Papers
arxiv:2509.25082

MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification

Published on Sep 29
· Submitted by Kejia Zhang on Oct 1
Authors:
,
,
,

Abstract

MANI-Pure, a magnitude-adaptive purification framework using diffusion models, effectively suppresses high-frequency adversarial perturbations while preserving low-frequency content, enhancing robust accuracy.

AI-generated summary

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 attack types. Motivated by this observation, we introduce MANI-Pure, a magnitude-adaptive purification framework that leverages the magnitude spectrum of inputs to guide the purification process. Instead of injecting homogeneous noise, MANI-Pure adaptively applies heterogeneous, frequency-targeted noise, effectively suppressing adversarial perturbations in fragile high-frequency, low-magnitude bands while preserving semantically critical low-frequency content. Extensive experiments on CIFAR-10 and ImageNet-1K validate the effectiveness of MANI-Pure. It narrows the clean accuracy gap to within 0.59 of the original classifier, while boosting robust accuracy by 2.15, and achieves the top-1 robust accuracy on the RobustBench leaderboard, surpassing the previous state-of-the-art method.

Community

Paper author Paper submitter

A good purification method achieve the trade-off between clean and adversarial conditions, and it surpass the SOTA method in RobustBench.

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.25082 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2509.25082 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.25082 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.