人脸视频深度伪造检测方法综述

doi:10.3778/j.issn.1673-9418.2205035

摘要/Abstract

摘要： 深度伪造（deepfake）技术的非法应用会对社会稳定、个人名誉甚至国家安全造成恶劣影响，因此针对人脸视频的深度伪造检测成为计算机视觉领域中的难点与研究热点。目前该领域的研究建立在传统人脸识别与图像分类技术基础上，通过搭建深度学习网络判别真伪，但存在数据集质量不一、多模态特征如何有效结合、模型泛化能力较差等问题。为进一步促进深度伪造检测技术的发展，对当前各类人脸视频深度伪造算法进行了全面总结，并对已有算法进行了归类、分析、比较。首先，主要介绍人脸视频深度伪造检测数据集；其次，对近三年主要的伪造视频检测方法进行总结，以特征选择为切入点，从空间特征、时空融合特征、生物特征的角度对各项检测技术进行分类整理，并对基于水印与区块链等非主流检测方法进行介绍；然后，从特征选择、迁移学习、模型设计与训练思路等方面介绍了各类检测方法所呈现出的主流趋势；最后，对全文进行总结并对未来技术发展进行展望。

关键词: 深度学习, 多媒体取证, 深度伪造, 视频检测, 人脸篡改

Abstract: The illegal use of deepfake technology will have a serious impact on social stability, personal reputation and even national security. Therefore, it is imperative to develop research on facial deepfake videos detection tech-nology, which is also a research hotspot in the field of computer vision in recent years. At present, the research is based on traditional face recognition and image classification technology, building a deep neural network to deter-mine a facial video is real or not, but there are still problems such as the low quality of dataset, the combine of multimodal features and the poor performance of model generalization. In order to further promote the development of deepfake video detection technology, a comprehensive summary of various current algorithms is carried out, and the existing algorithms are classified, analyzed and compared. Firstly, this paper mainly introduces the facial deepfake videos detection datasets. Secondly, taking feature selection as the starting point, this paper summarizes the main method of detecting deepfake videos in the past three years, classifies various detection technologies from the pers-pectives of spatial features, spatial-temporal fusion features and biological features, and introduces some new detec-tion methods based on watermarking and blockchain. Then, this paper introduces the new trends of facial deepfake video detection methods from the aspects of feature selection, transfer learning, model architecture and training ideas. Finally, the full text is summarized and the future technology development is prospected.

Key words: deep learning, multimedia forensics, deepfake, video detection, face forgery

张璐, 芦天亮, 杜彦辉. 人脸视频深度伪造检测方法综述[J]. 计算机科学与探索, 2023, 17(1): 1-26.

ZHANG Lu, LU Tianliang, DU Yanhui. Overview of Facial Deepfake Video Detection Methods[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(1): 1-26.

参考文献

[1] 姬德强. 深度造假: 人工智能时代的视觉政治[J]. 新闻大学, 2020, 7: 1-16.
JI D Q. DeepFake: visual politics in the era of artificial in-telligence[J]. Journalistic University, 2020, 7: 1-16.
[2] 高威, 萧子豪, 朱益灵. DeepFake 技术背后的安全问题: 机遇与挑战[J]. 信息安全研究, 2020, 6(7): 634-644.
GAO W, XIAO Z H, ZHU Y L. The security problems of the DeepFake technology: oppotunities and challenges[J]. Journal of Information Security Research, 2020, 6(7): 634-644.
[3] DOLHANSKY B, BITTON J, PFLAUM B, et al. The deepfake detection challenge (DFDC) dataset[J]. arXiv:2006.07397, 2020.
[4] RÖSSLER A, COZZOLINO D, VERDOLIVA L, et al. Face-Forensics++: learning to detect manipulated facial images[C]//Proceedings of the 2019 IEEE/CVF International Con-ference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Pis-cataway: IEEE, 2019: 1-11.
[5] LI Y Z, YANG X, SUN P, et al. Celeb-DF: a large-scale cha-llenging dataset for deepfake forensics[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 3204-3213.
[6] LI Y, CHANG M C, LYU S. In ICTU Oculi: exposing AI generated fake face videos by detecting eye blinking[J]. arXiv:1806.02877, 2018.
[7] KORSHUNOV P, MARCEL S. DeepFakes: a new threat to face recognition? Assessment and detection[J]. arXiv:1812.08685, 2018.
[8] THIES J, ZOLLHOFER M, STAMMINGER M, et al. Face2-Face: real-time face capture and reenactment of RGB videos[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 26-30, 2016. Washington: IEEE Computer Society, 2016: 2387-2395.
[9] THIES J, ZOLLHÖFER M, NIEßNER M. Deferred neural rendering: image synthesis using neural textures[J]. ACM Transactions on Graphics, 2019, 38(4): 66.
[10] ISOLA P, ZHU J Y, ZHOU T, et al. Image-to-image trans-lation with conditional adversarial networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pat-tern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 1125-1134.
[11] LI L, BAO J, YANG H, et al. FaceShifter: towards high fi-delity and occlusion aware face swapping[J]. arXiv:1912.13457, 2019.
[12] JIANG L M, LI R, WU W, et al. DeeperForensics-1.0: a large-scale dataset for real-world face forgery detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 2886-2895.
[13] ZHOU T, WANG W, LIANG Z, et al. Face forensics in the wild[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 19-25, 2021. Piscataway: IEEE, 2021: 5778-5788.
[14] PEROV I, GAO D, CHERVONIY N, et al. DeepFaceLab: integrated, flexible and extensible face-swapping framework[J]. arXiv:2005.05535, 2020.
[15] NIRKIN Y, KELLER Y, HASSNER T. FSGAN: subject ag-nostic face swapping and reenactment[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 7184-7193.
[16] KWON P, YOU J, NAM G, et al. KoDF: a large-scale Ko-rean deepfake detection dataset[J]. arXiv:2103.10094, 2021.
[17] SIAROHIN A, LATHUILIèRE S, TULYAKOV S, et al. First order motion model for image animation[C]//Proceedings of the Annual Conference on Neural Information Proces-sing Systems 2019, Vancouver, Dec 8-14, 2019: 7135-7145.
[18] YI R, YE Z, ZHANG J, et al. Audio-driven talking face video generation with learning-based personalized head pose[J]. arXiv:2002.10137, 2020.
[19] PRAJWAL K R, MUKHOPADHYAY R, NAMBOODIRI V P, et al. A lip sync expert is all you need for speech to lip generation in the wild[C]//Proceedings of the 28th ACM International Conference on Multimedia, Seattle, Oct 12-16, 2020. New York: ACM, 2020: 484-492.
[20] DONG X Y, BAO J M, CHEN D D, et al. Identity-driven deepfake detection[J]. arXiv:2012.03930, 2020.
[21] NAGRANI A, CHUNG J S, XIE W D, et al. VoxCeleb: large-scale speaker verification in the wild[J]. Computer Speech & Language, 2020, 60: 101027.
[22] ZI B J, CHANG M H, CHEN J J, et al. WildDeepfake: a challenging real-world dataset for deepfake detection[C]//Pro-ceedings of the 28th ACM International Conference on Multi-media, Seattle, Oct 12-16, 2020. New York: ACM, 2020: 2382-2390.
[23] LI X, LANG Y, CHEN Y, et al. Sharp multiple instance lear-ning for deepfake video detection[C]//Proceedings of the 28th ACM International Conference on Multimedia, Seattle, Oct 12-16, 2020. New York: ACM, 2020: 1864-1872.
[24] LE T N, NGUYEN H H, YAMAGISHI J, et al. Open-Forensics: large-scale challenging dataset for multi-face forgery detection and segmentation in-the-wild[J]. arXiv:2107.14480, 2021.
[25] AFCHAR D, NOZICK V, YAMAGISHI J, et al. MesoNet: a compact facial video forgery detection network[C]//Pro-ceedings of the 2018 IEEE International Workshop on Infor-mation Forensics and Security, Hong Kong, China, Dec 11-13,?2018. Piscataway: IEEE, 2018: 1-7.
[26] DE LIMA O, FRANKLIN S, BASU S, et al. Deepfake de-tection using spatiotemporal convolutional networks[J]. arXiv: 2006.14749, 2020.
[27] LI Y, LYU S. Exposing deepfake videos by detecting face warping artifacts[J]. arXiv:1811.00656, 2018.
[28] GUARNERA L, GIUDICE O, BATTIATO S. Deepfake de-tection by analyzing convolutional traces[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, Jun 14-19, 2020. Pis-cataway: IEEE, 2020: 2841-2850.
[29] WANG C R, DENG W H. Representative forgery mining for fake face detection[C]//Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition, Jun 19-25, 2021. Piscataway: IEEE, 2021: 14923-14932.
[30] BONETTINI N, CANNAS E D, MANDELLI S, et al. Vi-deo face manipulation detection through ensemble of CNNs[C]//Proceedings of the 25th International Conference on Pattern Recognition, Milan, Jan 10-15, 2021. Piscataway: IEEE, 2021: 5012-5019.
[31] WODAJO D, ATNAFU S. Deepfake video detection using convolutional vision transformer[J]. arXiv:2102.11126, 2021.
[32] LIU Z, QI X, TORR P H S. Global texture enhancement for fake face detection in the wild[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Re-cognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 8060-8069.
[33] COCCOMINI D A, MESSINA N, GENNARO C, et al. Com-bining EfficientNet and vision transformers for video deep-fake detection[C]//LNCS 13233: Proceedings of the 21st In-ternational Conference on Image Analysis and Processing,Lecce, May 23-27, 2022. Cham: Springer, 2022: 219-229.
[34] 暴雨轩, 芦天亮, 杜彦辉, 等. 基于i_ResNet34模型和数据增强的深度伪造视频检测方法[J]. 计算机科学, 2021, 48(7): 77-85.
BAO Y X, LU T L, DU Y H, et al. Deepfake video detec-tion method based on i_ResNet34 model and data augmen-tation[J]. Computer Science, 2021, 48(7): 77-85.
[35] NGUYEN H H, YAMAGISHI J, ECHIZEN I. Capsule-Forensics: using capsule networks to detect forged images and videos[C]//Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing, Brighton, May 12-17,?2019. Piscataway: IEEE, 2019: 2307-2311.
[36] 耿鹏志, 唐云祁, 樊红兴, 等. 基于CutMix算法和改进Xcep-tion网络的深度伪造检测研究[J]. 激光与光电子学进展, 2022, 59(16): 348-355.
GENG P Z, TANG Y Q, FAN H X, et al. Deep forgery detection using CutMix algorithm and improved Xception network[J]. Laser & Optoelectronics Progress, 2022, 59(16): 348-355.
[37] 张时润, 彭勃, 王伟, 等. 基于空洞卷积和注意力机制的深度伪造检测[J]. 现代电子技术, 2022, 45(5): 42-48.
ZHANG S R, PENG B, WANG W, et al. Deepfake detec-tion based on dilated convolution and attention mechanism[J]. Modern Electronics Technique, 2022, 45(5): 42-48.
[38] 朱新同, 唐云祁, 耿鹏志. 基于特征融合的篡改与深度伪造图像检测算法[J]. 信息网络安全, 2021, 21(8): 70-81.
ZHU X T, TANG Y Q, GENG P Z. Detection algorithm of tamper and deepfake image based on feature fusion[J]. Net-info Security, 2021, 21(8): 70-81.
[39] NATARAJ L, MOHAMMED T M, MANJUNATH B S, et al. Detecting GAN generated fake images using co-occurrence matrices[J]. Electronic Imaging, 2019(5): 532.
[40] TAN M, LE Q. EfficientNet: rethinking model scaling for con-volutional neural networks[C]//Proceedings of the 36th Inter-national Conference on Machine Learning, Long Beach, Jun 9-15, 2019: 6105-6114.
[41] CHEN C F R, FAN Q, PANDA R. CrossViT: cross-attention multi-scale vision transformer for image classification[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, Montreal, Aug 28, 2021. Piscataway: IEEE, 2021: 357-366.
