Guided Diffusion Model for Adversarial Purification from Random Noise

2022/06/22 by Quanlin Wu, Hang Ye, Wu, Quanlin +3 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2206.10875

openalex publication_date 2022/06/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose a novel guided diffusion purification approach to provide a strong defense against adversarial attacks. Our model achieves 89.62% robust accuracy under PGD-L_inf attack (eps = 8/255) on the CIFAR-10 dataset. We first explore the essential correlations between unguided diffusion models and randomized smoothing, enabling us to apply the models to certified robustness. The empirical results show that our models outperform randomized smoothing by 5% when the certified L2 radius r is larger than 0.5.

Cited by

• DBLP: Noise Bridge Consistency Distillation For Efficient And Reliable Adversarial Purification
• Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion

Related

• Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
• Random Sampling for Diffusion-based Adversarial Purification
• ADBM: Adversarial diffusion bridge model for reliable adversarial purification
• Guided Diffusion Model for Adversarial Purification
• DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification