Detection Network
Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630761 · Cited by 1,872 · see citing works
OpenFace: An open source facial behavior analysis toolkit
Baltrušaitis, T., Robinson, P., & Morency, L. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477553 · Cited by 1,794 · cited 2× · see citing works
“Faces for this facial biometric and the behavioral biometric are extracted using OpenFace [26].”
MethodFace2Face: Real-Time Face Capture and Reenactment of RGB Videos
Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., & Niessner, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.262 · Cited by 1,747 · see citing works
Ekman, P., & Friesen, W. V. (1976) · Journal of Nonverbal Behavior · doi:10.1007/bf01115465 · Cited by 1,242 · cited 1× · see citing works
“frame-by-frame facial expressions (parameterized as 18 action units [19] and 3-D head rotation about two axes).”
BackgroundDeepfakes and beyond: A Survey of face manipulation and fake detection
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.06.014 · Cited by 1,237 · see citing works
Face X-Ray for More General Face Forgery Detection
Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00505 · Cited by 1,211 · see citing works
CNN-Generated Images Are Surprisingly Easy to Spot… for Now
Wang, S.-Y., Wang, O., Zhang, R., Owens, A., & Efros, A. A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00872 · Cited by 1,210 · see citing works
Exposing Deep Fakes Using Inconsistent Head Poses
Yang, X., Li, Y., & Lyu, S. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683164 · Cited by 1,196 · see citing works
In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking
Li, Y., Chang, M.-C., & Lyu, S. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630787 · Cited by 1,089 · cited 1× · see citing works
“These techniques focus on semantically meaningful features including, for example, inconsistencies in eye blinks [15], headpose [16], physiological signals [17], and distinct mannerisms [18].”
BackgroundSynthesizing Obama: learning lip sync from audio
Suwajanakorn, S., Seitz, S. M., & Kemelmacher-Shlizerman, I. (2017) · ACM Transactions on Graphics · doi:10.1145/3072959.3073640 · Cited by 1,057 · cited 1× · see citing works
“c deep fakes in which a person’s mouth is modied to be consistent with a new audio track. This work generalizes earlier work that was designed to create lip-sync deep fakes on a per-individual basis [30]. Unlike these learning-based methods, some methods rely on more traditional computer-graphics approaches to create…”
BackgroundMulti-Similarity Loss With General Pair Weighting for Deep Metric Learning
Wang, X., Han, X., Huang, W., Dong, D., & Scott, M. R. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00516 · Cited by 893 · cited 4× · see citing works
“All other optimization hyper-parameters are the same as in [33].”
BackgroundMethodInfluentialDeep Fakes: A Looming Challenge for Privacy, Democracy, and National Security
Chesney, R., & Citron, D. K. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3213954 · Cited by 880 · cited 1× · see citing works
“deep fakes, and continues to pose a threat particularly to women, ranging from celebrities to journalists, and those that simply attract unwanted attention [5].”
BackgroundExposing DeepFake Videos By Detecting Face Warping Artifacts
Li, Y., & Lyu, S. (2018) · arXiv · doi:10.48550/arxiv.1811.00656 · Cited by 785 · cited 1× · see citing works
“detect generic artifacts [7]–[10], while others detect explicit artifacts that result from, for example, image warping [11], image blending [12] and inconsistencies between the image and metadata [13].”
BackgroundFSGAN: Subject Agnostic Face Swapping and Reenactment
Nirkin, Y., Keller, Y., & Hassner, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00728 · Cited by 706 · cited 2× · see citing works
“s The term deep fake is often used to describe synthetically-generated images and videos (typically of people) generated from a range of dierent techniques including DeepFake FaceSwap [1] and FS-GAN [24], Neural Textures [29], Face2Face [31], and FaceSwaps [2]. The popular DeepFake FaceSwap software uses a generative…”
MethodWu, Y., AbdAlmageed, W., & Natarajan, P. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00977 · Cited by 702 · cited 1× · see citing works
“ime, etc.). An image is then authenticated using this network to determine if each image patch is consistent with the same imaging pipeline. Although not necessarily focused on deep fakes, Mantra-Net [35] uses end-to-end training of a fully convolutional network to detect and localize dierent types of image manipulati…”
MethodTwo-Stream Neural Networks for Tampered Face Detection
Zhou, P., Han, X., Morariu, V. I., & Davis, L. S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.229 · Cited by 700 · cited 1× · see citing works
“detect generic artifacts [7]–[10], while others detect explicit artifacts that result from, for example, image warping [11], image blending [12] and inconsistencies between the image and metadata [13].”
BackgroundDetecting and Simulating Artifacts in GAN Fake Images
Zhang, X., Karaman, S., & Chang, S.-F. (2019) · 2019 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs47025.2019.9035107 · Cited by 567 · cited 1× · see citing works
“The authors in [37] and [38] showed that GAN-generated content contains distinct digital fingerprints which can be learned and used to classify images as GAN-generated or not.”
BackgroundFakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
Ciftci, U. A., Demir, I., & Yin, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3009287 · Cited by 499 · see citing works
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
Yu, N., Davis, L. S., & Fritz, M. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00765 · Cited by 491 · cited 1× · see citing works
“The authors in [37] and [38] showed that GAN-generated content contains distinct digital fingerprints which can be learned and used to classify images as GAN-generated or not.”
