FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction

Yihao Huang, Felix Juefei-Xu, Run Wang, Qing Guo, Lei Ma, Xiaofei Xie, Jianwen Li, Weikai Miao, Yang Liu, Geguang Pu, Geguang Pu

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

5 被引用数 (Scopus)

抄録

At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image. Such artifact patterns can be easily exploited (by recent methods) for difference detection of real and GAN-synthesized images. However, the existing detection methods put much emphasis on the artifact patterns, which can become futile if such artifact patterns were reduced. Towards reducing the artifacts in the synthesized images, in this paper, we devise a simple yet powerful approach termed FakePolisher that performs shallow reconstruction of fake images through a learned linear dictionary, intending to effectively and efficiently reduce the artifacts introduced during image synthesis. In particular, we first train a dictionary model to capture the patterns of real images. Based on this dictionary, we seek the representation of DeepFake images in a low dimensional subspace through linear projection or sparse coding. Then, we are able to perform shallow reconstruction of the 'fake-free' version of the DeepFake image, which largely reduces the artifact patterns DeepFake introduces. The comprehensive evaluation on 3 state-of-the-art DeepFake detection methods and fake images generated by 16 popular GAN-based fake image generation techniques, demonstrates the effectiveness of our technique. Overall, through reducing artifact patterns, our technique significantly reduces the accuracy of the 3 state-of-the-art fake image detection methods, i.e., 47% on average and up to 93% in the worst case. Our results confirm the limitation of current fake detection methods and calls the attention of DeepFake researchers and practitioners for more general-purpose fake detection techniques.

本文言語英語
ホスト出版物のタイトルMM 2020 - Proceedings of the 28th ACM International Conference on Multimedia
出版社Association for Computing Machinery, Inc
ページ1217-1226
ページ数10
ISBN(電子版)9781450379885
DOI
出版ステータス出版済み - 10 12 2020
イベント28th ACM International Conference on Multimedia, MM 2020 - Virtual, Online, 米国
継続期間: 10 12 202010 16 2020

出版物シリーズ

名前MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia

会議

会議28th ACM International Conference on Multimedia, MM 2020
国/地域米国
CityVirtual, Online
Period10/12/2010/16/20

All Science Journal Classification (ASJC) codes

  • ソフトウェア
  • コンピュータ グラフィックスおよびコンピュータ支援設計
  • 人間とコンピュータの相互作用

フィンガープリント

「FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル