Browse > Article
http://dx.doi.org/10.3837/tiis.2022.05.014

Cascaded-Hop For DeepFake Videos Detection  

Zhang, Dengyong (Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology)
Wu, Pengjie (Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology)
Li, Feng (Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology)
Zhu, Wenjie (Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology)
Sheng, Victor S. (Department of Computer Science, Texas Tech University)
Publication Information
KSII Transactions on Internet and Information Systems (TIIS) / v.16, no.5, 2022 , pp. 1671-1686 More about this Journal
Abstract
Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models.
Keywords
Face manipulation; Deepfake detection; Machine learning; PixelHop++; SSL;
Citations & Related Records
연도 인용수 순위
  • Reference
1 H. H Nguyen, F. Fang, J. Yamagishi, and I. Echizen, "Multi-task learning for detecting and segmenting manipulated facial images and videos," in Proc. of BTAS, Tampa, FL, USA, pp. 1-8, 2019.
2 P. Yu, J. Fei, Z. Xia, Z. Zhou and J. Weng, "Improving Generalization by Commonality Learning in Face Forgery Detection," IEEE Transactions on Information Forensics and Security, vol. 17, pp. 547-558, Jan. 2022.   DOI
3 R. Tolosana, R. Vera-Rodriguez, J. Fierrez, A. Morales, and J. Ortega-Garcia, "Deepfakes and beyond: A survey of face manipulation and fake detection," Information Fusion, vol. 64, pp. 131-148, Dec. 2020.   DOI
4 S. Agarwal, H. Farid, Y. Gu, M. He, K. Nagano et al., "Protecting world leaders against deep fakes," in Proc. of CVPR, Long Beach, USA, pp. 38-45, 2019.
5 A. Piva, "An overview on image forensics," ISRN Signal Processing, vol. 2013, pp. 1-22, Jan. 2013.   DOI
6 R. Tolosana, S. Romero-Tapiador, J. Fierrez, and R. Vera-Rodriguez, "DeepFake evolution: Analysis of facial regions and fake detection performance," in Proc. of ICPR, Sanya, China, pp. 442-456, 2021.
7 H. H. Nguyen, F. Fang, J. Yamagishi, and I. Echizen, "Multi-task learning for detecting and segmenting manipulated facial images and videos," in Proc. of 2019 IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS), 2019.
8 D. M. Montserrat, H. Hao, S. K. Yarlagadda, S. Baireddy, R. Shao et al., "DeepFake Detection with Automatic Face Weighting," in Proc. of CVPRW, Salt Lake City, Utah, USA, pp. 668-669, 2020.
9 C. L. Wang, Y. L. Liu, Y. J. Tong, J. W. Wang, "GAN-GLS: Generative Lyric Steganography based on Generative Adversarial Networks," Computers, Materials & Continua, vol. 69, no.1, pp. 1375-1390, Jun. 2021.   DOI
10 H. Li, B. Li, S. Tan, and J. Huang, "Detection of deep network generated images using disparities in color components," Eprint arXiv:1808.07276, 2018.
11 B. Dolhansky, R. Howes, B. Pflaum, N. Baram, and C. C. Ferrer, "The deepfake detection challenge (DFDC) preview dataset," Eprint arXiv:1910.08854, 2019.
12 P. Zhou, X. Han, V. I Morariu, and L. S. Davis, "Two-stream neural networks for tampered face detection," in Proc. of CVPR, Hawaii, USA, pp. 1831-1839, 2017.
13 D. Afchar, V. Nozick, J. Yamagishi, and I. Echizen, "Mesonet: a compact facial video forgery detection network," in Proc. of WIFS, Hong Kong, China, pp. 1-7, 2018.