BackgroundFighting Fake News: Image Splice Detection via Learned Self-Consistency
Huh, M., Liu, A., Owens, A., & Efros, A. A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01252-6_7 · Cited by 465 · see citing works
(2019) · Cited by 415 · see citing works
Self-citationThe Deepfake Detection Challenge (DFDC) Preview Dataset
Dolhansky, B., Howes, R., Pflaum, B., Baram, N., & Ferrer, C. C. (2019) · arXiv · doi:10.48550/arxiv.1910.08854 · Cited by 413 · cited 16× · see citing works
“The Deep Fake Detection Challenge Preview dataset (DFDC-P) [29] consists of 1131 real and 4113 face-swap deep fakes videos of 66 individuals of various genders, ages and ethnicities.”
BackgroundInfluentialNagano, K., Seo, J., Xing, J., Wei, L., Li, Z., Saito, S., Agarwal, A., Fursund, J., & Li, H. (2018) · ACM Transactions on Graphics · doi:10.1145/3272127.3275075 · Cited by 165 · cited 1× · see citing works
“In a related puppet-master technique, the authors in [23] build a photo-realistic avatar GAN that synthesizes faces in arbitrary expressions and orientations in real-time on a mobile device.”
MethodFarid, H. (2016) · The MIT Press eBooks · doi:10.7551/mitpress/10451.001.0001 · Cited by 130 · cited 1× · see citing works
“There is a significant literature in the general area of digital forensics [6].”
BackgroundSelf-citationSelf-supervised learning of a facial attribute embedding from video
Wiles, O., Koepke, A. S., & Zisserman, A. (2018) · arXiv · doi:10.48550/arxiv.1808.06882 · Cited by 111 · cited 1× · see citing works
“In [21], the authors proposed a self-supervised, encoderdecoder network (Facial Attributes-Net, FAb-Net) trained to embed the movement between video frames into a common 256-D space.”
BackgroundCeleb-DF: A New Dataset for DeepFake ForensicsPreprint
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2019) · arXiv (Cornell University) · Cited by 91 · see citing works
Deferred Neural Rendering: Image Synthesis using Neural TexturesPreprint
Thies, J., Zollhöfer, M., & Nießner, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.12356 · Cited by 90 · cited 2× · see citing works
“amounts of training data. The more recent method FS-GAN [24], on the other hand, creates high-quality fakes using a recurrent neural network-based reenactment with less training data. Neural Textures [29] is a generic image synthesis framework that combines traditional graphics rendering with more modern learnable com…”
MethodDetecting and Simulating Artifacts in GAN Fake ImagesPreprint
Zhang, X., Karaman, S., & Chang, S.-F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.06515 · Cited by 39 · cited 1× · see citing works
“The authors in [37] and [38] showed that GAN-generated content contains distinct digital fingerprints which can be learned and used to classify images as GAN-generated or not.”
Background
Flagged first, then by citations
1 of the 39 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A.C., Bengio, Y.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems. pp. 2672-2680 (2014)
- Nagano, K., Seo, J., Xing, J., Wei, L., Li, Z., Saito, S., Agarwal, A., Fursund, J., Li, H.: PaGAN: Real-time avatars using dynamic textures. ACM Transaction on Graphics (2018)
Cited by
Sorted by citations
Deep learning in computer vision: A critical review of emerging techniques and application scenarios
Chai, J., Zeng, H., Li, A., & Ngai, E. W. T. (2021) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100134 · Cited by 754 · see citing works
Masood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023) · Applied Intelligence · doi:10.1007/s10489-022-03766-z · Cited by 543 · see citing works
“This approach [147] works well for unseen cases, however, it may not generalize well to lip-synch-based deepfakes.”
BackgroundMethodInfluentialDeep Learning for Deepfakes Creation and Detection: A Survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2019) · arXiv · doi:10.48550/arxiv.1909.11573 · Cited by 464
“Using appearance and behaviour [148] Rules based on facial and behavioural features.”
MethodDeep learning for deepfakes creation and detection: A survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103525 · Cited by 464 · see citing works
“Using appearance and behaviour [148] Rules based on facial and behavioural features.”
MethodDeepFake Detection for Human Face Images and Videos: A Survey
Malik, A., Kuribayashi, M., Abdullahi, S. M., & Khan, A. N. (2022) · IEEE Access · doi:10.1109/access.2022.3151186 · Cited by 297 · see citing works
“Agarwal et al. [88], [97] proposed a combination of static biometrics on facial identity with temporal behavioral biometrics on facial expressions and head movements for DeepFake detection.”
BackgroundDeepfake detection by human crowds, machines, and machine-informed crowds
Groh, M., Epstein, Z., Firestone, C., & Picard, R. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2110013119 · Cited by 248 · see citing works
“While there are many proposed techniques for algorithmically detecting fakes (including affective computing approaches like examining heart rate and breathing rate (37) and looking for emotion-congruent speech and facial expressions) (38, 39), the most accurate computer vision model in the contest (40) focused on loca…”
MethodID-Reveal: Identity-aware DeepFake Video Detection
Cozzolino, D., Rossler, A., Thies, J., Niesner, M., & Verdoliva, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01483 · Cited by 221 · see citing works
“The idea is to focus on the specific traits of a subject and then detect possible anomalies with respect to them [4, 2].”
BackgroundMethodInfluentialNeural Head Avatars from Monocular RGB Videos
Grassal, P.-W., Prinzler, M., Leistner, T., Rother, C., NieBner, M., & Thies, J. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01810 · Cited by 205 · see citing works
“While these methods can be trained to detect specific manipulation methods [62, 63], generalized methods [2, 22, 23] have problems in reliably detecting fakes.”
BackgroundMethodCountering Malicious DeepFakes: Survey, Battleground, and Horizon
Juefei-Xu, F., Wang, R., Huang, Y., Guo, Q., Ma, L., & Liu, Y. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01606-8 · Cited by 191 · see citing works
“Researchers leveraged this clue for detecting lip-sync DeepFakes (Agarwal et al., 2020b).”
BackgroundA Hybrid CNN-LSTM model for Video Deepfake Detection by Leveraging Optical Flow Features
Saikia, P., Dholaria, D., Yadav, P., Patel, V., & Roy, M. (2022) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892905 · Cited by 133 · see citing works
“Moreover, many traditional ways have also been explored to detect manipulated media, such as exposing inconsistent in headposes, consideration of the background color manipulation [9].”
BackgroundA Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats
Mubarak, R., Alsboui, T., Alshaikh, O., Inuwa-Dutse, I., Khan, S., & Parkinson, S. (2023) · IEEE Access · doi:10.1109/access.2023.3344653 · Cited by 132 · see citing works
“Agarwal et al. [168] proposed a face swap detection method that combines deep learning features and behavioural biometrics to identify manipulated videos.”
MethodDeep Learning for Deepfakes Creation and Detection: A Survey
Nguyen, T. T., Nguyen, M. C., Nguyen, D. T., Nguyen, D. T., & Nahavandi, S. (2020) · Figshare · doi:10.6084/m9.figshare.12731039.v1 · Cited by 122 · see citing works
FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning
Kim, M., Tariq, S., & Woo, S. S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00111 · Cited by 118 · see citing works
“These methods include splice detection [88, 89, 8, 7, 30, 70], abnormal eye blinking [50], signal level artifacts [55, 51], irregular head poses [84], peculiar behavior patterns [3, 2], and many other data-driven methods that do not rely on particular traces or artifacts in the deepfake videos [75, 76, 77, 47, 46, 41,…”
MethodDeepfake Detection: A Comprehensive Survey from the Reliability Perspective
Wang, T., Liao, X., Chow, K. P., Lin, X., & Wang, Y. (2025) · ACM Computing Surveys · doi:10.1145/3699710 · Cited by 107 · see citing works
“The most recent KoDF [95] dataset is so far the largest Deepfake benchmark dataset that is publicly available with reasonable diversity and contains synthetic videos at high resolutions.”
Deepfake Media Forensics: Status and Future Challenges
Amerini, I., Barni, M., Battiato, S., Bestagini, P., Boato, G., Bruni, V., Caldelli, R., De Natale, F., De Nicola, R., Guarnera, L., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11030073 · Cited by 113 · see citing works
“In [146], the authors establish a mapping between audio and video frames by analyzing the changes in the lip opening degree, while in [32,147,148], the authenticity of a speaker is verified by detecting anomalous correspondences between their facial movements and what they say.”
Audio-Visual Person-of-Interest DeepFake Detection
Cozzolino, D., Pianese, A., Nießner, M., & Verdoliva, L. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00101 · Cited by 104 · see citing works
“The first papers on this topic exploited specific face and head movement patterns [6,5,9], inconsistencies between mouth shape dynamics and spoken phonemes [3] or cues related to the specific words uttered by the subject [4].”
BackgroundMethodCreating, Using, Misusing, and Detecting Deep Fakes
Farid, H. (2022) · Journal of Online Trust and Safety · doi:10.54501/jots.v1i4.56 · Cited by 92 · see citing works
Self-citationDynamic Difference Learning With Spatio–Temporal Correlation for Deepfake Video Detection
Yin, Q., Lu, W., Li, B., & Huang, J. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3290752 · Cited by 92 · see citing works
“Agarwal et al. mined spatio-temporal features for face forgery detection by measuring the consistency of mouth shapes and visemes [40], [41], appearance and behavior [42].”
BackgroundVideo Transformer for Deepfake Detection with Incremental Learning
Khan, S. A., & Dai, H. (2021) · Proceedings of the 29th ACM International Conference on Multimedia · doi:10.1145/3474085.3475332 · Cited by 79 · see citing works
Estimating optical flow: A comprehensive review of the state of the art
Alfarano, A., Maiano, L., Papa, L., & Amerini, I. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104160 · Cited by 78 · see citing works
Detecting Deep-Fake Videos from Aural and Oral Dynamics
Agarwal, S., & Farid, H. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00109 · Cited by 69 · see citing works
“These techniques focus on semantically meaningful features including inconsistencies in eye blinks [25], head-pose [36], physiological signals [13], mouth shape and movement [5], and distinct mannerisms [6, 4].”
