DePatch: Towards Robust Adversarial Patch for Evading Person Detectors in the Real World
This work improves robustness for physical adversarial attacks against person detectors, but it is incremental as it builds on existing patch-based methods.
The paper tackles the problem of poor robustness in physical adversarial patches for person detectors by addressing the self-coupling issue, resulting in a method that demonstrates superior performance in real-world experiments.
Recent years have seen an increasing interest in physical adversarial attacks, which aim to craft deployable patterns for deceiving deep neural networks, especially for person detectors. However, the adversarial patterns of existing patch-based attacks heavily suffer from the self-coupling issue, where a degradation, caused by physical transformations, in any small patch segment can result in a complete adversarial dysfunction, leading to poor robustness in the complex real world. Upon this observation, we introduce the Decoupled adversarial Patch (DePatch) attack to address the self-coupling issue of adversarial patches. Specifically, we divide the adversarial patch into block-wise segments, and reduce the inter-dependency among these segments through randomly erasing out some segments during the optimization. We further introduce a border shifting operation and a progressive decoupling strategy to improve the overall attack capabilities. Extensive experiments demonstrate the superior performance of our method over other physical adversarial attacks, especially in the real world.