Browse > Article

데이터 기반 딥페이크 탐지기법에 관한 최신 기술 동향 조사  

Kim, Jeongho (성균관대학교 수학과)
An, Jaeju (을지대학교 의료IT마케팅학과)
Yang, Bosung (아주대학교 사이버보안학과)
Jung, Jooyeon (숙명여자대학교 컴퓨터과학과)
Woo, Simon S. (성균관대학교 데이터사이언스융합학과/소프트웨어학과)
Publication Information
Review of KIISC / v.30, no.5, 2020 , pp. 79-92 More about this Journal
Keywords
Citations & Related Records
연도 인용수 순위
  • Reference
1 Justus Thies, Michael Zollhofer, Marc Stamminger, Christian Theobalt, and Matthias Niessner. Face2Face: Real-Time Face Capture and Reenactment of RGB Videos. In IEEE pages 2387-2395, June 2016
2 Faceswap. https://github.com/Marek Kowalski/FaceSwap/.
3 Deepfakes https://github.com/deepfakes/faceswap. Accessed: 2018-10-29
4 Justus Thies, Michael Zollhofer, and Matthias Nie$\ss$ner. Deferred neural rendering: Image synthesis using neural textures. ACM Transactions on Graphics 2019 (TOG), 2019
5 Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros. Image-to-image translation with conditional adversarial networks. CVPR, 2017
6 Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courvile, and Yoshua Bengio, "Generative adversarial nets", In Advances in neural information processing systems, 27, June 2014.
7 Ivan Perov, Daiheng Gao, Nikolay Chervoniy, Kunlin Liu, Sugasa Maranggonda, Chris Ume, Mr. dpfks, carl Shift Facenheim, Luis RP, Jian Jiang, Sheng Zhang, Pingyu Wo, Bo zhou, Weiming Zhang, "DeepFaceLab: A simple, flexible and extensible face swapping framework", Computer Vision and Pattern Recognition, May 2020.
8 Deepfakes. Deepfakes. https://github.co m/deepfakes/faceswap, 2017.
9 Lingzhi Li, Jianmin Bao, Hao Yang, Dong Chen, Fang Wen, "FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping", Computer Vision and Pattern Recognition. Dec 2019.
10 Olaf Ronneberger, Philipp Fischer, Thomas Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation", Computer Vision and Pattern Recognition. May 2015.
11 Hyeonseong Jeon Youngoh Bang, Junyaup Kim and Simon S.Woo, "T-GD: Transferable GAN-generated Images Detection Framewok", ICML, 2020
12 RoyChowdhury, A., Chakrabarty, P., Singh, A., Jin, S., Jiang, H., Cao, L., and Learned-Miller, E. Automatic adaptation of object detectors to new domains using selftraining. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 780-790, 2019.
13 Li, X., Grandvalet, Y., and Davoine, F. Explicit inductive bias for transfer learning with convolutional networks. arXiv preprint arXiv:1802.01483, 2018.
14 Xuan, X., Peng, B., Wang, W., and Dong, J. On the generalization of gan image forensics. In Chinese Conference on Biometric Recognition, pp. 134-141. Springer, 2019.
15 Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1):1929-1958, 2014.
16 Huang, G., Sun, Y., Liu, Z., Sedra, D., and Weinberger, K. Q. Deep networks with stochastic depth. In European conference on computer vision, pp. 646-661. Springer, 2016.
17 Wang, S.-Y., Wang, O., Zhang, R., Owens, A., and Efros, A. A. Cnn-generated images are surprisingly easy to spot... for now. arXiv preprint arXiv:1912.11035, 2019
18 Yun, S., Han, D., Oh, S. J., Chun, S., Choe, J., and Yoo, Y. Cutmix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE International Conference on Computer Vision, pp. 6023-6032, 2019.
19 Diederik P Kingma and Max Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
20 Wikipedia contributors. Graphical model - Wikipedia, the free encyclopedia, 2020. [Online; accessed 15-February-2020].
21 Wikipedia contributors. Kullback-leibler divergence-Wikipedia, the free encyclopedia, 2020.
22 Wikipedia contributors. Monte carlo method - Wikipedia, the free encyclopedia, 2020. [Online; accessed 13-March-2020].
23 Davide Cozzolino, Giovanni Poggi, and Luisa Verdoliva. Recasting residual-based local descriptors as convolutional neural networks: an application to image forgery detection. In ACM Workshop on Information Hiding and Multimedia Security, pages 1-6, 2017
24 Cozzolino, Davide, Justus Thies, Andreas Rossler, Christian Riess, Matthias Nie$\ss$ner, and Luisa Verdoliva. "Forensictransfer: Weakly-supervised domain adaptation for forgery detection." arXiv preprint arXiv:1812.02510 (2018)
25 Belhassen Bayar and Matthew C. Stamm. A deep learning approach to universal image manipulation detection using a new convolutional layer. In ACM Workshop on Information Hiding and Multimedia Security, pages 5-10, 2016
26 Nicolas Rahmouni, Vincent Nozick, Junichi Yamagishi, and Isao Echizen. Distinguishing computer graphics from natural images using convolution neural networks. In IEEE Workshop on Information Forensics and Security, pages 1-6, 2017
27 Darius Afchar, Vincent Nozick, Junichi Yamagishi, and Isao Echizen. Mesonet: a compact facial video forgery detection network. arXiv preprint arXiv:1809.00888, 2018
28 Hasam Khalid and Simon S. Woo. OC-FakeDect: Classifying Deepfakes Using One-class Variational Autoencoder. CVPR, 2020
29 Regina Rini, "Deepfakes Are Coming. We Can No Longer Believe What We See.", June 2019, 2020년 9월 접속 https://www.nytimes.com/2019/06/10/opinion/deepfake-pelosi-video.html
30 Oscar Schwartz, "You thought fake news was bad? Deepfakes are where truth goes to die.", Nov 2018, 2020년 9월 접속, https://www.theguar dian.com/technology/2018/nov/12/deep-fakes-fake-news-truth
31 BBC NEWS, "Deepfake videos could 'spark violent social unrest", June 2019, 2020년 9월 접속, https://www.bbc.com/news/technology-48621452
32 Lux Alptraum, "Deepfake Pron Harms Adult Performers, Too.", Jan 2020, 2020년 9월 접속, https://www.wired.com/sto ry/deepfake-porn-harms-adult-performers-too/
33 Alex Moltzau, "What Strategy Does Europe Have to Tackle Deepfakes?", 2020년 9월 접속, https://medium.com/dataseries/what-strategy-does-europe-have-to-tackle-deepfakes-fb159040f0c
34 Wikipedia contributors. Deepfake -Wikipedia, the free encyclopedia, 2020.
35 RIvan Mehta, "A new study says nearly 96% of deepfake videos are porn.", Oct 2019, 2020년 9월 접속, https://thenextweb.com/apps/2019/10/07/a-new-study-says-nearly-96-of-deepfake-videos-areporn/
36 Rossler, Andreas, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Niessner. "Faceforensics++: Learning to detect manipulated facial images." In Proceedings of the IEEE International Conference on Computer Vision, pp. 1-11. 2019