Light Can Hack Your Face! Black-box Backdoor Attack on Face Recognition Systems

Abstract

Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the targeted DNN is always available, and an attacker can always inject a specific pattern to the training data to further fine-tune the DNN model. However, in practice, such attack may not be feasible as the DNN model is encrypted and only available to the secure enclave. In this paper, we propose a novel black-box backdoor attack technique on face recognition systems, which can be conducted without the knowledge of the targeted DNN model. To be specific, we propose a backdoor attack with a novel color stripe pattern trigger, which can be generated by modulating LED in a specialized waveform. We also use an evolutionary computing strategy to optimize the waveform for backdoor attack. Our backdoor attack can be conducted in a very mild condition: 1) the adversary cannot manipulate the input in an unnatural way (e.g., injecting adversarial noise); 2) the adversary cannot access the training database; 3) the adversary has no knowledge of the training model as well as the training set used by the victim party. We show that the backdoor trigger can be quite effective, where the attack success rate can be up to $88\%$ based on our simulation study and up to $40\%$ based on our physical-domain study by considering the task of face recognition and verification based on at most three-time attempts during authentication. Finally, we evaluate several state-of-the-art potential defenses towards backdoor attacks, and find that our attack can still be effective. We highlight that our study revealed a new physical backdoor attack, which calls for the attention of the security issue of the existing face recognition/verification techniques.

First two authors contributed equally

References in corpus (15)

• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• How To Backdoor Federated Learning
• RetinaFace: Single-stage Dense Face Localisation in the Wild
• SphereFace: Deep Hypersphere Embedding for Face Recognition
• Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems
• Generating Adversarial Examples with Adversarial Networks
• Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
• Transferable Clean-Label Poisoning Attacks on Deep Neural Nets
• Invisible Mask: Practical Attacks on Face Recognition with Infrared
• Hardware Trojan Attacks on Neural Networks
• Defending against Backdoor Attack on Deep Neural Networks
• Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
• Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networks
• Face Image Reflection Removal

Cited by in corpus (1)

• SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image Classifiers