Deep convolutional pooling transformer for deepfake detection
Open accessAbstract
Recently, Deepfake has drawn considerable public attention due to security and privacy concerns in social media digital forensics. As the wildly spreading Deepfake videos on the Internet become more realistic, traditional detection techniques have failed in distinguishing between real and fake. Most existing deep learning methods mainly focus on local features and relations within the face image using convolutional neural networks as a backbone. However, local features and relations are insufficient for model training to learn enough general information for Deepfake detection. Therefore, the existing Deepfake detection methods have reached a bottleneck to further improve the detection performance. To address this issue, we propose a deep convolutional Transformer to incorporate the decisive image features both locally and globally. Specifically, we apply convolutional pooling and re-attention to enrich the extracted features and enhance efficacy. Moreover, we employ the barely discussed image keyframes in model training for performance improvement and visualize the feature quantity gap between the key and normal image frames caused by video compression. We finally illustrate the transferability with extensive experiments on several Deepfake benchmark datasets. The proposed solution consistently outperforms several state-of-the-art baselines on both within- and cross-dataset experiments.
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?
Augmenting training datasets with diverse samples, employing transfer learning from pre-trained models, and integrating attention mechanisms can enhance generalization capabilities.
“Augmenting training datasets with diverse samples, employing transfer learning from pre-trained models, and integrating attention mechanisms can enhance generalization capabilities [45].”
From A Comprehensive Review of DeepFake Detection Using Advanced Machine Learning and Fusion Methods (2023) · cites this paper as [45]
Section 4.4 reports better performance from augmenting a limited keyframe training set and from combining keyframes with normal frames. Section 4.5 reports that re-attention improves cross-dataset performance. The Introduction and Section 2.2 mention pre-trained CNNs used by earlier approaches, but do not show that transfer learning from pre-trained models improves generalization; the claim therefore combines supported findings with an unsupported component. (LLM, conf=0.86)
Experimental — accuracy not yet measured
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
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
(1993) · doi:10.1109/cvpr.1993 · Cited by 17,989 · see citing works
Proceedings of IEEE International Conference on Computer Vision
(1995) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.1995.466933 · Cited by 13,117 · see citing works
Proceedings European Conference on Computer Vision 2002
Heyden, A., Sparr, G., Nielsen, M., & Johansen, P. (2002) · Lund University Publications (Lund University) · Cited by 5,153 · see citing works
Proceedings of the 16th international joint conference on Artificial Intelligence - IJCAI '99
Colton, S., Bundy, A., & Walsh, T. (1999) · Cited by 2,500 · 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
Deepfakes 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 · cited 1× · see citing works
“While the highquality Deepfake videos can facilitate human lives in multiple domains such as educational media and digital communications [58], they can be easily misused by criminals for malicious purposes and cause potential threats in societal, political, and business realms [28, 37, 52].”
BackgroundThe Emergence of Deepfake Technology: A Review
Westerlund, M. (2019) · Technology Innovation Management Review · doi:10.22215/timreview/1282 · Cited by 1,138 · cited 1× · see citing works
“While the highquality Deepfake videos can facilitate human lives in multiple domains such as educational media and digital communications [58], they can be easily misused by criminals for malicious purposes and cause potential threats in societal, political, and business realms [28, 37, 52].”
BackgroundContextual Transformer Networks for Visual Recognition
Li, Y., Yao, T., Pan, Y., & Mei, T. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3164083 · Cited by 771 · see citing works
Kietzmann, J., Lee, L. W., McCarthy, I. P., & Kietzmann, T. C. (2020) · Business Horizons · doi:10.1016/j.bushor.2019.11.006 · Cited by 504 · see citing works
WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
Zi, B., Chang, M., Chen, J., Ma, X., & Jiang, Y.-G. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413769 · Cited by 448 · cited 1× · see citing works
“Deepfake Detection Challenge (DFDC) [12] is one of the largest public Deepfake datasets [20, 31, 69] by far with 128,154 videos, which includes synthesized videos using eight diferent facial manipulation methods as listed in Table 1.”
MethodDeepViT: Towards Deeper Vision Transformer
Zhou, D., Kang, B., Jin, X., Yang, L., Lian, X., Jiang, Z., Hou, Q., & Feng, J. (2021) · arXiv · doi:10.48550/arxiv.2103.11886 · Cited by 398 · cited 2× · see citing works
“However, a deep ViT model empirically sufers from the attention collapse issue, such that the attention maps tend to be overly similar, and obvious performance decline is observed as the model goes deeper [67].”
BackgroundMethodCombating Deepfake Videos Using Blockchain and Smart Contracts
Hasan, H. R., & Salah, K. (2019) · IEEE Access · doi:10.1109/access.2019.2905689 · Cited by 339 · see citing works
Combining EfficientNet and Vision Transformers for Video Deepfake Detection
Coccomini, D. A., Messina, N., Gennaro, C., & Falchi, F. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-06433-3_19 · Cited by 296 · cited 2× · see citing works
“The three experiments are conducted upon the model with depths [4, 4, 6], [8, 8, 8], and [10, 10, 12] for the three phases and having the total depths of 14, 24, and 32 from shallow to deep, respectively.”
MethodFaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
Li, L., Bao, J., Yang, H., Chen, D., & Wen, F. (2019) · arXiv · doi:10.48550/arxiv.1912.13457 · Cited by 236 · cited 4× · see citing works
“1), has achieved remarkable success with various face synthesis algorithms in recent years [11, 25, 32, 38].”
BackgroundInfluentialDual Contrastive Learning for General Face Forgery Detection
Sun, K., Yao, T., Chen, S., Ding, S., Li, J., & Ji, R. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20130 · Cited by 209 · cited 1× · see citing works
“[46] proposed Dual Contrastive Learning (DCL) to study positive and negative paired data for Deepfake detection with better transferability.”
