Robust Physical-World Attacks on Face Recognition
This work addresses security concerns in safety-critical applications like face recognition by improving adversarial robustness, though it is incremental as it builds on existing sticker-based attack methods.
The paper tackles the vulnerability of deep neural network-based face recognition systems to physical adversarial attacks by proposing a robust framework called PadvFace, which models variations in stickers, faces, and environmental conditions, and demonstrates superior performance in dodging and impersonation attacks through extensive experiments.
Face recognition has been greatly facilitated by the development of deep neural networks (DNNs) and has been widely applied to many safety-critical applications. However, recent studies have shown that DNNs are very vulnerable to adversarial examples, raising serious concerns on the security of real-world face recognition. In this work, we study sticker-based physical attacks on face recognition for better understanding its adversarial robustness. To this end, we first analyze in-depth the complicated physical-world conditions confronted by attacking face recognition, including the different variations of stickers, faces, and environmental conditions. Then, we propose a novel robust physical attack framework, dubbed PadvFace, to model these challenging variations specifically. Furthermore, considering the difference in attack complexity, we propose an efficient Curriculum Adversarial Attack (CAA) algorithm that gradually adapts adversarial stickers to environmental variations from easy to complex. Finally, we construct a standardized testing protocol to facilitate the fair evaluation of physical attacks on face recognition, and extensive experiments on both dodging and impersonation attacks demonstrate the superior performance of the proposed method.