[42] ZHAO H, ZHOU W, CHEN D, et al. Multi-attentional deep-fake detection[J]. arXiv:2103.02406, 2021.
[43] GUO Z, YANG G, CHEN J, et al. Fake face detection via adaptive manipulation traces extraction network[J]. Computer Vision and Image Understanding, 2021, 204(11): 103170.
[44] ZHOU P, HAN X, MORARIU V I, et al. Two-stream neural networks for tampered face detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, Jul 21-26, 2017. Washing-ton: IEEE Computer Society, 2017: 1831-1839.
[45] ZHU X, WANG H, FEI H, et al. Face forgery detection by 3D decomposition[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 19-25, 2021. Piscataway: IEEE, 2021: 2929-2939.
[46] LIU S, LIAN Z, GU S, et al. Block shuffling learning for deepfake detection[J]. arXiv:2202.02819, 2022.
[47] CHEN L, ZHANG Y, SONG Y, et al. Self-supervised learning of adversarial example: towards good generalizations for deepfake detection[J]. arXiv:2203.12208, 2022.
[48] ZHAO T C, XU X, XU M Z, et al. Learning self-consistency for deepfake detection[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, Montreal, Oct 10-17, 2021. Piscataway: IEEE, 2021: 15023-15033.
[49] GU Q, CHEN S, YAO T, et al. Exploiting fine-grained face forgery clues via progressive enhancement learning[J]. arXiv: 2112.13977, 2021.
[50] DURALL R, KEUPER M, PFREUNDT F J, et al. Unmas-king deepfakes with simple features[J]. arXiv:1911.00686, 2019.
[51] QIAN Y, YIN G, SHENG L Z, et al. Thinking in frequency: face forgery detection by mining frequency-aware clues[J]. arXiv:2007.09355, 2020.
[52] ZHANG X, KARAMAN S, CHANG S F. Detecting and simulating artifacts in GAN fake images[C]//Proceedings of the 2019 IEEE International Workshop on Information Forensics and Security, Delft, Dec 9-12, 2019. Piscataway:IEEE, 2019: 1-6.
[53] FRANK J, EISENHOFER T, SCH?NHERR L, et al. Lever-aging frequency analysis for deep fake image recognition[C]//Proceedings of the 37th International Conference on Machine Learning, Jul 13-18, 2020: 3247-3258.
[54] LUO Y C, ZHANG Y, YAN J C, et al. Generalizing face forgery detection with high-frequency features[C]//Procee-dings of the 2021 IEEE/CVF Conference on Computer Vi-sion and Pattern Recognition, Jun 19-25, 2021. Piscataway: IEEE, 2021: 16317-16326.
[55] LI J, XIE H, LI J, et al. Frequency-aware discriminative feature learning supervised by single-center loss for face forgery detection[J]. arXiv:2103.09096, 2021.
[56] LIU H G, LI X D, ZHOU W B, et al. Spatial-phase shallow learning: rethinking face forgery detection in frequency domain[J]. arXiv:2103.01856, 2021.
[57] WANG J, WU Z, CHEN J, et al. M2TR: multi-modal multi-scale transformers for deepfake detection[J]. arXiv:2104.09770, 2021.
[58] CHEN S, YAO T P, CHEN Y, et al. Local relation learning for face forgery detection[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence, the 33rd Conference on Innovative Applications of Artificial Intelligence, the 11th Symposium on Educational Advances in Artificial In-telligence, Feb 2-9, 2021. Menlo Park: AAAI, 2021: 1081-1088.
[59] LI L Z, BAO J, ZHANG T, et al. Face X-Ray for more general face forgery detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Re-cognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 5000-5009.
[60] NIRKIN Y, WOLF L, KELLER Y, et al. Deepfake detection based on discrepancies between faces and their context[J]. IEEE Transactions on Pattern Analysis and Machine Intelli-gence, 2022, 44(10): 6111-6121.
[61] SUN K, YAO T, CHEN S, et al. Dual contrastive learning for general face forgery detection[J]. arXiv:2112.13522, 2021.
