CapGen:An Environment-Adaptive Generator of Adversarial Patches
This work addresses the need for visually stealthy adversarial patches for physical protection and robustness assessment, though it is incremental as it builds on existing patch methods by focusing on environmental adaptation.
The paper tackled the problem of adversarial patches being visually noticeable by introducing CAPGen, which generates patches that blend with the background environment, achieving superior visual stealthiness while maintaining robust adversarial performance, with patterns found to have a more pronounced effect on attack effectiveness than colors.
Adversarial patches, often used to provide physical stealth protection for critical assets and assess perception algorithm robustness, usually neglect the need for visual harmony with the background environment, making them easily noticeable. Moreover, existing methods primarily concentrate on improving attack performance, disregarding the intricate dynamics of adversarial patch elements. In this work, we introduce the Camouflaged Adversarial Pattern Generator (CAPGen), a novel approach that leverages specific base colors from the surrounding environment to produce patches that seamlessly blend with their background for superior visual stealthiness while maintaining robust adversarial performance. We delve into the influence of both patterns (i.e., color-agnostic texture information) and colors on the effectiveness of attacks facilitated by patches, discovering that patterns exert a more pronounced effect on performance than colors. Based on these findings, we propose a rapid generation strategy for adversarial patches. This involves updating the colors of high-performance adversarial patches to align with those of the new environment, ensuring visual stealthiness without compromising adversarial impact. This paper is the first to comprehensively examine the roles played by patterns and colors in the context of adversarial patches.