DePatch: Towards Robust Adversarial Patch for Evading Person Detectors in the Real World

TL;DR

DePatch is a novel adversarial patch method that improves robustness against physical transformations by decoupling patch segments, significantly enhancing attack success in real-world person detection evasion.

Contribution

The paper introduces DePatch, a decoupled adversarial patch approach that addresses self-coupling issues, with novel strategies like block-wise segmentation, random erasing, border shifting, and progressive decoupling.

Findings

DePatch outperforms existing physical adversarial attacks in real-world scenarios.

Decoupling segments enhances robustness against physical transformations.

The method achieves higher attack success rates in person detection evasion.

Abstract

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.