BackgroundSelf-citationDeepfake audio detection by speaker verification
Pianese, A., Cozzolino, D., Poggi, G., & Verdoliva, L. (2022) · 2022 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs55849.2022.9975428 · Cited by 74 · see citing works
Shin, S. Y., & Lee, J. (2022) · Digital Journalism · doi:10.1080/21670811.2022.2026797 · Cited by 67 · see citing works
“With increasing concerns over the potential impacts of deepfakes on our society, the demand for effective prevention and correction methods is also rising (e.g., Agarwal et al. 2020; Hwang, Ryu, and Jeong 2021).”
BackgroundDeepFake on Face and Expression Swap: A Review
Waseem, S., Abu Bakar, S. A. R. S., Ahmed, B. A., Omar, Z., Eisa, T. A. E., & Dalam, M. E. E. (2023) · IEEE Access · doi:10.1109/access.2023.3324403 · Cited by 65 · see citing works
“In another study, Agarwal et al. [132] proposed an approach for detecting deepfake face swap.”
BackgroundAn Experimental Evaluation on Deepfake Detection using Deep Face Recognition
Ramachandran, S., Nadimpalli, A. V., & Rattani, A. (2021) · IEEE International Carnahan Conference on Security Technology (ICCST) · doi:10.1109/iccst49569.2021.9717407 · Cited by 71 · see citing works
On Improving Cross-dataset Generalization of Deepfake Detectors
Nadimpalli, A. V., & Rattani, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00019 · Cited by 63 · see citing works
“, facial expression, head, and body movement) have been used for deep fake detection [2, 3, 10, 25].”
MethodTIMIT-TTS: A Text-to-Speech Dataset for Multimodal Synthetic Media Detection
Salvi, D., Hosler, B., Bestagini, P., Stamm, M. C., & Tubaro, S. (2023) · IEEE Access · doi:10.1109/access.2023.3276480 · Cited by 65 · see citing works
“These leverage different characteristics, ranging from low-level artifacts left by the generators [14], [15] to more semantic aspects [16], [17].”
BackgroundDetecting computer-generated disinformation
Stiff, H., & Johansson, F. (2022) · International Journal of Data Science and Analytics · doi:10.1007/s41060-021-00299-5 · Cited by 79 · see citing works
“However, compared to detection of images [11,31,45,46] and videos [2,7,32] being synthesized or manipulated using generative models, its text counterpart is under-researched.”
BackgroundA novel approach for detecting deep fake videos using graph neural network
El-Gayar, M. M., Abouhawwash, M., Askar, S., & Sweidan, S. (2024) · Journal Of Big Data · doi:10.1186/s40537-024-00884-y · Cited by 60 · see citing works
“Agarwal et al. [7] proposed a method combining temporal and behavioral biometric features with a CNN, demonstrating robustness against coun-terattacks and effective generalization across FF ++ , DFDC-P, and Celeb-DF datasets.”
DFGNN: An interpretable and generalized graph neural network for deepfakes detection
Khalid, F., Javed, A., Ain, Q., Ilyas, H., & Irtaza, A. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119843 · Cited by 58 · see citing works
Video deepfake detection using a hybrid CNN-LSTM-Transformer model for identity verification
Πετμεζάς, Γ., Vanian, V., Konstantoudakis, K., Almaloglou, E. E. I., & Zarpalas, D. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20548-6 · Cited by 67 · see citing works
“At the same time, Agarwal et al. [14] introduced a biometric-based forensic method that combines static facial recognition and temporal behavioral traits, which are learned through a CNN, for the detection of face-swap deepfakes, while a study by Wang and Dantcheva [15] compared three different…”
Virtual microstructure design for steels using generative adversarial networks
Lee, J.-W., Goo, N. H., Park, W. B., Pyo, M., & Sohn, K. (2020) · Engineering Reports · doi:10.1002/eng2.12274 · Cited by 56 · see citing works
CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation
Kim, M., Tariq, S., & Woo, S. S. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475535 · Cited by 58 · see citing works
Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection
Cui, X., Li, Y., Luo, A., Zhou, J., & Dong, J. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01789 · Cited by 58 · see citing works
“…to capture the forgery traces, utilizing features ranging from the biological signals ( e.g. , eye blinking [39], heart-beat rhythm [52], head pose [72], facial action units [1]), frequency signals ( e.g. , [43, 47, 53]), and auto-learned clues with dedicated training schemes ( e.g. , [6, 11, 58]).”
TI <sup>2</sup> Net: Temporal Identity Inconsistency Network for Deepfake Detection
Liu, B., Liu, B., Ding, M., Zhu, T., & Yu, X. (2023) · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv56688.2023.00467 · Cited by 50 · see citing works
“Besides, we also compare our method with two close-set baselines: (4) A&B [2]: A Deepfake detector that integrates behaviour and appearance of identities.”
BackgroundMethodInfluentialImproving Generalization of Deepfake Detection With Data Farming and Few-Shot Learning
Korshunov, P., & Marcel, S. (2022) · IEEE Transactions on Biometrics, Behavior, and Identity Science · doi:10.1109/tbiom.2022.3143404 · Cited by 50 · see citing works
“…networks, such as Xception [1], capsules networks [8], EfficientNet [2], and discriminators of GANs used to generate synthetic images [9], which were shown to outperform the methods based on shallow CNNs, facial physical characteristics [10], [11], [12], [13], or distortion features [14], [15].”
