Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical World

TL;DR

This paper introduces AdvIC, a novel physical-world infrared attack method using optimized Bezier curves and cold patches, achieving high success rates and demonstrating robustness and stealthiness against infrared pedestrian detectors.

Contribution

We propose AdvIC, a new physical infrared attack technique employing Particle Swarm Optimization and Bezier curves, improving realism, stealth, and robustness over existing methods.

Findings

Achieves 94.8% digital attack success rate

Achieves 67.2% physical attack success rate

Maintains high effectiveness against diverse detectors

Abstract

Deep neural network security is a persistent concern, with considerable research on visible light physical attacks but limited exploration in the infrared domain. Existing approaches, like white-box infrared attacks using bulb boards and QR suits, lack realism and stealthiness. Meanwhile, black-box methods with cold and hot patches often struggle to ensure robustness. To bridge these gaps, we propose Adversarial Infrared Curves (AdvIC). Using Particle Swarm Optimization, we optimize two Bezier curves and employ cold patches in the physical realm to introduce perturbations, creating infrared curve patterns for physical sample generation. Our extensive experiments confirm AdvIC's effectiveness, achieving 94.8\% and 67.2\% attack success rates for digital and physical attacks, respectively. Stealthiness is demonstrated through a comparative analysis, and robustness assessments reveal AdvIC's superiority over baseline methods. When deployed against diverse advanced detectors, AdvIC achieves an average attack success rate of 76.8\%, emphasizing its robust nature. we explore adversarial defense strategies against AdvIC and examine its impact under various defense mechanisms. Given AdvIC's substantial security implications for real-world vision-based applications, urgent attention and mitigation efforts are warranted.