Evasion attacks on generative safeguards: target-concept reappearance under structural control in grey-box settings
Abstract Concept erasure has emerged as a practical safeguard for suppressing unsafe or unwanted concepts in text-to-image diffusion models. However, existing methods are primarily designed for text-triggered generation and are usually evaluated under text-only prompting. In this paper, we identify a practical robustne...
Qiqi Bao, Jiaoling Li, Yunxin Zhang et al.
· Cybersecurity · 0 citations