Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detection

TL;DR

This paper introduces learnable Fourier shapes within an end-to-end differentiable framework to generate effective physical adversarial patches for infrared object detection, significantly improving attack success rates.

Contribution

It proposes a novel Fourier shape-based method for infrared attacks, overcoming previous limitations in representational capacity and optimization efficiency.

Findings

Achieves over 88% attack success rate at distances greater than 25m

Demonstrates robustness across various angles, poses, and individuals

Outperforms existing shape-based attack methods in effectiveness

Abstract

Infrared object detection is crucial for perception in autonomous driving and surveillance but remains vulnerable to physical adversarial attacks. Unlike in the RGB domain, where attacks rely on color texture, infrared attacks must manipulate thermal signatures, making the geometry shape of heat-blocking materials the primary adversarial information carrier. Current shape-based methods suffer from a fundamental trade-off between representational capability and optimization power, limiting their attack effectiveness.In this work, we overcome this dilemma by introducing learnable Fourier shapes to the infrared domain. We utilize an end-to-end differentiable framework where a compact set of Fourier coefficients, defining the shape boundary, is analytically mapped to a pixel-space mask via the winding number theorem. This enables efficient gradient-based optimization to generate potent shapes that cause human targets to evade detection. Extensive digital and physical experiments provide a comprehensive evaluation and validate our superior performance. Our resulting physical patch achieves striking robustness, successfully evading detectors across diverse distances, angles, poses, and individuals, and achieves over 88% attack success rate at distances greater than 25m (conf.=0.5). Code is available at https://github.com/Yongyx99/Fourier-shape-attack.