Adversarial Purification with the Manifold Hypothesis

2022/10/26 by Zhaoyuan Yang, Zhiwei Xu, Yang, Zhaoyuan +7 · 2 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Bacillus and Francisella bacterial research #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2210.14404

openalex publication_date 2022/10/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this work, we formulate a novel framework for adversarial robustness using the manifold hypothesis. This framework provides sufficient conditions for defending against adversarial examples. We develop an adversarial purification method with this framework. Our method combines manifold learning with variational inference to provide adversarial robustness without the need for expensive adversarial training. Experimentally, our approach can provide adversarial robustness even if attackers are aware of the existence of the defense. In addition, our method can also serve as a test-time defense mechanism for variational autoencoders.

Cited by

• Adversarial Machine Learning Attacks on Financial Reporting via Maximum Violated Multi-Objective Attack
• Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense

Related

• Manifold attack
• Approximate Manifold Defense Against Multiple Adversarial Perturbations
• Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks
• Understanding Adversarial Robustness Against On-manifold Adversarial Examples
• Variational Inference with Latent Space Quantization for Adversarial\n Resilience