Adversarial Catoptric Light: An Effective, Stealthy and Robust Physical-World Attack to DNNs

TL;DR

This paper introduces a novel physical attack on deep neural networks using natural catoptric light, achieving high success, stealthiness, and robustness in both simulated and real-world scenarios.

Contribution

The study presents a new stealthy physical attack method leveraging natural catoptric light, improving over prior artificial light-based attacks in effectiveness and natural appearance.

Findings

Attack success rate of 83.5% in physical scenarios

Over 80% success rate against robust DNNs

Enhanced stealthiness with naturalistic perturbations

Abstract

Deep neural networks (DNNs) have demonstrated exceptional success across various tasks, underscoring the need to evaluate the robustness of advanced DNNs. However, traditional methods using stickers as physical perturbations to deceive classifiers present challenges in achieving stealthiness and suffer from printing loss. Recent advancements in physical attacks have utilized light beams such as lasers and projectors to perform attacks, where the optical patterns generated are artificial rather than natural. In this study, we introduce a novel physical attack, adversarial catoptric light (AdvCL), where adversarial perturbations are generated using a common natural phenomenon, catoptric light, to achieve stealthy and naturalistic adversarial attacks against advanced DNNs in a black-box setting. We evaluate the proposed method in three aspects: effectiveness, stealthiness, and robustness. Quantitative results obtained in simulated environments demonstrate the effectiveness of the proposed method, and in physical scenarios, we achieve an attack success rate of 83.5%, surpassing the baseline. We use common catoptric light as a perturbation to enhance the stealthiness of the method and make physical samples appear more natural. Robustness is validated by successfully attacking advanced and robust DNNs with a success rate over 80% in all cases. Additionally, we discuss defense strategy against AdvCL and put forward some light-based physical attacks.