BackgroundUnderstanding Humans in Crowded Scenes
Zhao, J. C., Li, J., Cheng, Y., Sim, T., Yan, S., & Feng, J. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240509 · Cited by 189 · see citing works
Yao, T., Li, Y., Pan, Y., Wang, Y., Zhang, X.-P. S., & Mei, T. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3268446 · Cited by 187 · cited 1× · see citing works
“Recently, a Dual Vision Transformer (Dual-ViT) [54] further enhances the computational”
BackgroundProceedings of the 17 th International Conference on Pattern Recognition
(2004) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2004.1333675 · Cited by 178 · see citing works
Use of a Capsule Network to Detect Fake Images and VideosPreprint
Nguyen, H. H., Yamagishi, J., & Echizen, I. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.12467 · Cited by 163 · see citing works
ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
He, Y., Gan, B., Chen, S., Zhou, Y., Yin, G., Song, L., Sheng, L., Shao, J., & Liu, Z. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00434 · Cited by 161 · cited 1× · see citing works
“Deepfake Detection Challenge (DFDC) [12] is one of the largest public Deepfake datasets [20, 31, 69] by far with 128,154 videos, which includes synthesized videos using eight diferent facial manipulation methods as listed in Table 1.”
MethodDeepFake video detection using convolutional vision transformer
Wodajo, D., & Atnafu, S. (2021) · arXiv · doi:10.48550/arxiv.2102.11126 · Cited by 147 · cited 4× · see citing works
“It can also be observed that the Transformer based CViT [18] approach directly adopts the vision Transformer (ViT) [23] where the utilized vanilla Transformer is unstable on image analysis tasks.”
MethodInfluentialRSGAN: face swapping and editing using face and hair representation in latent spaces
Natsume, R., Yatagawa, T., & Morishima, S. (2018) · ACM SIGGRAPH 2018 Posters · doi:10.1145/3230744.3230818 · Cited by 140 · see citing works
HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
Wang, Y., Chen, X., Zhu, J., Chu, W., Tai, Y., Wang, C., Li, J., Wu, Y., Huang, F., & Ji, R. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/157 · Cited by 138 · cited 1× · see citing works
“HiiFace [56] and MegaFS [68] achieve high-resolution identity swap on 512 and 1,024 resolutions for arbitrary identities, respectively.”
BackgroundDeferred 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 · see citing works
Kemelmacher-Shlizerman, I. (2016) · ACM Transactions on Graphics · doi:10.1145/2897824.2925871 · Cited by 79 · see citing works
3D-Aided Deep Pose-Invariant Face Recognition
Zhao, J. C., Xiong, L., Yu, C., Cheng, Y., Li, J., Zhou, L. P., Xu, Y. L., Jayashree, K., Pranata, S., Shen, S., et al. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/165 · Cited by 79 · cited 1× · see citing works
“In light of the promising synthetic performance of Generative Adversarial Networks (GAN) [16] in domains such as face recognition [55, 63, 65], face synthesis [66], and human parsing [64], recent Deepfake research has exploited GAN for better synthesis authenticity.”
BackgroundFace.evoLVe: A cross-platform library for high-performance face analytics
Wang, Q., Zhang, P., Xiong, H., & Zhao, J. C. (2022) · Neurocomputing · doi:10.48550/arxiv.2107.08621 · Cited by 57 · cited 1× · see citing works
“In light of the promising synthetic performance of Generative Adversarial Networks (GAN) [16] in domains such as face recognition [55, 63, 65], face synthesis [66], and human parsing [64], recent Deepfake research has exploited GAN for better synthesis authenticity.”
BackgroundHybrid Transformer Network for Deepfake Detection
Khan, S. A., & Dang‐Nguyen, D. (2022) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1145/3549555.3549588 · Cited by 47 · cited 1× · see citing works
“It is also worth noting that a Transformer based approach, CViT [59], has been proposed with source code published and has shown promising results, and several latest models [8, 9, 26] are further designed following similar ideas but devoting better detection performance.”
MethodContrast Enhancement Estimation for Digital Image Forensics
Wen, L., Qi, H., & Lyu, S. (2018) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3183518 · Cited by 42 · cited 1× · see citing works
“While the classic forgery detection methods [42, 57] are insuicient to identify hyper-realistic Deepfake materials, deep learning models are frequently utilized.”
MethodDutta, T., & Gupta, H. P. (2017) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3002178 · Cited by 38 · cited 1× · see citing works
“On the contrary, the keyframes within a video are the only image frames that carry complete frame information with high resolution and do not suffer from information loss during the image frame reconstruction process [66].”
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 · cited 1× · see citing works
“It is also worth noting that a Transformer based approach, CViT [59], has been proposed with source code published and has shown promising results, and several latest models [8, 9, 26] are further designed following similar ideas but devoting better detection performance.”
MethodForensic Analysis of Linear and Nonlinear Image Filtering Using Quantization Noise
Ravi, H., Subramanyam, A. V., & Emmanuel, S. (2016) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2857069 · Cited by 12 · cited 1× · see citing works
“While the classic forgery detection methods [42, 57] are insuicient to identify hyper-realistic Deepfake materials, deep learning models are frequently utilized.”
MethodKhodabakhshi, N., & Hefeeda, M. M. (2013) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2422956.2422963 · Cited by 11 · cited 1× · see citing works
“2 and following the early approach for keyframe extraction [27], we irst derived all keyframe faces from the videos using FFmpeg [15] and augmented(1) the real keyframe faces for a balanced keyframe dataset.”
MethodInformation Technology Systems Infrastructure
Norman, T. (2014) · Elsevier eBooks · doi:10.1016/b978-0-12-800022-9.00011-5 · Cited by 4 · cited 1× · see citing works
“The commonly used compression formats include H.264, MPEG-4, and JPEG [45].”
MethodMINTIME: Multi-Identity Size-Invariant Video Deepfake DetectionPreprint
Coccomini, D. A., Kordopatis-Zilos, G., Amato, G. M., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.10996 · Cited by 4 · cited 1× · see citing works
“It is also worth noting that a Transformer based approach, CViT [59], has been proposed with source code published and has shown promising results, and several latest models [8, 9, 26] are further designed following similar ideas but devoting better detection performance.”
