Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models

TL;DR

This paper introduces TriPatch, a novel physical adversarial patch method that disrupts pedestrian detection across multiple stages and under diverse physical conditions, significantly improving attack success rates.

Contribution

TriPatch combines multi-stage collaborative attacks with robustness enhancements, including appearance consistency and data augmentation, to improve physical adversarial patch effectiveness.

Findings

TriPatch achieves higher attack success rates than existing methods.

The method maintains robustness under various physical and environmental conditions.

Extensive experiments validate the effectiveness across multiple detector models.

Abstract

Physical adversarial patch attacks critically threaten pedestrian detection, causing surveillance and autonomous driving systems to miss pedestrians and creating severe safety risks. Despite their effectiveness in controlled settings, existing physical attacks face two major limitations in practice: they lack systematic disruption of the multi-stage decision pipeline, enabling residual modules to offset perturbations, and they fail to model complex physical variations, leading to poor robustness. To overcome these limitations, we propose a novel pedestrian adversarial patch generation method that combines multi-stage collaborative attacks with robustness enhancement under physical diversity, called TriPatch. Specifically, we design a triplet loss consisting of detection confidence suppression, bounding-box offset amplification, and non-maximum suppression (NMS) disruption, which jointly act across different stages of the detection pipeline. In addition, we introduce an appearance consistency loss to constrain the color distribution of the patch, thereby improving its adaptability under diverse imaging conditions, and incorporate data augmentation to further enhance robustness against complex physical perturbations. Extensive experiments demonstrate that TriPatch achieves a higher attack success rate across multiple detector models compared to existing approaches.