信息安全研究 ›› 2022, Vol. 8 ›› Issue (3): 258-.
张煜之;王锐芳;朱亮;赵坤园;刘梦琪;
出版日期:
2022-03-01
发布日期:
2022-03-01
通讯作者:
张煜之 硕士研究生.主要研究方向为信息安全、机器学习对抗.
2301747676@qq.com
作者简介:
张煜之 硕士研究生.主要研究方向为信息安全、机器学习对抗.
2301747676@qq.com
王锐芳 硕士,讲师.主要研究方向为信息安全、机器学习对抗.
wangruifang29@163.com
朱亮 硕士研究生.主要研究方向为信息安全、机器学习对抗.
179728398@qq.com
赵坤园 硕士研究生.主要研究方向为信息安全.
280518242@qq.com
刘梦琪 硕士研究生.主要研究方向为信息安全.
liu_confidence@163.com
Online:
2022-03-01
Published:
2022-03-01
摘要: 近年来兴起的深度伪造技术能够篡改或生成高度逼真且难以甄别的音视频内容,并得到了广泛的良性和恶意应用。针对深度伪造的生成和检测,国内外专家学者进行了深入研究,并提出了相应的生成和检测方案。对现有的基于深度学习的音视频深度伪造生成技术、检测技术、数据集以及未来的研究方向进行了全面的概述和详细分析,这些工作将有助于相关人员对深度伪造的理解和对恶意深度伪造防御检测的研究。
张煜之, 王锐芳, 朱亮, 赵坤园, 刘梦琪, . 深度伪造生成和检测技术综述[J]. 信息安全研究, 2022, 8(3): 258-.
[1]Mirsky Y, Lee W. The creation and detection of deepfakes: A survey[J]. ACM Computing Surveys (CSUR), 2021, 54(1): 1-41 [2] Xu F J, Wang Run, Huang Yihao, et al. Countering malicious deepfakes: Survey, battleground, and horizon[EB/OL].(2021-12-07)[2021-12-20]. https://arxiv.org/abs/2103.00218v1 [3] Masood M, Nawaz M, Malik K M, et al. Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward[EB/OL].(2021-11-23)[2021-12-20].https://arxiv.org/abs/2103.00484 [4]VisionborneInc.Faceswap:Deepfakes software for all[EB/OL].(2020-09-08)[2021-12-20].https://github.com/deepfakes/faceswap [5]GitHubInc.Faceswap-GAN[EB/OL].(2020-09-18)[2021-12-20].https://github.com/shaoanlu/faceswap-GAN [6]Natsume R, Yatagawa T, Morishima S. Fsnet: an identity-aware generative model for image-basedface swapping[EB/OL].(2018-11-30)[2021-12-20].https://arxiv.org/abs/1811.12666v1 [7]Natsume R, Yatagawa T, Morishima S. Rsgan: face swapping and editing using face and hair representation in latent spaces[EB/OL].(2018-04-18)[2021-12-20].https://arxiv.org/abs/1804.03447v1 [8]Li Lingzhi, Bao Jianmin, Yang Hao, et al. Advancing high fidelity identity swapping for forgery detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.NJ:IEEE,2020: 5074-5083 [9] Korshunova I, Shi Wenzhe, Dambre J, et al. Fast face-swap using convolutional neural networks[C]//2017IEEE International Conference on Computer Vision.NJ:IEEE,2017: 3677-3685 [10] KR P, Mukhopadhyay R, Philip J, et al. Towards automatic face-to-face translation[C]// The 27th ACM International Conference on Multimedia. New York: ACM, 2019: 1428-1436 [11]Wu W, Zhang Y, Li C, et al. Reenactgan: Learning to reenact faces via boundary transfer[EB/OL]. [2021-12-20].https://xs.dailyheadlines.cc/scholar?hl=zh-CN&as_sdt=0%2C5&q=Reenactgan%3A+Learning+to+reenact+faces+via+boundary+transfer&btnG= [12] Tripathy S, Kannala J, Rahtu E. Icface: Interpretable and controllable face reenactment using gans[C]//The IEEE/CVF Winter Conference on Applications of Computer Vision. NJ:IEEE, 2020: 3385-3394 [13]Nirkin Y, Keller Y, Hassner T. Fsgan: Subject agnostic face swapping and reenactment[C]//The IEEE/CVF International Conference on Computer Vision. NJ:IEEE, 2019: 7184-7193 [14] Karras T, Aila T, Laine S, et al. Progressive growing of gans for improved quality, stability, and variation[EB/OL].