AI RESEARCH
Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations
arXiv CS.LG
•
ArXi:2605.06357v1 Announce Type: new This work studies the robust evaluation of iterative stochastic purification defenses under white-box adversarial attacks. Our key technical insight is that gradient checkpointing makes exact end-to-end gradient computation through long purification trajectories practical by trading additional recomputation for substantially lower memory usage. This enables full-gradient adaptive attacks against diffusion- and Langevin-based purification defenses, where prior evaluations often resort to approximate backpropagation due to memory constraints.