MethodDual Vision TransformerPreprint
Yao, T., Li, Y., Pan, Y., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.04976 · Cited by 2 · cited 1× · see citing works
“Recently, a Dual Vision Transformer (Dual-ViT) [54] further enhances the computational”
Background
Flagged first, then by citations
Research works printed but not linked: 27
- [2]2. Irene Amerini, Leonardo Galteri, Roberto Caldelli, and Alberto Del Bimbo. 2019. Deepfake video detection through optical flow based CNN. In Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshop. IEEE, 1205-1207.
- [6]6. Renwang Chen, Xuanhong Chen, Bingbing Ni, and Yanhao Ge. 2020. SimSwap: An efficient framework for high fidelity face swapping. In Proceedings of the MM'20: The 28th ACM International Conference on Multimedia.
- [7]7. Francois Chollet. 2017. Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Patten Recognition. 1251-1258.
- [12]12. Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, and Cristian Canton Ferrer. 2020. The DeepFake Detection Challenge (DFDC) Dataset. arXiv:cs.CV/2006.07397. Retrieved from https://arxiv.org/abs/ 2006.07397. Accessed August 29, 2021.
- [13]13. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In Proceedings of the International Confer- ence on Learning Representations.
- [16]16. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of the Advances in Neural Information Processing Systems, Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K. Q. Weinberger (Eds.), Vol. 27. Curran Associates, Inc.
- [19]19. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Patten Recognition. IEEE, 770-778.
- [21]21. Byeongho Heo, Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, Junsuk Choe, and Seong Joon Oh. 2021. Rethinking spatial dimensions of vision transformers. In Proceedings of the International Conference on Computer Vision.
- [22]22. Mousa Tayseer Jafar, Mohammad Ababneh, Mohammad Al-Zoube, and Ammar Elhassan. 2020. Forensics and analysis of deepfake videos. In Proceedings of the 2020 11th International Conference on Information and Communication Systems. IEEE, 053-058.
- [23]23. Liming Jiang, Ren Li, Wayne Wu, Chen Qian, and Chen Change Loy. 2020. DeeperForensics-1.0: A large-scale dataset for real-world face forgery detection. In Proceedings of the IEEE Conference on Computer Vision and Patten Recognition. 2889-2898.
- [30]30. Diederik P. Kingma and Max Welling. 2014. Auto-encoding variational bayes. In Proceedings of the 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.).
- [31]31. Patrick Kwon, Jaeseong You, Gyuhyeon Nam, Sungwoo Park, and Gyeongsu Chae. 2021. KoDF: A large-scale Korean deepfake detection dataset. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 10744-10753.
- [33]33. Yuezun Li, Xin Yang, Pu Sun, Honggang Qi, and Siwei Lyu. 2020. Celeb-DF: A large-scale challenging dataset for deepfake forensics. In Proceedings of the IEEE Conference on Computer Vision and Patten Recognition. 3207-3216.
- [35]35. Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin trans- former: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision.
- [36]36. Yuchen Luo, Yong Zhang, Junchi Yan, and Wei Liu. 2021. Generalizing face forgery detection with high-frequency features. In Proceedings of the IEEE Conference on Computer Vision and Patten Recognition (CVPR). 16317-16326.
- [41]41. Ivan Perov, Daiheng Gao, Nikolay Chervoniy, Kunlin Liu, Sugasa Marangonda, Chris Umé, Mr. Dpfks, Carl Shift Facen- heim, Luis R. P., Jian Jiang, Sheng Zhang, Pingyu Wu, Bo Zhou, and Weiming Zhang. 2021. DeepFaceLab: Integrated, flexible and extensible face-swapping framework. arXiv:cs.CV/2005.05535. Retrieved from https://arxiv.org/abs/2005. 05535. Accessed August 29, 2021.
- [43]43. Andreas Rossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Niessner. 2019. Face- Forensics++: Learning to detect manipulated facial images. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 1-11.
- [45]45. Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of the 3rd International Conference on Learning Representations (ICLR). IEEE.
- [47]47. Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In Pro- ceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research), Vol. 97. PMLR, 6105-6114.
- [50]50. Justus Thies, Michael Zollhofer, Marc Stamminger, Christian Theobalt, and Matthias Niessner. 2016. Face2Face: Real- time face capture and reenactment of RGB videos. In Proceedings of the IEEE Conference on Computer Vision and Patten Recognition (CVPR). 2387-2395.
- [53]53. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems, I.
- [54]54. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc.
- [63]63. Hanqing Zhao, Wenbo Zhou, Dongdong Chen, Tianyi Wei, Weiming Zhang, and Nenghai Yu. 2021. Multi-attentional deepfake detection. In Proceedings of the IEEE Conference on Computer Vision and Patten Recognition. 2185-2194.
- [64]64. Jian Zhao, Yu Cheng, Yan Xu, Lin Xiong, Jianshu Li, Fang Zhao, Karlekar Jayashree, Sugiri Pranata, Shengmei Shen, Junliang Xing, et al. 2018. Towards pose invariant face recognition in the wild. In Proceedings of the IEEE Conference on Computer Vision and Patten Recognition. 2207-2216.
- [67]67. Jian Zhao, Lin Xiong, Panasonic Karlekar Jayashree, Jianshu Li, Fang Zhao, Zhecan Wang, Panasonic Sugiri Pranata, Panasonic Shengmei Shen, Shuicheng Yan, and Jiashi Feng. 2017. Dual-agent GANs for photorealistic and identity preserving profile face synthesis. In Proceedings of the Advances in Neural Information Processing Systems, I.
- [68]68. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc.
- [70]70. Yuhao Zhu, Qi Li, Jian Wang, Chengzhong Xu, and Zhenan Sun. 2021. One shot face swapping on megapixels. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4834-4844.
Cited by
Sorted by citations
Deepfake 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
Self-citationA Comprehensive Review of DeepFake Detection Using Advanced Machine Learning and Fusion Methods
Gupta, G., Raja, K., Gupta, M., Jan, T., Whiteside, S. T., & Prasad, M. (2023) · Electronics · doi:10.3390/electronics13010095 · Cited by 99 · see citing works
“Wang et al. [45] proposed a deep convolutional transformer to incorporate the decisive image features both locally and globally.”
