ML Security PapersRevoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models
Daiheng Gao, Nanxiang Jiang, Andi Zhang et al. · University of Science and Technology of China · Beihang University +3 more
RL-based trajectory steering attack that resurrects concepts erased by safety mechanisms in diffusion models 10x faster than prior methods
Concept erasure techniques have been widely deployed in T2I diffusion models to prevent inappropriate content generation for safety and copyright considerations. However, as models evolve to next-generation architectures like Flux, established erasure methods (\textit{e.g.}, ESD, UCE, AC) exhibit degraded effectiveness, raising questions about their true mechanisms. Through systematic analysis, we reveal that concept erasure creates only an illusion of ``amnesia": rather than genuine forgetting, these methods bias sampling trajectories away from target concepts, making the erasure fundamentally reversible. This insight motivates the need to distinguish superficial safety from genuine concept removal. In this work, we propose \textbf{RevAm} (\underline{Rev}oking \underline{Am}nesia), an RL-based trajectory optimization framework that resurrects erased concepts by dynamically steering the denoising process without modifying model weights. By adapting Group Relative Policy Optimization (GRPO) to diffusion models, RevAm explores diverse recovery trajectories through trajectory-level rewards, overcoming local optima that limit existing methods. Extensive experiments demonstrate that RevAm achieves superior concept resurrection fidelity while reducing computational time by 10$\times$, exposing critical vulnerabilities in current safety mechanisms and underscoring the need for more robust erasure techniques beyond trajectory manipulation.