Jointly Defending DeepFake Manipulation and Adversarial Attack Using Decoy Mechanism

Guan Lin Chen, Chih Chung Hsu

Research output: Contribution to journalArticlepeer-review

Abstract

Highly realistic imaging and video synthesis have become possible and relatively simple tasks with the rapid growth of generative adversarial networks (GANs). GAN-related applications, such as DeepFake image and video manipulation and adversarial attacks, have been used to disrupt and confound the truth in images and videos over social media. DeepFake technology aims to synthesize high visual quality image content that can mislead the human vision system, while the adversarial perturbation attempts to mislead the deep neural networks to a wrong prediction. Defense strategy becomes difficult when adversarial perturbation and DeepFake are combined. This study examined a novel deceptive mechanism based on statistical hypothesis testing against DeepFake manipulation and adversarial attacks. First, a deceptive model based on two isolated sub-networks was designed to generate two-dimensional random variables with a specific distribution for detecting the DeepFake image and video. This research proposes a maximum likelihood loss for training the deceptive model with two isolated sub-networks. Afterward, a novel hypothesis was proposed for a testing scheme to detect the DeepFake video and images with a well-trained deceptive model. The comprehensive experiments demonstrated that the proposed decoy mechanism could be generalized to compressed and unseen manipulation methods for both DeepFake and attack detection.

Original languageEnglish
Pages (from-to)9922-9931
Number of pages10
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume45
Issue number8
DOIs
Publication statusPublished - 2023 Aug 1

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Jointly Defending DeepFake Manipulation and Adversarial Attack Using Decoy Mechanism'. Together they form a unique fingerprint.

Cite this