Tootfinder

MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification
Xiaoyi Huang, Junwei Wu, Kejia Zhang, Carl Yang, Zhiming Luo
https://arxiv.org/abs/2509.25082 https://…

MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification
Adversarial purification with diffusion models has emerged as a promising defense strategy, but existing methods typically rely on uniform noise injection, which indiscriminately perturbs all frequencies, corrupting semantic structures and undermining robustness. Our empirical study reveals that adversarial perturbations are not uniformly distributed: they are predominantly concentrated in high-frequency regions, with heterogeneous magnitude intensity patterns that vary across frequencies and a…