Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

6-2023

Abstract

In recent years, as various realistic face forgery techniques known as DeepFake improves by leaps and bounds, more and more DeepFake detection techniques have been proposed. These methods typically rely on detecting statistical differences between natural (i.e., real) and DeepFake-generated images in both spatial and frequency domains. In this work, we propose to explicitly minimize the statistical differences to evade state-of-the-art DeepFake detectors. To this end, we propose a statistical consistency attack (StatAttack) against DeepFake detectors, which contains two main parts. First, we select several statistical-sensitive natural degradations (i.e., exposure, blur, and noise) and add them to the fake images in an adversarial way. Second, we find that the statistical differences between natural and DeepFake images are positively associated with the distribution shifting between the two kinds of images, and we propose to use a distribution-aware loss to guide the optimization of different degradations. As a result, the feature distributions of generated adversarial examples is close to the natural images. Furthermore, we extend the StatAttack to a more powerful version, MStatAttack, where we extend the single-layer degradation to multi-layer degradations sequentially and use the loss to tune the combination weights jointly. Comprehensive experimental results on four spatial-based detectors and two frequency-based detectors with four datasets demonstrate the effectiveness of our proposed attack method in both white-box and black-box settings.

Keywords

degradation, deepfakes, frequency-domain analysis, closed box, detectors, forgery, pattern recognition

Discipline

Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

First Page

12271

Last Page

12280

Identifier

10.1109/CVPR52729.2023.01181

Publisher

IEEE

City or Country

Canada

Additional URL

https://doi.org/10.1109/CVPR52729.2023.01181

Share

COinS