Showing 2025Show all
2 papers · 1 filter
cs.CV2025
LoRA Patching: Exposing the Fragility of Proactive Defenses against Deepfakes
Zuomin Qu, Yimao Guo, Qianyue Hu +1
Deepfakes pose significant societal risks, motivating the development of proactive defenses that embed adversarial perturbations in facial images to prevent manipulation. However,…
cs.CV2025
Anti-Inpainting: A Proactive Defense Approach against Malicious Diffusion-based Inpainters under Unknown Conditions
Yimao Guo, Zuomin Qu, Wei Lu +1
With the increasing prevalence of diffusion-based malicious image manipulation, existing proactive defense methods struggle to safeguard images against tampering under unknown cond…