[62] SABIR E, CHENG J X, JAISWAL A, et al. Recurrent con-volutional strategies for face manipulation detection in videos[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Long Beach,Jun 16-20, 2019. Piscataway: IEEE, 2019: 80-87.
[63] GüERA D, DELP E J. Deepfake video detection using recurrent neural networks[C]//Proceedings of the 15th IEEE International Conference on Advanced Video and Signal Based Surveillance, Auckland, Nov 27-30, 2018. Piscataway: IEEE, 2018: 1-6.
[64] 邢豪. 基于时空特征的深度伪造视频篡改检测[D]. 太原: 太原理工大学, 2021.
XING H. Deepfake video detection based on spatial-temporal features[D]. Taiyuan: Taiyuan University of Technology, 2021.
[65] CHINTHA A, THAI B, SOHRAWARDI S J, et al. Recurrent convolutional structures for audio spoof and video deepfake detection[J]. IEEE Journal of Selected Topics in Signal Pro-cessing, 2020, 14(5): 1024-1037.
[66] CHOLLET F. Xception: deep learning with depthwise separ-able convolutions[C]//Proceedings of the 2017 IEEE Con-ference on Computer Vision and Pattern Recognition, Ho-nolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 1800-1807.
[67] FEI J, XIA Z, YU P, et al. Exposing AI-generated videos with motion magnification[J]. Multimedia Tools and Appli-cations, 2021, 80(20): 30789-30802.
[68] WU X, XIE Z, GAO Y T, et al. SSTNet: detecting manipu-lated faces through spatial, steganalysis and temporal features[C]//Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona,May 4-8, 2020. Piscataway: IEEE, 2020: 2952-2956.
[69] AMERINI I, CALDELLI R. Exploiting prediction error in-consistencies through LSTM-based classifiers to detect deep-fake videos[C]//Proceedings of the 2020 ACM Workshop on Information Hiding and Multimedia Security, Denver,Jun 22-24, 2020. New York: ACM, 2020: 97-102.
[70] MASI I, KILLEKAR A, MASCARENHAS R M, et al. Two-branch recurrent network for isolating deepfakes in videos[C]//LNCS 12352: Proceedings of the 16th European Conference on Computer Vision, Aug 23-28, 2020. Cham:Springer, 2020: 667-684.
[71] MONTSERRAT D M, HAO H X, YARLAGADDA S K, et al. Deepfakes detection with automatic face weighting[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 2851-2859.
[72] 邢豪, 李明. 基于3D CNNS的深度伪造视频篡改检测[J]. 计算机科学, 2021, 48(7): 86-92.
XING H, LI M. Deepfake video detection based on 3D convolutional nerual network[J]. Computer Science, 2021, 48(7): 86-92.
[73] ZHANG D C, LI C Y, LIN F Z, et al. Detecting deepfake videos with temporal dropout 3DCNN[C]//Proceedings of the 30th International Joint Conference on Artificial Intelli-gence, Aug 19-26, 2021: 1288-1294.
[74] ZHENG Y L, BAO J M, CHEN D, et al. Exploring temporal coherence for more general video face forgery detection[J]. arXiv:2108.06693, 2021.
[75] GU Z H, CHEN Y, YAO T P, et al. Spatiotemporal inconsis-tency learning for deepfake video detection[C]//Proceedings of the 29th ACM International Conference on Multimedia,Chengdu, Oct 20-24, 2021. New York: ACM, 2021: 3473-3481.
[76] GU Z H, CHEN Y, YAO T P, et al. Delving into the local: dynamic inconsistency learning for deepfake video detection[C]//Proceedings of the 36th AAAI Conference on Artificial Intelligence, the 34th Conference on Innovative Applica-tions of Artificial Intelligence, the 12th Symposium on Edu-cational Advances in Artificial Intelligence, Feb 22-Mar 1, 2022. Menlo Park: AAAI, 2022: 744-752.
[77] AMERINI I, GALTERI L, CALDELLI R, et al. Deepfake video detection through optical flow based CNN[C]//Pro-ceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, Seoul, Oct 27-28, 2019. Piscataway: IEEE, 2019: 1205-1207.