BackgroundNoise Based Deepfake Detection via Multi-Head Relative-Interaction
Wang, T., & Chow, K. P. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i12.26701 · Cited by 93 · see citing works
“…swap technique, methods have been explored to perform Deepfake detection with the help of deep neural networks (Afchar et al. 2018; Nguyen, Yamagishi, and Echizen 2019; Zhao et al. 2021; Zhang et al. 2022; Hu et al. 2022b; Wang et al. 2022; Hu et al. 2022a; Cheng et al. 2022; Wang and Chow 2022).”
MethodSelf-citationA review of deep learning‐based approaches for deepfake content detection
(2024) · doi:10.1111/exsy.13570 · Cited by 116 · see citing works
“[109] 2023 Local and global feature maps FaceForensics++, Celeb-DF, DF-1.”
BackgroundInfluentialQureshi, S. M., Saeed, A., Almotiri, S. H., Ahmad, F., & Al Ghamdi, M. A. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2037 · Cited by 71 · see citing works
Babaei, R., Cheng, S. S. M., Duan, R., & Zhao, S. (2025) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan14010017 · Cited by 80 · see citing works
“Wang et al. [98] integrated convolutional pooling with re-attention mechanisms to enhance local and global feature extraction, significantly improving video deepfake detection.”
A Review of Deepfake Techniques: Architecture, Detection and Datasets
Edwards, P., Nebel, J.-C., Greenhill, D., & Liang, X. (2024) · IEEE Access · doi:10.1109/access.2024.3477257 · Cited by 50 · see citing works
“Instead of focusing on a multi-modal approach, study [50] uses extracted video keyframes to overcome compression and image quality loss using a Deep Convolutional Transformer model, which utilises Convolutional Pooling and Re-Attention.”
MethodKhan, A. A., Chen, Y., Hajjej, F., Shaikh, A. A., Yang, J., Ku, C. S., & Por, L. Y. (2024) · Egyptian Informatics Journal · doi:10.1016/j.eij.2024.100502 · Cited by 52 · see citing works
Fsbi: Deepfake detection with frequency enhanced self-blended images
Abul Hasanaath, A., Luqman, H., Katib, R., & Anwar, S. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105418 · Cited by 34 · see citing works
Deep Fake Image Detection using Xception Architecture
Joshi, P., & Nivethitha, V. (2024) · International Conference on Recent Trends in Computer Science and Technology (ICRTCST) · doi:10.1109/icrtcst61793.2024.10578398 · Cited by 32 · see citing works
A 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
LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks
Wang, T., Huang, M., Cheng, H. H., Zhang, X., & Shen, Z. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680869 · Cited by 29 · see citing works
“…artifacts, experiencing the evolution of CNN based approaches [1, 55], CNN backbone based approaches [21, 28, 31, 37], integrated architectures [24, 36, 53], dataset enrichment strategies [5, 32, 33, 54], and deep analysis on implicit feature domains [4, 8, 22], they mainly lack generalization…”
Self-citationSpatio-Temporal Disentanglement and Constrained Self-Attention for Multi-Modal Deception Detection
Shao, Z., Yang, H., Zhu, H., Yao, R., Zou, L., Li, M., & Sheng, B. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3783994 · Cited by 23 · 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
An Efficient Attribute-Preserving Framework for Face Swapping
Wang, T., Li, Z., Liu, R., Wang, Y., & Nie, L. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3354573 · Cited by 22 · see citing works
“it has been repeatedly observed [47], [48], [49], [50] that convolutional blocks primarily focus on local information.”
BackgroundSelf-citationUnravelling Digital Forgeries: A Systematic Survey on Image Manipulation Detection and Localization
Kadha, V., Bakshi, S., & Das, S. K. (2025) · ACM Computing Surveys · doi:10.1145/3731243 · Cited by 26 · see citing works
Deepfake detection based on cross-domain local characteristic analysis with multi-domain transformer
Amin, M. A., Hu, Y., Li, C., & Liu, B. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.02.035 · Cited by 21 · see citing works
Deepfake Detection using Integrate-backward-integrate Logic Optimization Algorithm with CNN
Maheshwari, R. U., Paulchamy, B., Arun, M., Selvaraj, V., Saranya, N. N., & S, D. S. G. (2024) · International Journal of Electrical and Electronics Research · doi:10.37391/ijeer.120248 · Cited by 20 · see citing works
“As deepfakes [19] become more sophisticated, the need for robust cybersecurity measures intensifies.”
BackgroundExploring Self-Supervised Vision Transformers for Deepfake Detection: A Comparative Analysis
Nguyen, H. H., Yamagishi, J., & Echizen, I. (2024) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb62174.2024.10744497 · Cited by 25 · see citing works
“Wang et al. [53] used ConvNets followed by a proposed convolutional pooling transformer before classification.”
MethodDeepfakes in digital media forensics: Generation, AI-based detection and challenges
Bendiab, G., Haiouni, H., Moulas, I., & Shiaeles, S. N. (2024) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2024.103935 · Cited by 22 · see citing works
Robust Frame-Level Detection for Deepfake Videos With Lightweight Bayesian Inference Weighting
Zhou, L., Ma, C., Wang, Z., Zhang, Y., Shi, X., & Wu, L. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3337128 · Cited by 19 · see citing works
“Deep convolutional pooling transformer [28] also were introduced to improve detection performance.”
MethodCombating deepfakes: a comprehensive multilayer deepfake video detection framework
Rathoure, N., Pateriya, R. K., Bharot, N., & Verma, P. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20012-5 · Cited by 18 · see citing works
MFCLIP: Multi-Modal Fine-Grained CLIP for Generalizable Diffusion Face Forgery Detection
Zhang, Y., Wang, T., Yu, Z., Gao, Z., Shen, L., & Chen, S. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3576577 · Cited by 19 · see citing works
“09724v1 [ c s .”
InfluentialSelf-citationDisrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization
Liu, Y., An, J., Zhang, W., Wu, D., Gu, J., Lin, Z., & Wang, W. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681243 · Cited by 17 · see citing works
Enhancing Deepfake Detection With Diversified Self-Blending Images and Residuals
Liu, Q., Xue, Z., Liu, H., & Liu, J. (2024) · IEEE Access · doi:10.1109/access.2024.3382196 · Cited by 17 · see citing works
“Wang et al. [53] propose a deep convolutional Transformer for Deepfake detection, which incorporates both local and global image features, applies convolutional pooling and re-attention to enrich the extracted features, and employs image keyframes in model training for performance improvement.”
Wang, Y., Sun, Q., Rong, D., & Geng, R. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104072 · Cited by 20 · see citing works
Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method With Forgery Style Mixture
Kong, C., Luo, A., Bao, P., Li, H., Wan, R., Zheng, Z., Rocha, A., & Kot, A. C. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3669190 · Cited by 22 · see citing works
“With the rapid advancements in vision transformers (ViT), several ViT-based approaches [18], [19], [21], [28], [38], [39], [40], [41], [42], [43], [44], [45], [46] have been developed, showing superior detection performance.”
Multi-Level Fusion for Robust RGBT Tracking via Enhanced Thermal Representation
Tang, Z., Xu, T., Wu, X.-J., & Kittler, J. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3678176 · Cited by 15 · see citing works
Advancements in AI-Generated Content Forensics: A Systematic Literature Review
Xu, Q., Mu, W., Li, J., Sun, T., & Jiang, X. (2025) · ACM Computing Surveys · doi:10.1145/3760526 · Cited by 16 · see citing works
“However, a major bottleneck was the scarcity of labeled data for training detectors.”
SecureVision: Advanced Cybersecurity Deepfake Detection with Big Data Analytics
Kumar, N., & Kundu, A. (2024) · Sensors · doi:10.3390/s24196300 · Cited by 14 · see citing works
“Real-time accuracy: Investigating methods to improve the real-time accuracy of deepfake detection systems, minimizing latency while maintaining high detection rates in dynamic environments [18,23,28,29].”
BackgroundMethodSemantics-Oriented Multitask Learning for DeepFake Detection: A Joint Embedding Approach
Zou, M., Yu, B., Zhan, Y., Lyu, S., & Ma, K. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3572508 · Cited by 15 · see citing works
“Additionally, complex architectures such as capsule networks [70] and vision Transformers [32], [71], [72], along with advanced training strategies such as adversarial training [25], [73], test-time training [74], graph learning [34], [36], contrastive learning [33], [38], and one-class…”
Subburaj, B., & Ragavendra, R. (2025) · IEEE Access · doi:10.1109/access.2025.3567523 · Cited by 12 · see citing works
“In [21] Deepfake detection system using local features extracted using CNN are used to further extract rich features through transformer blocks with reattention to leverage the detection performance.”
Spatiotemporal Inconsistency Learning and Interactive Fusion for Deepfake Video Detection
Zhang, D., Zhu, W., Liao, X., Qi, F., Yang, G., & Ding, X. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3664654 · Cited by 13 · see citing works
XAI – Empowered Ensemble Deep Learning for Deepfake Detection
Kumar, A. A., Priyangha, S. J. D., Meghana, P. S., Dheeraj, M., & Aarthi, R. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10726125 · Cited by 11 · see citing works
DeepGuardNet: A Novel CNN Architecture for DeepFake Image Detection
Amritha Devi, N., & Simon, P. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.313 · Cited by 13 · see citing works
Siamese Network-Based Detection of Deepfake Impersonation Attacks with a Person of Interest Approach
Samrouth, K., Housseini, P. E., & Olivier Déforges, A. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3708352 · Cited by 10 · see citing works
“On the other hand, methods with medium and complexity ([5, 18, 25, 34, 37, 39, 45] and [12]) strike a balance between performance and complexity, showing high accuracy levels without the computational burden of high-complexity methods.”
InfluentialFractalForensics: Proactive Deepfake Detection and Localization via Fractal Watermarks
Wang, T., Cheng, H., Liu, M.-H., & Kankanhalli, M. (2025) · Proceedings of the 33rd ACM International Conference on Multimedia · doi:10.1145/3746027.3754544 · Cited by 9 · see citing works
“Although classic passive detectors [18, 20, 31, 32, 38, 39] have achieved significant progress since the first occurrence of Deep-fake, recent advancements in generative models [35, 42, 47, 51] have brought strong challenges with high-quality synthetic images.”
Self-citationCAST: Cross-Attentive Spatio-Temporal feature fusion for deepfake detection
Thakre, A., Nagwekar, O., Talekar, V., & Biswas, A. S. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115560 · Cited by 11 · see citing works
“Similarly, Wang et al. [14] adopted a convolutional pooling transformer to further enhance spatio-temporal coherence understanding in video forgeries.”
A Comparative Analysis of Deep Learning Based Approaches for DeepFake Identification
Duhan, K., & Kajal, A. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.350 · Cited by 9 · see citing works
MITD-Net: Multi-scale iterative tamper detection network for image manipulation localization
Deng, F., Yu, H., Liu, T., & Yang, R. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104901 · Cited by 7 · see citing works
Wu, Y.-C., Sohrawardi, S. J., Gerstner, C. R., & Wright, M. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713711 · Cited by 7 · see citing works
“Techniques like convolutional neural networks (CNNs) [2, 89], recurrent neural networks (RNNs) [11, 12, 33], and more recently transformers [86, 93] have shown promising results in detecting various types of deepfakes.”
Deepfake Detection Leveraging Self-Blended Artifacts Guided by Facial Embedding Discrepancy
Shan-shan, H., Li, S., Wang, S., Yuan, L., Zhang, Y., & Gao, X. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3585724 · Cited by 7 · see citing works
“To address these limitations, researchers have proposed learning-based approaches that explore deeper spatial features to detect forged data [13], [19], [20], [21], [22], [23], [24].”