14 M. Zhang, K. Zeng, and J. Wang, "A survey on face anti-spoofing algorithms," Journal of Information Hiding and Privacy Protection, vol. 2, no. 1, pp. 21-34, Oct. 2020.   DOI
15 B. Hu, J. Wang, "Deep learning for distinguishing computer generated images and natural images: a survey," Journal of Information Hiding and Privacy Protection, vol. 2, no.2, pp. 95-105, Nov. 2020.   DOI
16 P. Korus, "Digital image integrity: a survey of protection and verification techniques Digit," Digital Signal Processing, vol. 71, pp. 1-26, Dec. 2017.   DOI
17 A. Rossler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies, M. Niessner, "FaceForensics++: Learning to Detect Manipulated Facial Images," in Proc. of ICCV, Seoul, Korea (South), pp. 1-11, 2019.
18 D. Wodajo, and S. Atnafu, "Deepfake Video Detection Using Convolutional Vision Transformer," Eprint arXiv: 2102.11126, 2021.
19 Y. Li and S. Lyu, "Exposing DeepFake Videos By Detecting Face Warping Artifacts," Eprint arXiv:1811.00656, 2018.
20 S. McCloskey, and M. Albright, "Detecting GAN-generated Imagery using Color Cues," Eprint arXiv:1812.08247, 2018.
21 N. Yu, L. Davis and M. Fritz, "Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints," in Proc. of ICCV, Santiago, Chile, pp. 7556-7566, 2019.
22 X. Yang, Y. Li, and S. Lyu, "Exposing DeepFake using inconsistent head poses," in Proc. of ICASSP, Brighton, UK, pp. 8261-8265, 2019.
23 F. Matern, C. Riess, and M. Stamminger, "Exploiting visual artifacts to expose DeepFake and face manipulations," in Proc. of WACVW, California, USA, pp. 83-92, 2019.
24 L. Li, J. Bao, T. Zhang, H. Yang, D. Chen, F. Wen et al., "Face X-ray for More General Face Forgery Detection," in Proc. of CVPR, Long Beach, USA, pp. 5000-5009, 2019.
25 Y. Chen, M. Rouhsedaghat, S. You, R. Rao, and C.-C. J. Kuo, "Pixelhop++: A small successive-subspace-learning-based (SSL-based) model for image classification," in Proc. of ICIP, Abu Dhabi, United Arab Emirates, pp. 3294-3298, 2020.
26 Deepfake project-non-official project based on original DeepFake thread [Online]. Available: https://github.com/Madhivarman/deepfake_faceswap, Accessed on: Jan. 2, 2018,
27 E. Sabir, J. Cheng, A. Jaiswal, W. AbdAlmageed, I. Masi et al., "Recurrent convolutional strategies for face manipulation detection in videos," in Proc. of CVPR, Long Beach, USA, pp. 80-87, 2019.
28 S. Suwajanakorn, S. Seitz, and I. Kemelmacher-Shlizerman, "Synthesizing Obama: Learning Lip Sync From Audio," ACM Transactions on Graphics, vol. 36, no. 4, pp. 1-13, Aug. 2017.
29 C.-C. Jay Kuo, "Understanding convolutional neural networks with a mathematical model," Journal of Visual Communication and Image Representation, vol. 41, pp. 406-413, Nov. 2016.   DOI
30 M. Rouhsedaghat, Y. Wang, X. Ge, S. Hu, S. You, "Facehop: A light-weight low-resolution face gender classification method," in Proc. of ICPR, Hong Kong, China, pp. 169-183, 2021.
31 J. C. Neves, R. Tolosana, R. Vera-Rodriguez, V. Lopes, H. Proenca et al., "GANprintR: Improved Fakes and Evaluation of the State-of-the-Art in Face Manipulation Detection," IEEE Journal of Selected Topics in Signal Processing, vol. 14, no. 5, pp. 1038-1048, Jul. 2020.   DOI
32 C.-C. J. Kuo, M. Zhang, S. Li, J. Duan, and Y. Chen, "Interpretable convolutional neural networks via feedforward design," Journal of Visual Communication and Image Representation, vol. 60, pp. 346-359, Apr. 2019.   DOI
33 D. Guera, and E. J. Delp, "Deepfake video detection using recurrent neural networks," in Proc. of AVSS, Auckland, New Zealand, pp. 1-6, 2018.
34 I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu et al., "Generative Adversarial Nets," in Proc. of NIPS, Long Beach, USA, pp. 2672-2680, 2014.