[78] SUN D, YANG X, LIU M Y, et al. PWC-Net: CNNs for op-tical flow using pyramid, warping, and cost volume[C]//Pro-ceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 8934-8943.
[79] CHINTHA A, RAO A, SOHRAWARDI S, et al. Leveraging edges and optical flow on faces for deepfake detection[C]//Proceedings of the 2020 IEEE International Joint Conference on Biometrics, Houston, Sep 28-Oct 1, 2020. Piscataway: IEEE, 2020: 1-10.
[80] LOPES A T, DE AGUIAR E, DE SOUZA A F, et al. Facial expression recognition with convolutional neural networks: coping with few data and the training sample order[J]. Pat-tern Recognition, 2017, 61: 610-628.
[81] DONG X, SI W, HUANG W. ECG-based identity recogni-tion via deterministic learning[J]. Biotechnology & Biotech-nological Equipment, 2018, 32(3): 769-777.
[82] AGARWAL S, FARID H, GU Y M, et al. Protecting world leaders against deep fakes[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 38-45.
[83] AGARWAL S, FARID H, EL-GAALY T, et al. Detecting deep-fake videos from appearance and behavior[C]//Procee-dings of the 12th IEEE International Workshop on Infor-mation Forensics and Security, New York, Dec 6-11, 2020.Piscataway: IEEE, 2020: 1-6.
[84] WILES O, KOEPKE A S, ZISSERMAN A. Self-supervised learning of a facial attribute embedding from video[J]. arXiv: 1808.06882, 2018.
[85] COZZOLINO D, R?SSLER A, THIES J, et al. ID-Reveal: identity-aware deepfake video detection[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, Montreal, Oct 10-17, 2021. Piscataway: IEEE, 2021: 15088-15097.
[86] DONG X Y, BAO J M, CHEN D D, et al. Protecting celebrities with identity consistency transformer[J]. arXiv:2203.01318, 2022.
[87] SUN Z K, HAN Y J, HUA Z Y, et al. Improving the effi-ciency and robustness of deepfakes detection through pre-cise geometric features[C]//Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition, Jun 19-25, 2021. Piscataway: IEEE, 2021: 3609-3618.
[88] CIFTCI U A, DEMIR I, YIN L. FakeCatcher: detection of synthetic portrait videos using biological signals[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020. DOI: 10.1109/TPAMI.2020.3009287.
[89] YANG X, LI Y Z, LYU S. Exposing deep fakes using in-consistent head poses[C]//Proceedings of the 2019 IEEE In-ternational Conference on Acoustics, Speech and Signal Pro-cessing, Brighton, May 12-17,?2019. Piscataway: IEEE, 2019: 8261-8265.
[90] QI H, GUO Q, XU J F, et al. DeepRhythm: exposing deep-fakes with attentional visual heartbeat rhythms[C]//Procee-dings of the 28th ACM International Conference on Multi-media, Seattle, Oct 12-16, 2020. New York: ACM, 2020: 4318-4327.
[91] NIU X, SHAN S, HAN H, et al. RhythmNet: end-to-end heart rate estimation from face via spatial-temporal representation[J]. IEEE Transactions on Image Processing, 2019, 29: 2409-2423.
[92] CIFTCI U A, DEMIR I, YIN L J. How do the hearts of deep fakes beat? Deep fake source detection via interpreting resi-duals with biological signals[C]//Proceedings of the 2020 IEEE International Joint Conference on Biometrics, Houston, Sep 28-Oct 1, 2020. Piscataway: IEEE, 2020: 1-10.
[93] NGUYEN H M, DERAKHSHANI R. Eyebrow recognition for identifying deepfake videos[C]//Proceedings of the 19th International Conference of the Biometrics Special Interest Group, Sep 16-18, 2020: 199-206.
[94] MATERN F, RIESS C, STAMMINGER M. Exploiting visual artifacts to expose deepfakes and face manipulations[C]//Proceedings of the 2019 IEEE Winter Applications of Computer Vision Workshops, Waikoloa Village, Jan 7-11, 2019. Piscataway: IEEE, 2019: 83-92.
[95] ZHOU Y P, LIM S N. Joint audio-visual deepfake detection[C]//Proceedings of the 2021 IEEE/CVF International Con-ference on Computer Vision, Montreal, Oct 10-17, 2021. Piscataway: IEEE, 2021: 14780-14789.
[96] WANG G, ZHANG P, XIE L, et al. An audio-visual atten-tion based multimodal network for fake talking face videos detection[J]. arXiv:2203.05178, 2022.
[97] CHUGH K, GUPTA P, DHALL A, et al. Not made for each other-audio-visual dissonance-based deepfake detection and localization[C]//Proceedings of the 28th ACM International Conference on Multimedia, Seattle, Oct 12-16, 2020. New York: ACM, 2020: 439-447.
[98] HALIASSOS A, VOUGIOUKAS K, PETRIDIS S, et al. Lips don’t lie: a generalisable and robust approach to face forgery detection[C]//Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition, Jun 19-25, 2021. Piscataway: IEEE, 2021: 5039-5049.
[99] CHUNG J S, ZISSERMAN A. Lip reading in the wild[C]//Proceedings of the 13th Asian Conference on Computer Vi-sion, Taipei, China, Nov 20-24, 2016. Cham: Springer, 2016: 87-103.
[100] ZHAO H, ZHOU W, CHEN D, et al. Self-supervised trans-former for deepfake detection[J]. arXiv:2203.01265, 2022.
[101] HALIASSOS A, MIRA R, PETRIDIS S, et al. Leveraging real talking faces via self-supervision for robust forgery detection[J]. arXiv:2201.07131, 2022.
[102] GRILL J B, STRUB F, ALTCHé F, et al. Bootstrap your own latent—a new approach to self-supervised learning[C]//Advances in Neural Information Processing Systems, 2020, 33: 21271-21284.
[103] LIN J, ZHOU W, LIU H, et al. Lip forgery video detec-tion via multi-phoneme Selection[C]//Proceedings of the 2021 International Workshop on Safety & Secruity of Deep Learning, New York, Jun 7-11, 2021: 1-8.
[104] AGARWAL S, FARID H, FRIED O, et al. Detecting deep-fake videos from phoneme-viseme mismatches[C]//Procee-dings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 14-19, 2020.Piscataway: IEEE, 2020: 2814-2822.
[105] CHENG H, GUO Y, WANG T, et al. Voice-face homo-geneity tells deepfake[J]. arXiv:2203.02195, 2022.
[106] AGARWAL S, FARID H. Detecting deep-fake videos from aural and oral dynamics[C]//Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Jun 19-25, 2021. Piscataway: IEEE, 2021: 981-989.
[107] MITTAL T, BHATTACHARYA U, CHANDRA R, et al. Emotions don’t lie: an audio-visual deepfake detection me-thod using affective cues[J]. arXiv:2003.06711, 2020.
[108] ZADEH A, LIANG P P, MAZUMDER N, et al. Memory fusion network for multi-view sequential learning[C]//Pro-ceedings of the 32nd AAAI Conference on Artificial In-telligence, the 30th Innovative Applications of Artificial Intelligence, and the 8th AAAI Symposium on Educa-tional Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 5634-5641.
[109] COX I, MILLER M, BLOOM J, et al. Digital watermarking and steganography[M]. San Mateo: Morgan Kaufmann, 2007.
[110] AKHTAR N, MIAN A. Threat of adversarial attacks on deep learning in computer vision: a survey[J]. IEEE Access, 2018, 6: 14410-14430.
[111] HUANG Q, ZHANG J, ZHOU W, et al. Initiative defense against facial manipulation[J]. arXiv:2112.10098, 2021.
[112] KIM C, REN Y, YANG Y. Decentralized attribution of generative models[J]. arXiv:2010.13974, 2021.
[113] YU N, SKRIPNIUK V, ABDELNABI S, et al. Artificial GAN fingerprints: rooting deepfake attribution in training data[J]. arXiv:2007.08457, 2007.
[114] MA C, GU Y, GONG C, et al. Unsupervised video hashing via deep neural network[J]. Neural Processing Letters, 2018, 47(3): 877-890.
[115] LI J, ZHANG H, WAN W, et al. Two-class 3D-CNN classi-fiers combination for video copy detection[J]. Multimedia Tools and Applications, 2020, 79(7): 4749-4761.
[116] TANG W, WO Y, HAN G. Geometrically robust video ha-shing based on ST-PCT for video copy detection[J]. Multi-media Tools and Applications, 2019, 78(15): 21999-22022.
[117] KOOPMAN M, RODRIGUEZ A M, GERADTS Z. Detection of deepfake video manipulation[C]//Proceedings of the 20th Irish Machine Vision and Image Processing Conference, Belfast, Aug 29-31, 2018: 133-136.
[118] HUANG H, WANG Y T, CHEN Z Y, et al. CMUA-Water-mark: a cross-model universal adversarial watermark for combating deepfakes[J]. arXiv:2105.10872, 2021.
[119] HASAN H R, SALAH K. Combating deepfake videos using blockchain and smart contracts[J]. IEEE Access, 2019, 7: 41596-41606.
[120] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers for image recognition at scale[J]. arXiv:2010.11929, 2020.
[121] LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierar-chical vision transformer using shifted windows[J]. arXiv:2103.14030, 2021.
[122] HEO Y J, CHOI Y J, LEE Y W, et al. Deepfake detection scheme based on vision transformer and distillation[J].arXiv:2104.01353, 2021.
[123] JEON H, BANG Y, WOO S S. FDFtNet: facing off fake images using fake detection fine-tuning network[C]//Pro-ceedings of the 35th IFIP TC 11 International Conference on ICT Systems Security and Privacy Protection, Maribor,Sep 21-23, 2020. Cham: Springer, 2020: 416-430.
[124] KHORMALI A, YUAN J S. DFDT: an end-to-end deep-fake detection framework using vision transformer[J]. App-lied Sciences, 2022, 12(6): 2953.
[125] KHAN S A, DAI H. Video transformer for deepfake detec-tion with incremental learning[C]//Proceedings of the 29th ACM International Conference on Multimedia, Chengdu, Oct 20-24, 2021. New York: ACM, 2021: 1821-1828.
[126] RAMACHANDRAN S, NADIMPALLI A V, RATTANI A. An experimental evaluation on deepfake detection using deep face recognition[J]. arXiv:2110.01640, 2021.
[127] SUN K, LIU H, YE Q X, et al. Domain general face for-gery detection by learning to weight[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence, the 33rd Conference on Innovative Applications of Artificial Intelligence, the 11th Symposium on Educational Advances in Artificial Intelligence, Feb 2-9, 2021. Menlo Park: AAAI,2021: 2638-2646.
[128] KHORMALI A, YUAN J S. ADD: attention-based deep-fake detection approach[J]. Big Data and Cognitive Com-puting, 2021, 5(4): 49.
[129] DANG H, LIU F, STEHOUWER J, et al. On the detection of digital face manipulation[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 5781-5790.
[130] NGUYEN H H, FANG F, YAMAGISHI J, et al. Multi-task learning for detecting and segmenting manipulated facial images and videos[J]. arXiv:1906.06876, 2019.
[131] HSU C C, ZHUANG Y X, LEE C Y. Deep fake image detection based on pairwise learning[J]. Applied Sciences, 2020, 10(1): 370.
[132] FERNANDO T, FOOKES C, DENMAN S, et al. Exploiting human social cognition for the detection of fake and frau-dulent faces via memory networks[J]. arXiv:1911.07844, 2019.
[133] DU M, PENTYALA S, LI Y, et al. Towards generalizable deepfake detection with locality-aware autoencoder[C]//Proceedings of the 29th ACM International Conference on Information and Knowledge Management, Ireland, Oct 19-23, 2020.?New York: ACM, 2020: 325-334.
[134] GUO Z H, YANG G B, CHEN J Y, et al. Fake face detec-tion via adaptive residuals extraction network[J]. arXiv:2005.04945, 2020.