Human-Imperceptible Physical Adversarial Attack for NIR Face Recognition Models
This work addresses security risks in biometric systems for real-world applications, though it is incremental as it builds on prior physical attack methods.
The paper tackles the vulnerability of near-infrared (NIR) face recognition systems to physical adversarial attacks by designing a stealthy patch using infrared-absorbing ink and a light reflection model, achieving an average attack success rate of 82.46% in the physical domain, outperforming existing methods at 64.18%.
Near-infrared (NIR) face recognition systems, which can operate effectively in low-light conditions or in the presence of makeup, exhibit vulnerabilities when subjected to physical adversarial attacks. To further demonstrate the potential risks in real-world applications, we design a novel, stealthy, and practical adversarial patch to attack NIR face recognition systems in a black-box setting. We achieved this by utilizing human-imperceptible infrared-absorbing ink to generate multiple patches with digitally optimized shapes and positions for infrared images. To address the optimization mismatch between digital and real-world NIR imaging, we develop a light reflection model for human skin to minimize pixel-level discrepancies by simulating NIR light reflection. Compared to state-of-the-art (SOTA) physical attacks on NIR face recognition systems, the experimental results show that our method improves the attack success rate in both digital and physical domains, particularly maintaining effectiveness across various face postures. Notably, the proposed approach outperforms SOTA methods, achieving an average attack success rate of 82.46% in the physical domain across different models, compared to 64.18% for existing methods. The artifact is available at https://anonymous.4open.science/r/Human-imperceptible-adversarial-patch-0703/.