Physical Adversarial Camouflage through Gradient Calibration and Regularization

TL;DR

This paper introduces a novel gradient-based adversarial camouflage method that improves attack success rates against deep object detectors across various distances and angles by ensuring stable and effective texture optimization.

Contribution

It proposes gradient calibration and decorrelation techniques to enhance physical adversarial camouflage stability and effectiveness in complex environments.

Findings

Achieved 13.46% higher attack success rate across distances

Achieved 11.03% higher attack success rate across angles

Demonstrated effectiveness in real-world scenarios

Abstract

The advancement of deep object detectors has greatly affected safety-critical fields like autonomous driving. However, physical adversarial camouflage poses a significant security risk by altering object textures to deceive detectors. Existing techniques struggle with variable physical environments, facing two main challenges: 1) inconsistent sampling point densities across distances hinder the gradient optimization from ensuring local continuity, and 2) updating texture gradients from multiple angles causes conflicts, reducing optimization stability and attack effectiveness. To address these issues, we propose a novel adversarial camouflage framework based on gradient optimization. First, we introduce a gradient calibration strategy, which ensures consistent gradient updates across distances by propagating gradients from sparsely to unsampled texture points. Additionally, we develop a gradient decorrelation method, which prioritizes and orthogonalizes gradients based on loss values, enhancing stability and effectiveness in multi-angle optimization by eliminating redundant or conflicting updates. Extensive experimental results on various detection models, angles and distances show that our method significantly exceeds the state of the art, with an average increase in attack success rate (ASR) of 13.46% across distances and 11.03% across angles. Furthermore, empirical evaluation in real-world scenarios highlights the need for more robust system design.