(2018-02-26)[2021-12-20].https://arxiv.org/abs/1710.10196 [15] Liu Mingyu, Tuzel O. Coupled generative adversarial networks[J]. Advances in Neural Information Processing Systems, 2016, 29(12): 469-477 [16]Zhang Han, Goodfellow I, Metaxas D, et al. Self-attention generative adversarial networks[EB/OL].(2019-06-14)[2021-12-20]. https://arxiv.org/abs/1805.08318 [17]Choi Y, Uh Y, Yoo J, et al. Stargan v2: Diverse image synthesis for multiple domains[C]//The IEEE/CVF Conference on Computer Vision and Pattern Recognition. NJ:IEEE, 2020: 8188-8197 [18]He Zhenliang, Zuo Wangmeng, Kan Meina, et al. Attgan: Facial attribute editing by only changing what you want[J].IEEE Transactions on Image Processing,2019, 28(11):5464-5478 [19]Liu Ming, Ding Yukang, Xia Min, et al. STGAN: A unified selective transfer network for arbitrary image attribute editing[C]//The IEEE/CVF Conference on Computer Vision and Pattern Recognition. NJ:IEEE, 2019: 3673-3682 [20]Ping Wei, Peng Kainan, Gibiansky A, et al. Deep Voice 3: 2000-Speaker Neural Text-to-Speech[EB/OL].(2018-02-22)[2021-12-20]. https://arxiv.org/abs/1710.07654v1 [21]Yasuda Y, Wang Xin, Takaki S, et al. Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language[C]//2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). NJ:IEEE, 2019: 6905-6909 [22]Arik S, Chen Jitong, Peng Kainan, et al. Neural voice cloning with a few samples[EB/OL].[2021-12-20].https://arxiv.org/abs/1802.06006 [23]Jia Ye, Zhang Yu, Weiss R, et al. Transfer learning from speaker verification to multispeaker text-to-speech synthesis[EB/OL].[2021-12-20].https://arxiv.org/abs/1806.04558 [24]Cong Jian, Yang Shan, Xie Lei, et al. Data efficient voice cloning from noisy samples with domain adversarial training[EB/OL].[2021-12-20].https://arxiv.org/abs/2008.04265 [25]Sun Lifa, Kang Shiyin, Li Kun, et al. Voice conversion using deep bidirectional long short-term memory based recurrent neural networks[C]//2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). NJ:IEEE, 2015: 4869-4873 [26]Kaneko T, Kameoka H, Tanaka K, et al. Cyclegan-vc2: Improved cyclegan-based non-parallel voice conversion[C]//2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). NJ:IEEE, 2019: 6820-6824 [27]Kameoka H, Kaneko T, Tanaka K, et al. Stargan-vc: Non-parallel many-to-many voice conversion using star generative adversarial networks[C]//2018 IEEE Spoken Language Technology Workshop (SLT). NJ:IEEE, 2018: 266-273 [28]Zhang Mingyang, Sisman B, Zhao Li, et al. DeepConversion: Voice conversion with limited parallel training data[J]. Speech Communication, 2020, 122(12): 31-43 [29]Li Haobin, Li Bin, Tan Shunquan, et al. Identification of deep network generated images using disparities in color components[EB/OL].