MethodLearning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videos
Bai, Z., Tan, F., Huang, Z., Sarkar, K., Tang, D., Qiu, D., Meka, A., Du, R., Dou, M., Orts‐Escolano, S., et al. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01620 · Cited by 49 · see citing works
“On the viewing side, forgery detection [2, 25, 35, 36, 41] is an active research field with promising progress.”
BackgroundDetecting Real-Time Deep-Fake Videos Using Active Illumination
Gerstner, C. R., & Farid, H. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00015 · Cited by 45 · see citing works
“High-level techniques focus on semantically meaningful features, including inconsistencies in eye blinks [20], head-pose [37], physiological signals [10], mouth shape and movement [5], and distinct mannerisms [3, 6].”
BackgroundSelf-citationLeveraging edges and optical flow on faces for deepfake detection
Chintha, A., Rao, A. G., Sohrawardi, S. J., Bhatt, K., Wright, M., & Ptucha, R. (2020) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304936 · Cited by 43 · see citing works
“[4, 2, 3] took a biometric approach to deepfake detection by looking for atypical facial behavior.”
MethodFrequency Domain Filtered Residual Network for Deepfake Detection
Wang, B., Wu, X., Tang, Y., Ma, Y., Shan, Z., & Wei, F. (2023) · Mathematics · doi:10.3390/math11040816 · Cited by 41 · see citing works
A forensic evaluation method for DeepFake detection using DCNN-based facial similarity scores
Reis, P. M. G. I., & Ribeiro, R. O. (2023) · Forensic Science International · doi:10.1016/j.forsciint.2023.111747 · Cited by 41 · see citing works
Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
Ur Rehman Ahmed, N., Badshah, A., Adeel, H., Tajammul, A., Daud, A., & Alsahfi, T. (2025) · IEEE Access · doi:10.1109/access.2024.3523288 · Cited by 45 · see citing works
GBDF: Gender Balanced DeepFake Dataset Towards Fair DeepFake Detection
Nadimpalli, A. V., & Rattani, A. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-37742-6_25 · Cited by 46 · see citing works
Improving Generalization of Deepfake Detectors by Imposing Gradient Regularization
Guan, W., Wang, W., Dong, J., & Peng, B. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3396064 · Cited by 38 · see citing works
“To ensure that detectors can learn method-agnostic forgery features, some previous studies [21], [28], [29], [30], [31] focus on utilizing semantic information to explore some universal inconsistency or anomaly in forgery images.”
Background3D CNN Architectures and Attention Mechanisms for Deepfake Detection
Roy, R., Joshi, I., Das, A., & Dantcheva, A. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-87664-7_10 · Cited by 36 · see citing works
A Comparative Study on Physical and Perceptual Features for Deepfake Audio Detection
Li, M., Ahmadiadli, Y., & Zhang, X.-P. (2022) · Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia · doi:10.1145/3552466.3556523 · Cited by 35 · see citing works
“As audio synthesis techniques grow in popularity, especially after the development of deep learning techniques, anti-spoofing methods are proposed in the literature to detect bonafide audio from Deepfake ones [1, 2, 31, 36].”
MethodDeepfakes: evolution and trends
Gil, R., Virgili‐Gomà, J., López, J. M., & Garcı́a, R. (2023) · Soft Computing · doi:10.1007/s00500-023-08605-y · Cited by 40 · see citing works
“…learning 27.7% convolutional neural networks 23.1% detection methods 16.9% Yang et al. (2019b), Jiang et al. (2020), Agarwal et al. (2019b), Agarwal et al. (2020a), Mittal et al. (2020b), Zi et al. (2020), Agarwal et al. (2020b), Chen et al. (2020), Montserrat et al. (2020), Ahmed…”
InfluentialAdaptive Face Forgery Detection in Cross Domain
Song, L., Fang, Z., Li, X., Dong, X., Jin, Z., Chen, Y., & Lyu, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19830-4_27 · Cited by 35 · see citing works
“(2) Freq. temporal feature [4, 34], optical flow [5], frequency [18, 20, 35, 40, 50], local facial region [10, 47, 55], forgery boundary [27] and biometric signals [12, 13, 37], to capture more robust features for forgery detection.”
BackgroundSpatial-frequency feature fusion based deepfake detection through knowledge distillation
Wang, B., Wu, X., Wang, F., Zhang, Y., Wei, F., & Song, Z. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108341 · Cited by 34 · see citing works
Subjective and Objective Evaluation of Deepfake Videos
Korshunov, P., & Marcel, S. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414258 · Cited by 32 · see citing works
“The recent surge in the number of publicly available deepfake databases allowed researchers to train and test detection approaches based on very deep neural networks, such as Xception [3], capsules networks [6], ResNet50 [7], and EfficientNet [8], which were shown to outperform the methods based on shallow CNNs, facia…”
BackgroundVisual User-Generated Content Verification in Journalism: An Overview
Khan, S. A., Sheikhi, G., Opdahl, A. L., Rabbi, F., Stoppel, S., Trattner, C., & Dang‐Nguyen, D. (2023) · IEEE Access · doi:10.1109/access.2023.3236993 · Cited by 36 · see citing works
“Some examples include, biological signals, behavioural features, 3D face decomposition features, and optical flow [117], [118], [119], [120], [121], [122], [123], [109], birds [110], buses [109], indoor and outdoor scenes [109].”
