Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid

TL;DR

This paper introduces AdvGrid, a novel black-box physical attack method using a grid-based perturbation approach and genetic algorithms to fool infrared pedestrian detectors across multiple views with high success rates.

Contribution

We propose AdvGrid, a new multi-view black-box physical attack technique on infrared detectors using grid perturbations and genetic algorithms, improving effectiveness and robustness over prior methods.

Findings

Achieves 80% success rate in digital environments

Achieves 91.86% success rate in physical environments

Outperforms baseline attack methods

Abstract

While extensive research exists on physical adversarial attacks within the visible spectrum, studies on such techniques in the infrared spectrum are limited. Infrared object detectors are vital in modern technological applications but are susceptible to adversarial attacks, posing significant security threats. Previous studies using physical perturbations like light bulb arrays and aerogels for white-box attacks, or hot and cold patches for black-box attacks, have proven impractical or limited in multi-view support. To address these issues, we propose the Adversarial Infrared Grid (AdvGrid), which models perturbations in a grid format and uses a genetic algorithm for black-box optimization. These perturbations are cyclically applied to various parts of a pedestrian's clothing to facilitate multi-view black-box physical attacks on infrared pedestrian detectors. Extensive experiments validate AdvGrid's effectiveness, stealthiness, and robustness. The method achieves attack success rates of 80.00\% in digital environments and 91.86\% in physical environments, outperforming baseline methods. Additionally, the average attack success rate exceeds 50\% against mainstream detectors, demonstrating AdvGrid's robustness. Our analyses include ablation studies, transfer attacks, and adversarial defenses, confirming the method's superiority.