[2021-12-20]. https://www.sciencedirect.com/science/article/abs/pii/S0165168420301596 [30]Liu Bo, Pun C. Deep fusion network for splicing forgery localization[EB/OL]. [2021-12-20].https://xs.dailyheadlines.cc/scholar?hl=zh-CN&as_sdt=0%2C5&q=%5B30%5DLiu+Bo%2C+Deep+fusion+network+for+splicing+forgery+localization&btnG=#d=gs_qabs&u=%23p%3DoHm946ya1nwJ [31]Zhou Peng, Han Xintong, Morariu V, et al. Learning rich features for image manipulation detection[C]//The IEEE Conference on Computer Vision and Pattern Recognition. NJ:IEEE, 2018: 1053-1061 [32]Durall R, Keuper M, Pfreundt F, et al. Unmasking deepfakes with simple features[EB/OL].[2021-12-20].https://arxiv.org/abs/1911.00686 [33]Dang Hao, Liu Feng, Stehouwer J, et al.On the detection of digital face manipulation[C]//The IEEE/CVF Conference on Computer Vision and Pattern Recognition. NJ:IEEE,2020: 5781-5790 [34]Bayar B, Stamm M.A deep learning approach to universal image manipulation detection using a new convolutional layer[C]//The 4th ACM Workshop on Information Hiding and Multimedia Security.New York:ACM, 2016: 5-10 [35]Rahmouni N, Nozick V, Yamagishi J, et al. Distinguishing computer graphics from natural images using convolution neural networks[C]//2017 IEEE Workshop on Information Forensics and Security (WIFS). NJ:IEEE,2017: 1−6 [36]Li Yuezun, Chang M, Lyu S. In ictu oculi: Exposing ai created fake videos by detecting eye blinking[C]//2018 IEEE International Workshop on Information Forensics and Security (WIFS). NJ:IEEE, 2018: 1-7 [37]Yang Xin, Li Yuezun, Lyu S. Exposing deep fakes using inconsistent head poses[C]//2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). NJ:IEEE,2019: 8261-8265 [38]Hernandez-Ortega J, Tolosana R, Fierrez J, et al. Deepfakeson-phys: Deepfakes detection based on heart rate estimation[EB/OL].[2021-12-20].https://arxiv.org/abs/2010.00400 [39]Qian Yuyang, Yin Guojun, Sheng L, et al. Thinking in frequency: Face forgery detection bymining frequency-aware clues[C]//European Conference on Computer Vision. Cham:Springer, 2020: 86-103 [40]Chen Yunpeng, Fan Haoqi, Xu Bing, et al. Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution[C]//The IEEE/CVF International Conference on Computer Vision. NJ:IEEE,2019: 3435-3444 [41]Zhang Zhenyu, Yi Xiaowei, Zhao Xiaofeng. Fake Speech Detection Using Residual Network with Transformer Encoder[C]//The 2021 ACM Workshop on Information Hiding and Multimedia Security. New York: ACM, 2021: 13-22 [42]Huang Lian, Pun C. Audio Replay Spoof Attack Detection by Joint Segment-Based Linear Filter Bank Feature Extraction and Attention-Enhanced DenseNet-BiLSTM Network[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020, 28(12): 1813-1825 [43]Zhang You, Jiang Fei, Duan Zhiyao.One-class learning towards synthetic voice spoofing detection[J]. IEEE Signal Processing Letters, 2021, 28(12): 937-941 [44]Wang Run, Xu J F, Huang Yihao, et al. Deepsonar: Towards effective and robustdetection of ai-synthesized fake voices[C]//The 28th ACM International Conference on Multimedia. New York:ACM, 2020: 1207-1216 [45]Reimao R, Tzerpos V. FoR: A Dataset for Synthetic Speech Detection[C]//2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD).NJ:IEEE, 2019: 1-10 [46]malavida.FakeApp 2.2.0[EB/OL].