Synthesizing Black-box Anti-forensics DeepFakes with High Visual Quality
This work addresses the challenge of creating more deceptive and visually appealing DeepFakes for attackers, but it is incremental as it builds on existing anti-forensics techniques.
The paper tackles the problem of anti-forensics attacks on DeepFake detectors, which often degrade image quality, by proposing a method to generate adversarial sharpening masks that achieve high anti-forensics performance while improving visual quality, with experimental results showing successful disruption of state-of-the-art detectors and significant refinement in visual quality compared to existing methods.
DeepFake, an AI technology for creating facial forgeries, has garnered global attention. Amid such circumstances, forensics researchers focus on developing defensive algorithms to counter these threats. In contrast, there are techniques developed for enhancing the aggressiveness of DeepFake, e.g., through anti-forensics attacks, to disrupt forensic detectors. However, such attacks often sacrifice image visual quality for improved undetectability. To address this issue, we propose a method to generate novel adversarial sharpening masks for launching black-box anti-forensics attacks. Unlike many existing arts, with such perturbations injected, DeepFakes could achieve high anti-forensics performance while exhibiting pleasant sharpening visual effects. After experimental evaluations, we prove that the proposed method could successfully disrupt the state-of-the-art DeepFake detectors. Besides, compared with the images processed by existing DeepFake anti-forensics methods, the visual qualities of anti-forensics DeepFakes rendered by the proposed method are significantly refined.