Liu, X., Dong, X., Xie, F., Lü, P., Lu, X., & Jiang, M. (2024) · Journal of Electronic Imaging · doi:10.1117/1.jei.33.2.023007 · Cited by 7 · see citing works
Agrawal, D. R., & Haneef, F. (2025) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.70083 · Cited by 7 · see citing works
Face forgery video detection based on expression key sequences
Tu, Y., Wu, J., Lu, L., Gao, S., & Li, M. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102142 · Cited by 6 · see citing works
Face Swap Detection: A Systematic Literature Review
Hriez, S. (2025) · IEEE Access · doi:10.1109/access.2025.3598980 · Cited by 6 · see citing works
“However, [82], at 63.27, is a stark reminder that some models are not able to achieve consistently high accuracy, particularly in real-world scenarios where face swaps may be more subtle or harder to detect.”
InfluentialNullSwap: Proactive Identity Cloaking Against Deepfake Face Swapping
Wang, T., Niu, S., Cheng, H., Zhang, X., & Wang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00927 · Cited by 5 · see citing works
“While traditional passive detection approaches [3, 5, 8, 28, 32, 33, 44] distinguish real and fake after Deepfake manipulations occur, proactive defense [16, 31, 34, 35, 39] against Deepfake aims to insert invisible signals into benign images in advance of potential Deepfake manipulations.”
Self-citationA survey on deepfake video detection datasets
Sohan, M. F., Solaiman, M., & Hasan, M. A. (2023) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v32.i2.pp1168-1176 · Cited by 5 · see citing works
Deepfake Detection System Using a Hybrid Model
Sudharson, S., Kokil, P., Sasikala, D., & Swamy, P. A. (2023) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt56998.2023.10308279 · Cited by 5 · see citing works
“The combination of CNNs and transformers [19] and the fusion of EfficientNet with vision transformers [20] made observations that the deep learning model produces outcomes in the deep fake detection field.”
BackgroundDomain-invariant and Patch-discriminative Feature Learning for General Deepfake Detection
Zhang, J., Ni, J., Nie, F., & Huang, J. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3657297 · Cited by 6 · see citing works
Domain-aware Multimodal Dialog Systems with Distribution-based User Characteristic Modeling
Chen, X., Song, X., Zuo, J., Wei, Y., Nie, L., & Chua, T. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3704811 · Cited by 5 · see citing works
Self-citationUnmasking Deepfakes: A Review of Current Datasets, Tools, and Detection Features
Garg, D., & Gill, R. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.129 · Cited by 6 · see citing works
Lingham, N. S. R., Devakanth, J. J. M. A., Raj, G., Gayathri, K., Janani, R., & Dhanapal, R. (2024) · International Conference on Applied Artificial Intelligence and Computing (ICAAIC) · doi:10.1109/icaaic60222.2024.10575155 · Cited by 4 · see citing works
“This helps the overall system to obtain various features and patterns associated with the deepfake generation [18].”
BackgroundImage-based DeepFake Detection Using Artificial Intelligence
Singh, S. K., Kumar, G., Dubey, A. K., Yadav, R., Rai, V., & Sharma, A. K. (2025) · IEEE International Conference on Communication Systems and Network Technologies (CSNT) · doi:10.1109/csnt64827.2025.10968600 · Cited by 4 · see citing works
TransFS: Face Swapping Using Transformer
Cao, W., Wang, T., Dong, A., & Shu, M. (2023) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg57933.2023.10042556 · Cited by 4 · see citing works
“The privacy protection issues brought by face swapping technology will promote research on DeepFake detection [28] [27] [3].”
MethodSelf-citationEvaluating Features and Variations in Deepfake Videos Using the CoAtNet Model
Alattas, E., Clark, J., Al-Aama, A. Y., & Jarraya, S. K. (2025) · Journal of Imaging · doi:10.3390/jimaging11060194 · Cited by 3 · see citing works
“For instance, the authors of [40] achieved an AUC of 0.7368, while the authors of [78] achieved an AUC of 0.6695.”
InfluentialMulti-spectral Class Center Network for Face Manipulation Localization
Miao, C., Chu, Q., Tan, Z., Jin, Z., Gong, T., Zhuang, W., Wu, Y., Liu, B., Hu, H., & Yu, N. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3747296 · Cited by 19 · see citing works
“Recently, data-derived detection models utilize spatial artifacts [6, 21, 24, 26, 30, 49, 57, 68, 71, 72, 76, 80, 83, 89, 94, 97, 107, 108] or temporal information [10, 18, 32, 46, 92, 96, 99, 102] to learn discriminative features and achieve remarkable detection performance.”
Javed, H., Ali, F., Shah, B., & Kwak, D. (2025) · IEEE Access · doi:10.1109/access.2025.3610616 · Cited by 3 · see citing works
“They are like detectives investigating crimes that happen online or with computers [56], [57], [58].”
A Spatial-Frequency Aware Multi-scale Fusion Network for Real-Time Deepfake Detection
Lv, L., Wang, T., Huang, M., Liu, R., & Wang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5676-2_36 · Cited by 3 · see citing works
Self-citationBekheet, A. A., Ghoneim, A. S., & Khoriba, G. A. (2024) · Intelligent Methods, Systems, and Applications (IMSA) · doi:10.1109/imsa61967.2024.10652683 · Cited by 3 · see citing works
Meta-Learning With Relation Embedding for Few-Shot Deepfake Detection
Liu, X., Song, P., Lü, P., & Wang, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3499353 · Cited by 3 · see citing works
Deepfake Detection Using Transfer Learning
Khan, S. A., & Valles, D. (2024) · 2024 IEEE 15th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon62879.2024.10754706 · Cited by 2 · see citing works
“Wang et al. [6] proposed a keyframe-based deep convolutional transformer model.”