35 Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong et al., "Image Super-Resolution Using Very Deep Residual Channel Attention Networks," in Proc. of ECCV, Munich, Germany, pp. 294-310, 2018.
36 P. Korshunov and S. Marcel, "DeepFake: a New Threat to Face Recognition? Assessment and Detection," Eprint arXiv:1812.08685, 2018.
37 A. Bansal, S. Ma, D. Ramanan, and Y. Sheikh, "Recycle-GAN: Unsupervised video retargeting," in Proc. of ECCV, Munich, Germany, pp. 119-135, 2018.
38 H. P. Wu, Y. L. Liu, J. W. Wang, "Review of Text Classification Methods on Deep Learning," Computers, Materials & Continua, vol. 63, no. 3, pp. 1309-1321, Apr. 2020.   DOI
39 Y. Li, X. Yang, P. Sun, H. Qi and S. Lyu, "Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics," in Proc. of CVPR, Seattle, WA, USA, pp. 3204-3213, 2020.
40 H. H Nguyen, J Yamagishi, and I. Echizen, "Use of a capsule network to detect fake images and videos," Eprint arXiv:1910.12467, 2019.
41 C. R. Wang and W. H. Deng, "Representative Forgery Mining for Fake Face Detection," in Proc. of CVPR, Nashville, TN, USA, pp. 14918-14927, 2021.
42 Y. Choi, M. Choi, M. Kim, J. Ha, S. Kim et al., "StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation," in Proc. of CVPR, Salt Lake City, UT, USA, pp. 8789-8797, 2018.
43 J. Thies, M. Zollhofer, M. Stamminger, C. Theobalt, and M. Niessner, "Face2face: Real-Time Face Capture and Reenactment of RGB Videos," in Proc. of CVPR, Las Vegas, USA, pp. 2387-2395, 2016.
44 Y.Z. Li, B.Y. Sun, T. F. Wu, Y. Wang, "Face Detection with End-to-End Integration of a ConvNet and a 3D Model," in Proc. of ECCV, Amsterdam, Netherlands, pp. 420-436, 2016.
45 C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov et al., "Going deeper with convolutions," in Proc. of CVPR, Boston, MA, USA, pp. 1-9, 2015.
46 D. Y. Zhang, J. W. Hu, F. Li, X. L. Ding, A. K. Sangaiah, V. S. Sheng, "Small Object Detection via Precise Region-Based Fully Convolutional Networks," Computers, Materials & Continua, vol. 69, no. 2, pp. 1503-1517, Jul. 2021.   DOI
47 H.S. Chen, M. Rouhsedaghat, H. Ghani, et al., "Defakehop: A light-weight high-performance deepfake detector," in Proc. of ICME. Shenzhen, China, pp. 1-6, 2021.
48 T. Shahroz, L. Sangyup, K. Hoyoung, S. Youjin, and S.W. Simon, "Detecting Both Machine and Human Created Fake Face Images In the Wild," in Proc. of MPS, Toronto, Canada, pp. 81-87, 2018.
49 Y. Li, M. Chang, S. Lyu, "In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking," in Proc. of WIFS, Hong Kong, China, pp. 1-7, 2018.
50 H. Li, P. He, S. Wang, A. Rocha, X. Jiang et al., "Learning generalized deep feature representation for face anti-spoofing," IEEE Transactions on Information Forensics and Security, vol. 13, no. 10, pp. 2639-2652, Oct. 2018.   DOI
51 Y. Li, X. Yang, P. Sun, H. Qi and S. Lyu, "Celeb-DF(v2): A new dataset for Deepfake forensics," Eprint arXiv:1909.12962, 2019.
52 T. Karras, S. Laine and T. Aila, "A Style-Based Generator Architecture for Generative Adversarial Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 12, pp. 4217-4228, Dec. 2021.   DOI
53 J. Donahue, L. Anne Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan et al., "Long-Term Recurrent Convolutional Networks for Visual Recognition and Description," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 4, pp. 677-691, 2017.   DOI