BackgroundA deep learning model for FaceSwap and face-reenactment deepfakes detection
Nawaz, M., Javed, A., & Irtaza, A. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111854 · Cited by 31 · see citing works
Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection
Attorresi, L., Salvi, D., Borrelli, C., Bestagini, P., & Tubaro, S. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-37742-6_21 · Cited by 30 · see citing works
Tariq, S., Jeon, S., & Woo, S. S. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3512212 · Cited by 54 · see citing works
“CLRNet [63], (iv) ABNet [2], (v) ShallowNet [62], (vi) MesoNet [1], and (vii) FTDetect [31], for the defense experiments.”
BackgroundMINTIME: Multi-Identity Size-Invariant Video Deepfake Detection
Coccomini, D. A., Zilos, G. K., Amato, G., Caldelli, R., Falchi, F., Papadopoulos, S., & Gennaro, C. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3409054 · Cited by 33 · see citing works
“Some works attempt to detect deepfake by identifying a person from temporal facial features, specific to how a person moves while talking [15] or by the usage of biometrics analysis techniques [2].”
BackgroundA Review of Deep Learning-based Approaches for Deepfake Content Detection
Passos, L. A., Jodas, D., Costa, K. A. P., Júnior, L. A. S., Rodrigues, D., Ser, J. D., Camacho*, D., & Papa, J. (2023) · doi:10.22541/au.169735672.27713914/v1 · Cited by 116 · see citing works
Emergence of deepfakes and video tampering detection approaches: A survey
Kingra, S., Aggarwal, N., & Kaur, N. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13100-x · Cited by 33 · see citing works
“Based on this, an appearance and behavioral-biometrics based model [3] was utilized to capture facial expressions and head movements of a person in the video along with static facial features.”
MethodMD-CSDNetwork: Multi-Domain Cross Stitched Network for Deepfake Detection
Agarwal, A., Agarwal, A., Sinha, S., Mayank Vatsa, A., & Singh, R. (2021) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg52635.2021.9666937 · Cited by 29 · see citing works
Global–Local Facial Fusion Based GAN Generated Fake Face Detection
Xue, Z., Jiang, X., Liu, Q., & Wei, Z. (2023) · Sensors · doi:10.3390/s23020616 · Cited by 32 · see citing works
Watch Those Words: Video Falsification Detection Using Word-Conditioned Facial Motion
Agarwal, S., Hu, L., Ng, E., Darrell, T., Li, H., & Rohrbach, A. (2023) · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv56688.2023.00469 · Cited by 28 · see citing works
“The videos for Obama, Biden, and Trump are from WLDR and for Harris, Oliver and O’Brien are created using the FaceSwap library [35].”
BackgroundMethodInfluentialSelf-citationFace manipulated deepfake generation and recognition approaches: a survey
Rehaan, M., Kaur, N., & Kingra, S. (2023) · Smart Science · doi:10.1080/23080477.2023.2268380 · Cited by 31 · see citing works
“This method [89] might not perform effectively on lip-sync deepfakes.”
BackgroundMethodInfluentialEmotions unveiled: detecting COVID-19 fake news on social media
Farhoudinia, B., Öztürkcan, S., & Kasap, N. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-03083-5 · Cited by 28 · see citing works
“Advancements in computer graphics, computer vision, and machine learning have made it feasible to create fake images or movies by merging them together (Agarwal et al., 2020).”
Hashmi, A., Shahzad, S. A., Lin, C., Tsao, Y., & Wang, H. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3554477 · Cited by 35 · see citing works
“Similarly, Lip Forensics [42] exploits visual lip movements to detect forgeries in videos with an accuracy of 0.76.”
InfluentialZhang, Y., Pang, Z., Huang, S., Wang, C., & Zhou, X. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00154-8 · Cited by 32 · see citing works
“Agarwal et al. (2018) enabled the model to learn spatio-temporal 5 Challenges, future research directions and conclusions”
Improving Generalization of Deepfake Detection by Training for Attribution
Jain, A., Korshunov, P., & Marcel, S. (2021) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp53017.2021.9733468 · Cited by 25 · see citing works
“An extensive set of the recently available deepfake video databases (see Figure 1 and Figure 2 for examples and Table I for an overview) allow researchers to train and test detection approaches based on very deep neural networks, such as Xception [16], capsules networks [14], and EfficientNet [13], which were shown to…”
MethodVideo authentication detection using deep learning: a systematic literature review
Alrawahneh, A. A.-M., Abdullah, S. N. H. S., Abdullah, S. N. H. S., Kamarudin, N. H., & Taylor, S. K. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05997-8 · Cited by 24 · see citing works
MIS-AVoiDD: Modality Invariant and Specific Representation for Audio-Visual Deepfake Detection
Katamneni, V. S., & Rattani, A. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00207 · Cited by 28 · see citing works
A guided-based approach for deepfake detection: RGB-depth integration via features fusion
Leporoni, G., Maiano, L., Papa, L., & Amerini, I. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2024.03.025 · Cited by 22 · see citing works
DeepFake video detection: Insights into model generalisation — A Systematic review
Ramanaharan, R., Guruge, D. B., & Agbinya, J. I. (2025) · Data and Information Management · doi:10.1016/j.dim.2025.100099 · Cited by 25 · see citing works
On the Exploitation of Deepfake Model Recognition
Guarnera, L., Giudice, O., Nießner, M., & Battiato, S. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00016 · Cited by 23 · see citing works
“Many techniques are available in literature that focus on different architectures and scenarios [2, 7, 13, 16, 37, 39].”
