RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World

TL;DR

This paper introduces RFLA, a stealthy physical adversarial attack using reflected light patterns created with transparent sheets and geometrical shapes, achieving high success rates in digital and physical settings.

Contribution

The paper proposes a novel reflected light attack framework that is highly stealthy and effective in both digital and physical environments, unlike previous conspicuous or weak optical attacks.

Findings

Achieves over 99% success rate across datasets and models.

Effective in physical environments using sunlight or flashlight.

Outperforms existing physical adversarial attack methods.

Abstract

Physical adversarial attacks against deep neural networks (DNNs) have recently gained increasing attention. The current mainstream physical attacks use printed adversarial patches or camouflage to alter the appearance of the target object. However, these approaches generate conspicuous adversarial patterns that show poor stealthiness. Another physical deployable attack is the optical attack, featuring stealthiness while exhibiting weakly in the daytime with sunlight. In this paper, we propose a novel Reflected Light Attack (RFLA), featuring effective and stealthy in both the digital and physical world, which is implemented by placing the color transparent plastic sheet and a paper cut of a specific shape in front of the mirror to create different colored geometries on the target object. To achieve these goals, we devise a general framework based on the circle to model the reflected light on the target object. Specifically, we optimize a circle (composed of a coordinate and radius) to carry various geometrical shapes determined by the optimized angle. The fill color of the geometry shape and its corresponding transparency are also optimized. We extensively evaluate the effectiveness of RFLA on different datasets and models. Experiment results suggest that the proposed method achieves over 99% success rate on different datasets and models in the digital world. Additionally, we verify the effectiveness of the proposed method in different physical environments by using sunlight or a flashlight.