Biswas, B., Raha, A. D., Paul, C., Dam, S. K., Adhikary, A., Debnath, R., Bairagi, A. K., & Gain, M. (2024) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit64611.2024.11021926 · Cited by 2 · see citing works
Robust deepfake detector against deep image watermarking
Yu, J., Liu, X., Zan, F., & Peng, Y. (2025) · PLoS ONE · doi:10.1371/journal.pone.0338778 · Cited by 2 · see citing works
“For instance, Chen et al. [13] employed self-supervised learning to capture image consistency, while Wang et al. [14] utilized Transformer-based models to extract and compare local and global image features.”
AT-HSTNet: An Efficient Hierarchical Action-Transformer Framework for Deepfake Video Detection
Javaid, S., Rai, M. C. E., Elkhouly, A., Al-Khatib, O., Far, A. B., & Barachi, M. E. (2026) · Applied Sciences · doi:10.3390/app16073450 · Cited by 2 · see citing works
Exploiting Backdoors of Face Synthesis Detection with Natural Triggers
Han, X., Yang, S., Wang, W., He, Z., & Dong, J. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3677380 · Cited by 5 · see citing works
Deepfake Classification For Human Faces using Custom CNN
Kalemullah, A. M., Prakash, P., & Sakthivel, V. (2024) · International Conference on Circuit, Power and Computing Technologies · doi:10.1109/iccpct61902.2024.10672973 · Cited by 2 · see citing works
“The authors of [10] talk about how difficult it is to identify deepfake films because of their growing realism.”
BackgroundWang, H., Sun, X., Sun, Y., & Li, P. (2024) · Computers & Graphics · doi:10.1016/j.cag.2024.104153 · Cited by 2 · see citing works
Generalizable Spatiotemporal Deepfake Detection with Late-Fusion
Alfalasi, H. R., Hashem, M., & Abul, O. (2024) · International Conference on Signal Processing and Information Security (ICSPIS) · doi:10.1109/icspis63676.2024.10812603 · Cited by 2 · see citing works
“…Train: CelebDF Test: CelebDF Test: FF++c23 AUC AUC ISTVT [24] 84.10 – FTCN [6] 86.90 – Face X-Ray [9] 79.50 – MTD-Net [11] 70.12 63.43 MAT [15] 67.44 – M2TR [18] 68.20 – DCPT [20] 72.43 – MRL [26] 83.58 – MSVT [25] 88.81 – Proposed Model 91.00 75.50 batch size is 8, and it is trained for 20 epochs.”
InfluentialSurvey of Fake Image Synthesis and its Detection
Uloli, T., Akash, R. M. K., Keerthika, A., & Dhanwanth, K. S. (2023) · Journal of Innovative Image Processing · doi:10.36548/jiip.2022.4.006 · Cited by 2 · see citing works
FSBI: Deepfakes Detection with Frequency Enhanced Self-Blended ImagesPreprint
Hasanaath, A. A., Luqman, H., KATIB, R. F., & Anwar, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4869258 · Cited by 2 · see citing works
Unveiling authenticity with diffusion-based face retouching reversal
Xing, F., Shi, X., Wang, Y., & Yang, C. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113062 · Cited by 1 · see citing works
Boosting Deepfake Video Detection Using Non-Local Attention and Sharpness-Aware Minimization
Singh, P., & Pankajakshan, V. (2025) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss65446.2025.11149952 · Cited by 1 · see citing works
“Also, the standard neural networks involving convolutional operations focus on local features and patterns [25], but tasks like deepfake detection may require the model to focus on a broader range of structural artifacts and manipulations, including all pixel correlations and inconsistencies…”
Yassin, W. M., Abdollah, F. M., Ismail, A., Kamis, N. H., Razak, A., & Joy, H. K. (2026) · Discover Computing · doi:10.1007/s10791-026-10093-1 · Cited by 1 · see citing works
“Methods such as Wang et al. [8] and Heo et al. [20] utilize CNN–Transformer combinations, which allow the model to capture both local spatial artifacts and global contextual relationships within manipulated facial regions.”
DeepFake Detection With Multi-View Fusion and Graph Convolutional Network
Xu, X., Chen, J., Zhang, Y., Li, C., Singh, A. K., & Lv, Z. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3618565 · Cited by 1 · see citing works
“Following the study [32], three typical evaluation criteria, i.e., area under curve (AUC), accuracy (ACC), and F1-score (F1) 5 [Online].”
InfluentialForgeFinder: Perceptive Multimodal Deepfake Detection via Multi-grained Forgery Localization
Liu, B., Liu, B., Ding, M., & Zhu, T. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3778030 · Cited by 1 · see citing works
A Survey on Deepfake Detection Techniques for Watermarking and Digital Forensics Using Deep Learning
Suhasini, T. S., Шарма, М., & Mishra, D. (2025) · doi:10.1109/cises66934.2025.11265509 · Cited by 1 · see citing works
“Several architectures, such as ResNet, Inception ResNetV2, EfficientNet, and VGG16, have been extensively studied [30], [21].”
Decoding deception: state-of-the-art approaches to deep fake detection
Hussain, T., Reddy, B. T., Phanindra, K., Terumalasetti, S., & Khan, G. A. (2026) · Frontiers in Big Data · doi:10.3389/fdata.2025.1670833 · Cited by 1 · see citing works
Defending Deepfake via Texture Feature Perturbation
Zhang, X., Chen, C., & Wang, T. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343336 · Cited by 1 · see citing works
Self-citationUnsupervised Domain Adaptation-Based Cross-Type Deepfake Image Detection
Wang, Q., Wang, X., Liu, Z., Bai, N., Zhao, M., & Pang, S. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3685445 · Cited by 1 · see citing works
“Other studies [38], [39], [40], [41] incorporated concepts from diverse disciplines to detect unseen deepfake samples.”
A Hybrid Deep Learning Approach Combining CNN and Vision Transformer for Deepfake Detection
Ananthakrishnan, S., Manivannan, D., Suresh, K. S., Ponmani, E., Asmita, P., & Vandhana, S. (2026) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict68280.2026.11511032 · Cited by 1 · see citing works
“Other studies have proposed convolutional pooling transformers and CNN – transformer hybrid models to jointly capture spatial and contextual features [5], [7].”
Efficient deepfake detection: a hybrid lightweight framework for cross-domain generalization
Nagar, H. V., Gandhi, V., & Rathod, D. M. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05419-x · Cited by 1 · see citing works
Liu, Z., Wang, T., Zhou, S., & Shu, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44210-0_20 · Cited by 1 · see citing works
Self-citationCross-Database in Deepfake Detection Based on a Convolutional Neural Network and Vision Transformer
Ferreira, E. E., Andrade, J. O., & Komati, K. S. (2023) · Workshop of Computer Vision (WVC) · doi:10.5753/wvc.2023.27533
Patil, P. P. (2024) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2024.61211
Fsbi: Deepfakes Detection with Frequency Enhanced Self-Blended ImagesPreprint
Hasanaath, A. A., Luqman, H., KATIB, R. F., & Anwar, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4876969
Deep Fake Detection Based on Hybrid Approach Involving Residual Network Deep Learning Architecture
Shibu, N. V., Muthunagai, R., & Prabu, S. (2024) · International Conference on System, Computation, Automation and Networking (ICSCAN) · doi:10.1109/icscan62807.2024.10894401
Detecting Deception: A Comparative Study of CNN Approaches for Deepfake Image Detection
Nithish, M., Thiyagarajan, P., & Rajalakshmi, S. (2025) · International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE) · doi:10.1109/rmkmate64874.2025.11042380
IDD: An Identity Disentanglement Framework for Deepfake Detection
Li, H., Xu, P., Zhu, Z., & Zhang, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9794-6_28
CNN vs. Transformer-Based Models for Deepfake Detection: A Comparative Analysis
Ameer, N. H. A., Al-Taee, M. M., Hussain, A.-S. T., Hussian, A., & Ali, H. (2025) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi65310.2025.11141105
“The rising prominence of realistic synthetic human faces, voices, and behaviors raises concerns about misinformation [3], cyber deception [4], risky commercial use [6], identity fraud [5], deepfakes [6], and political destabilization [7].”
SwinGAN: A Synergistic Approach Combining Swin Transformers and GANs for DeepFake Detection
Kumar, V., Chaudhary, P., Singh, A. K., Srivastava, A., Diswar, P., & Singh, H. (2025) · International Conference on Multidisciplinary Research and Innovations in Engineering (MRIE) · doi:10.1109/mrie66930.2025.11156622
“Architectures based on transformers such as the Swin Transformer lay the foundation for deepfake detection because of their ability to capture both global and local visual features, including the small artifacts based on history [4] and [24].”
InfluentialProactive Deepfake Detection via Self-Verifiable Semantic Watermarking
Jiang, P., Lei, B., Sun, Y., Yu, L., Chen, Z., Xie, H., & Zhang, Y. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755587
Rana, P., Kumari, R., Bagga, R., Kumar, P., & Kanupriya (2025) · AIP conference proceedings · doi:10.1063/5.0292512
Disruptive Attacks on Face Swapping via Low-Frequency Perceptual Perturbations
Huang, M., Shu, M., Zhou, S., & Liu, Z. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228245
“Most current detection methods rely on passive analysis [21]–[26], using visual computing and machine learning to identify manipulation traces in images.”
D4-Net: Detecting Deepfakes using a Dual-branch Deep Learner
Karmakar, O., Mohiuddin, S., Ali, A., Kaplun, D., Romanov, S., & Sarkar, R. (2025) · International Workshop on Multimodal and Responsible Affective Computing (MRAC) · doi:10.1145/3746270.3760238
Advancing Deepfake Detection Through Head Pose Estimation on New-Generation Datasets
Bisogni, C., Castiglione, A., Migliaccio, M., Miglino, A., Nappi, M., & Pero, C. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-3551-4_24
MAP-Mamba: Multi-Artifacts Perception Mamba for Generalizable Face Forgery Detection
Wang, C., He, Z., Hu, X., Guan, W., Wang, W., & Fu, Z. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3651948
“DCPT [21] proposes a deep convolutional Transformer to incorporate the decisive image features both locally and globally to enrich the extracted features and enhance e ffi cacy.”
Liu, F., Yang, H., Zhang, X., Li, J., & Zeng, Y. (2025) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv67407.2025.11349243
“Additionally, subtle visual artifacts introduced during manipulation, such as geometric distortions and texture inconsistencies, are often difficult to detect, necessitating more effective solutions for forgery detection under such constraints[11].”
AI-Driven Detection of Synthetic Videos and Deep Fakes
Tamilkodi, R., Madhuri, N., Deekshith, B., Krishna, D. S. R., Chaitanya, M. V. K., & Venkatesh, P. (2026) · Cognitive science and technology · doi:10.1007/978-981-95-0144-1_42
Robust Cross-Modal Deepfake Detection via Facial UV Maps and Momentum Contrastive Learning
Tang, Y., Zhang, Y., Mao, W., & Li, Y. (2025) · International Symposium on Research in Attacks, Intrusions and Defenses (RAID) · doi:10.1109/raid67961.2025.00013
“This fusion enables detectors to leverage both local pixel-level textures and global semantic features, as evidenced in works integrating CNN and ViT [16], as well as those combining EfficientNet-B7 with ViT to balance detection performance and computational efficiency [17].”
- Authors
- Wang, T., Cheng, H., Chow, K. P., & Nie, L.
- Affiliations
- University of Hong Kong (HK)
- Shandong University (CN)
- Harbin Institute of Technology (CN)
- Venue
- ACM Transactions on Multimedia Computing, Communications, and Applications
- Published
- 2023-05-30
- Volume
- 19
- Issue
- 6
- Pages
- 1-20
- ISSN
- 1551-6857 (ISSN-L)
- 1551-6865
- OpenAlex
- W4361003656
- Cited by
- 111
- References
- 31
- Citations by year
- 2026: 21 · 2025: 42 · 2024: 39 · 2023: 9
- FWCI
- 10.09
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM Transactions on Multimedia Computing Communications and Applications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, convolutional transformer, key frames, video compression artifacts, cross-dataset transferability, digital forensics
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
