AI RESEARCH
LURE: Latent Space Unblocking for Multi-Concept Reawakening in Diffusion Models
arXiv CS.LG
•
ArXi:2601.14330v2 Announce Type: replace-cross Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods. Existing reawakening methods mainly rely on prompt-level optimization to manipulate sampling trajectories, neglecting other generative factors, which limits a comprehensive understanding of the underlying dynamics.