(2020-09-18)[2021-12-20].https://www.malavida.com/en/soft/fakeapp [47]Rossler A, Cozzolino D, Verdoliva L, et al. Faceforensics++: Learning to detect manipulated facial images[C]//The IEEE/CVF International Conference on Computer Vision. NJ:IEEE, 2019: 1-11 [48]Rössler A, Cozzolino D, Verdoliva L, et al. Faceforensics: A large-scale video dataset for forgery detection in human faces[EB/OL].[2021-12-20].https://arxiv.org/abs/1803.09179 [49]Korshunov P, Marcel S. Deepfakes: a new threat to face recognition?assessment and detection[EB/OL].[2021-12-20].https://arxiv.org/abs/1812.08685 [50]Li Yuezun, Yang Xin, Sun Pu, et al. Celeb-df: A new dataset for deepfakeforensics[EB/OL]. [2021-12-20].https://arxiv.org/abs/1909.12962 [51]Dolhansky B, Howes R, Pflaum B, et al. The deepfake detection challenge (dfdc) preview dataset[EB/OL].[2021-12-20].https://arxiv.org/abs/1910.08854 [52]Jiang Liming, Li Ren, Wu W, et al. Deeperforensics-1.0: A large-scale dataset for real-world face forgery detection[C]//The IEEE/CVF Conference on Computer Vision and Pattern Recognition. NJ:IEEE,2020: 2889-2898 [53]Wang Xin, Yamagishi J, Todisco M, et al. ASVspoof 2019: A large-scale public databaseof synthesized, converted and replayed speech[EB/OL].(2020-07-14)[2021-12-20]. https://arxiv.org/abs/1911.01601v1 [54]Arik S O, Chen Jitong, Peng Kainan, et al. Neural voice cloning with a few samples[EB/OL].[2021-12-20].https://arxiv.org/abs/1802.06006 |
[1] | 金志刚 周峻毅 何晓勇. 面向自然语言处理领域的对抗攻击研究与展望[J]. 信息安全研究, 2022, 8(3): 202-. |
[2] | 桓琦, 谢小权, 郭敏, 曾颖明, . 针对深度强化学习导航的物理对抗攻击方法[J]. 信息安全研究, 2022, 8(3): 212-. |
[3] | 梁晨, 王利斌, 李卓群, 薛源, . 生成式对抗网络技术与研究进展[J]. 信息安全研究, 2022, 8(3): 235-. |
[4] | 孙毅, 王志浩, 邓佳, 李犇, 杨彬, 唐胜, . 人脸深度伪造检测综述[J]. 信息安全研究, 2022, 8(3): 241-. |
[5] | 胡韵, 刘嘉驹, 李春国, . 一种基于差分隐私的可追踪深度学习分类器[J]. 信息安全研究, 2022, 8(3): 277-. |
[6] | 石波, 于然, 陈志浩, 朱健, . 工业控制系统安全态势评估与预测方案[J]. 信息安全研究, 2022, 8(2): 145-. |
[7] | 卫霞 白国柱 张文俊. 基于区块链技术对抗深度伪造现状研究[J]. 信息安全研究, 2021, 7(7): 615-620. |
[8] | 徐金才 任民 李琦 孙哲南. 图像对抗样本的安全性研究概述[J]. 信息安全研究, 2021, 7(4): 294-309. |
[9] | 冯科 阮树骅 陈兴蜀 王海舟 王文贤 蒋术语. 基于联合模型的网络舆情事件检测方法 [J]. 信息安全研究, 2021, 7(3): 207-214. |
[10] | 白国柱 王蓓蓓. Deepfake检测技术现状研究及其对中国的启示[J]. 信息安全研究, 2020, 6(9): 0-0. |
[11] | 肖喜生 彭凯飞 龙春 魏金侠 赵静. 基于人工智能的安全态势预测技术研究综述[J]. 信息安全研究, 2020, 6(6): 0-0. |
[12] | 白国柱 王蓓蓓. Deepfake技术监管政策现状、面临的挑战及建议[J]. 信息安全研究, 2020, 6(5): 454-457. |
[13] | 雷惊鹏. 基于云计算和深度学习的协议监测系统设计[J]. 信息安全研究, 2020, 6(12): 1127-1132. |
[14] | 周琳娜 吕欣一. 基于GAN图像生成的信息隐藏技术综述[J]. 信息安全研究, 2019, 5(9): 771-777. |
[15] | 李创丰 李云龙 孙伟. 基于CNN和朴素贝叶斯方法的安卓恶意 应用检测算法[J]. 信息安全研究, 2019, 5(6): 470-476. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||