PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Wavelets

2026-02-03

AI Summary

This work proposes a plug-and-play, non-intrusive defense mechanism in the spectral domain for 3D point cloud adversarial robustness, circumventing the need for invasive model modifications, auxiliary data, or costly retraining. By introducing spectral graph wavelet theory into adversarial purification—a first for 3D point clouds—the method leverages the strong correlation between imperceptible perturbations and high-frequency spectral components. It constructs a hierarchical purification framework that combines saliency scoring with local sparsity to selectively remove highly salient adversarial outliers and attenuate high-frequency noise in moderately salient points. Evaluated across multiple benchmarks, the approach significantly enhances model robustness against imperceptible attacks while preserving high clean accuracy, offering an efficient and deployable solution for real-world applications.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

Recent progress in adversarial attacks on 3D point clouds, particularly in achieving spatial imperceptibility and high attack performance, presents significant challenges for defenders. Current defensive approaches remain cumbersome, often requiring invasive model modifications, expensive training procedures or auxiliary data access. To address these threats, in this paper, we propose a plug-and-play and non-invasive defense mechanism in the spectral domain, grounded in a theoretical and empirical analysis of the relationship between imperceptible perturbations and high-frequency spectral components. Building upon these insights, we introduce a novel purification framework, termed PWAVEP, which begins by computing a spectral graph wavelet domain saliency score and local sparsity score for each point. Guided by these values, PWAVEP adopts a hierarchical strategy, it eliminates the most salient points, which are identified as hardly recoverable adversarial outliers. Simultaneously, it applies a spectral filtering process to a broader set of moderately salient points. This process leverages a graph wavelet transform to attenuate high-frequency coefficients associated with the targeted points, thereby effectively suppressing adversarial noise. Extensive evaluations demonstrate that the proposed PWAVEP achieves superior accuracy and robustness compared to existing approaches, advancing the state-of-the-art in 3D point cloud purification. Code and datasets are available at https://github.com/a772316182/pwavep

Problem

• adversarial perturbations
• 3D point clouds
• imperceptibility
• defense mechanism
• spectral domain

Innovation

• spectral graph wavelets
• 3D point cloud defense
• adversarial purification
• non-invasive defense
• high-frequency attenuation