Sorry, you need to enable JavaScript to visit this website.

Synthesizing Black-box Anti-forensics DeepFakes with High Visual Quality

DOI:
10.60864/2n42-0m49
Citation Author(s):
Bing Fan,Shu Hu,Feng Ding
Submitted by:
bing fan
Last updated:
6 June 2024 - 10:22am
Document Type:
Presentation Slides
Document Year:
2024
Event:
Presenters:
bing fan
Categories:
 

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.

up
0 users have voted: