Disrupting Anti-Spoofing Systems by Images of Consistent Identity

Feng Ding, Zihan Jiang, Yue Zhou, Jianfeng Xu, Guopu Zhu

Abstract: Face anti-spoofing aims to distinguish between live and spoof images to ensure the authenticity and reliability of face recognition. Methods based on convolutional neural networks surpass prior approaches in accuracy but remain vulnerable to adversarial attacks. Traditional vulnerability disclosure relies on image quality metrics, which lack crucial identity details for face recognition in deceptive images. Thus, we introduce a novel framework that creates identity-consistent adversarial samples for face anti-spoofing. We also redefine image quality assessment for anti-spoofing by using detection rates from facial recognizers rather than conventional metrics. Inspired by style transfer, our generator incorporates an LKA module to enhance performance. An identity recognition module ensures consistency within synthesized images, capturing the essence of identity across live and spoof visuals. Our approach outperforms most adversarial tactics on anti-spoofing detectors while retaining a high identity recognition rate.