The Illusion of Forgetting: Attack Unlearned Diffusion via Initial Latent Variable Optimization
概要
arXiv:2602.00175v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models (DMs) are frequently abused to produce harmful or copyrighted content, violating public interests. Concept erasure (unlearning) is a promising paradigm to alleviate this issue. However, there exists a peculiar …