BackgroundDeepfake Generation and Detection - An Exploratory Study
Garg, D., & Gill, R. (2023) · IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON) · doi:10.1109/upcon59197.2023.10434896 · Cited by 27 · see citing works
Sohrawardi, S. J., Wu, Y.-C., Hickerson, A., & Wright, M. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641973 · Cited by 22 · see citing works
Comparative study of deep learning techniques for DeepFake video detection
Khan, R., Sohail, M., Usman, I., Sandhu, M. M., Jafri, M. R., Yaqub, M. A., & Liotta, A. (2024) · ICT Express · doi:10.1016/j.icte.2024.09.018 · Cited by 23 · see citing works
Saif, S., Tehsin, S., & Ali, S. S. (2024) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2024.123471 · Cited by 21 · see citing works
Demystifying Attention Mechanisms for Deepfake Detection
Das, A., Das, S., & Dantcheva, A. (2021) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg52635.2021.9667026 · Cited by 17 · see citing works
Video Manipulations Beyond Faces: A Dataset with Human-Machine Analysis
Mittal, T., Sinha, R., Swaminathan, V., Collomosse, J. P., & Manocha, D. (2023) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw58289.2023.00071 · Cited by 16 · see citing works
“More recently, interesting affective computing approaches that focus on correlated emotion signals from audio-visual cues [40, 3], and detecting signals like heart rate and breathing rate [47] from the videos have also been proposed.”
BackgroundFake-checker: A fusion of texture features and deep learning for deepfakes detection
Huda, N. U., Javed, A., Maswadi, K., Alhazmi, A. H., & Ashraf, R. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17586-x · Cited by 15 · see citing works
“Later, some works [6] [7] tried to build a generalized model but failed to generalize better for other datasets.”
Hydara, E., Kikuchi, M., & Ozono, T. (2024) · IEEE Access · doi:10.1109/access.2024.3480320 · Cited by 18 · see citing works
“Agarwal et al. [13] introduced a combined static and behavioral biometric technique to detect face-swap deepfakes, which correlates facial recognition with dynamic cues, such as expressions and head movements.”
BackgroundMethodMulti-modal Semantic Inconsistency Detection in Social Media News Posts
McCrae, S., Wang, K., & Zakhor, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-98355-0_28 · Cited by 15 · see citing works
Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization
Katamneni, V. S., & Rattani, A. (2024) · 2024 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb62174.2024.10744480 · Cited by 20 · see citing works
“As a countermeasure, several unimodal audio and visual deepfake detectors have been proposed [32, 23, 2, 39, 13, 24, 46].”
BackgroundBiFPro: A Bidirectional Facial-data Protection Framework against DeepFake
Liu, H., Li, X., Zhou, W., Fang, H., Bestagini, P., Zhang, W., Chen, Y., Tubaro, S., Yu, N., He, Y., et al. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3613752 · Cited by 14 · see citing works
“Some DeepFake detection methods [2, 3, 29, 30, 38, 57] focus on the obvious artifacts at the explicit facial feature level.”
BackgroundSTIDNet: Identity-Aware Face Forgery Detection With Spatiotemporal Knowledge Distillation
Fang, M., Yu, L., Xie, H., Tan, Q., Tan, Z., Hussain, A., Wang, Z., Li, J., & Tian, Z. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3356549 · Cited by 14 · see citing works
“Consider that the generalization ability is the most important property for detection model, our comparison is following a cross-dataset protocol [33], [35], [36], [39], [40], [42], [46], [47], i.e., all the methods are tested in the manipulation dataset that unseen during training.”
BackgroundMethodInfluentialSemi-Supervised Deep Domain Adaptation for Deepfake Detection
Seraj, M. S., Singh, A., & Chakraborty, S. (2024) · 2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00116 · Cited by 14 · see citing works
“…detection [12,13,21,56,74,75], abnormal eye blinking [38], signal level artifacts [39, 45], irregular head poses [69], peculiar behavior patterns [8, 9], and many other data-driven methods that do not rely on particular artifacts in the deepfake videos [22–24, 28, Domain Adaptation: Domain…”
BackgroundDeepfake Video Detection Based on Convolutional Neural Networks
Adnan, S. R., & Abdulbaqi, H. A. (2022) · International Conference on Data Science and Intelligent Computing (ICDSIC) · doi:10.1109/icdsic56987.2022.10075830 · Cited by 13 · see citing works
“Recently, deep learning techniques are continuously developed especially generative adversarial networks and autoencoders for the Deepfake field [7] that display as follows:”
BackgroundMethodAdversarially robust deepfake media detection using fused convolutional neural network predictionsPreprint
Khan, S. A., Artusi, A., & Dai, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.05950 · Cited by 27 · see citing works
“Our models also beat the Kaggle DFDC competition’s winning model on LogLoss score as well as achieves higher accuracy then the previously proposed studies [20, 21].”
ResultHan, C., Mitra, P., & Billah, S. M. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642817 · Cited by 12 · see citing works
“For instance, sighted individuals can detect inconsistent lighting, shadows, and refections in the video or observe unnatural facial movements, expressions, and blinking that do not align with speech [6, 22, 44].”
BackgroundDeepFake Detection Based VGG-16 Model
Jbara, W. A., & Soud, J. H. (2024) · International Conference on Cyber Resilience (ICCR) · doi:10.1109/iccr61006.2024.10533024 · Cited by 14 · see citing works
“A survey of recent research on Deepfake detection, arranged according to deep learning techniques, is provided in this section. wherein Agarwal et al. [18] presented DeepFake detection, a biometric-based forensic system.”
MethodDeep Learning for Forgery Face Detection Using Fuzzy Fisher Capsule Dual Graph
Arunkumar, P. M., Sangeetha, Y., Raja, P. V., & Sangeetha, S. N. (2022) · Information Technology And Control · doi:10.5755/j01.itc.51.3.31510 · Cited by 13 · see citing works
“(2020) [2] Video Siamese network Deepfake TIMIT and DFDC”
BackgroundBeuve, N., Hamidouche, W., & Olivier Déforges, A. (2021) · doi:10.1145/3476099.3484316 · Cited by 11 · see citing works
“Eyes were then followed by ears [3], mouth [2] and the whole face [48] movement inconsistencies.”
BackgroundLyu, S. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-16-7621-5_12 · Cited by 11 · see citing works
Compound Frechet Inception Distance for Quality Assessment of GAN Created ImagesPreprint
Nunn, E. J., Khadivi, P., & Samavi, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.08575 · Cited by 29 · see citing works
Facial Behavior Analysis-Based Deepfake Video Detection using GAN Discriminator
Jaleel, Q., & Ali, I. H. (2022) · International Conference on Data Science and Intelligent Computing (ICDSIC) · doi:10.1109/icdsic56987.2022.10075660 · Cited by 10 · see citing works
“[8] detecting deepfakes in videos was accomplished through the use of forensic technology in this proposal.”
BackgroundMethodAvatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos
Prashnani, E., Nagano, K., Mello, S. D., Luebke, D. P., & Gallo, O. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72633-0_12 · Cited by 10 · see citing works
IEIRNet: Inconsistency Exploiting Based Identity Rectification for Face Forgery Detection
Fang, M., Yu, L., Song, Y., Zhang, Y., & Xie, H. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3453066 · Cited by 9 · see citing works
“Specifically, the synthesized data is introduced in the training phase of Face X-ray [34], ICT [46] and SBIs [36], while A&B [45], ID-Reveal [43] and DFR [42] are only trained with real images.”
InfluentialAlkurdi, D. A., Cevik, M., & Akgündoğdu, A. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.057029 · Cited by 9 · see citing works
“In view of the increasing number of creative fakes manufactured by computers in music and movies [7] present a biometric forensic method for the assessment of disinformation created by swapping faces.”
A Transformer-Based DeepFake-Detection Method for Facial Organs
Xue, Z., Liu, Q., Shi, H., Zou, R., & Jiang, X. (2022) · Electronics · doi:10.3390/electronics11244143 · Cited by 9 · see citing works
Jain, A. K., Yadav, A., Kumar, M., García‐Peñalvo, F. J., Chui, K. T., & Santaniello, D. (2022) · International Journal of Cloud Applications and Computing · doi:10.4018/ijcac.312565 · Cited by 9 · see citing works
A comprehensive analysis of digital video forensics techniques and challenges
Sandhya, & Kashyap, A. (2023) · Iran Journal of Computer Science · doi:10.1007/s42044-023-00165-6 · Cited by 11 · see citing works
A Multi-Layer Capsule-based Forensics Model for Fake Detection of Digital Visual Media
Khalil, S. S., Youssef, S. M., & Saleh, S. N. (2021) · International Conference on Communications, Signal Processing, and their Applications (ICCSPA) · doi:10.1109/iccspa49915.2021.9385719 · Cited by 9 · see citing works
“Audio production can place words to the voices of people who didn’t say them, fake image creation can produce images of people in places they have never been to and fake video creations can forge victim’s actions and words [1].”
BackgroundMethodRobust Face-Swap Detection Based on 3D Facial Shape Information
Guan, W., Wang, W., Dong, J., Peng, B., & Tan, T. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20497-5_33 · Cited by 10 · see citing works
- Authors
- Agarwal, S., Farid, H., El-Gaaly, T., & Lim, S.-N.
- Affiliations
- University of California, Berkeley (US)
- Meta (United States) (US)
- Venue
- 2020 IEEE International Workshop on Information Forensics and Security (WIFS)
- Publisher
- IEEE
- Published
- 2020-12-06
- Pages
- 1-6
- ISSN
- 2157-4774 (ISSN-L)
- OpenAlex
- W3021589373
- Cited by
- 242
- References
- 39
- Citations by year
- 2026: 26 · 2025: 39 · 2024: 79 · 2023: 36 · 2022: 36 · 2021: 22 · 2020: 4
- FWCI
- 7.56
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE International Workshop on Information Forensics and Security (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Advanced Research Projects Agency
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- deepfake detection, face recognition, facial expressions, head movement, behavioral biometrics, metric learning, disinformation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
