Detecting Compressed Deepfake Videos in Social Networks Using Frame-Temporality Two-Stream Convolutional Network
Top Cited Papers
- 20 April 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (3) , 1089-1102
Abstract
The development of technologies that can generate Deepfake videos is expanding rapidly. These videos are easily synthesized without leaving obvious traces of manipulation. Though forensically detection in high-definition video datasets has achieved remarkable results, the forensics of compressed videos is worth further exploring. In fact, compressed videos are common in social networks, such as videos from Instagram, Wechat, and Tiktok. Therefore, how to identify compressed Deepfake videos becomes a fundamental issue. In this paper, we propose a two-stream method by analyzing the frame-level and temporality-level of compressed Deepfake videos. Since the video compression brings lots of redundant information to frames, the proposed frame-level stream gradually prunes the network to prevent the model from fitting the compression noise. Aiming at the problem that the temporal consistency in Deepfake videos might be ignored, we apply a temporality-level stream to extract temporal correlation features. When combined with scores from the two streams, our proposed method performs better than the state-of-the-art methods in compressed Deepfake videos detection.Keywords
Funding Information
- National Natural Science Foundation of China (61972142, 61972395, 61772191)
- Hunan Provincial Natural Science Foundation of China (2020JJ4212)
- Key Lab of Information Network Security, Ministry of Public Security (C20611)
- Science and Technology Program of Changsha (kq2004021)
This publication has 31 references indexed in Scilit:
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition2016
- Motion-Adaptive Frame Deletion Detection for Digital Video ForensicsIEEE Transactions on Circuits and Systems for Video Technology, 2016
- Deep Residual Learning for Image Recognition2016
- Face2Face: Real-Time Face Capture and Reenactment of RGB Videos2016
- Learning Deep Features for Discriminative Localization2016
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Automatic Detection of Object-Based Forgery in Advanced VideoIEEE Transactions on Circuits and Systems for Video Technology, 2015
- Design and Implementation of Mediaplayer Based on FFmpeg2012
- Image information and visual qualityIEEE Transactions on Image Processing, 2006
- Multiscale structural similarity for image quality assessment2004