Abstract
Deep neural networks (DNNs) are proved to be vulnerable against backdoor attacks. A backdoor is often embedded in the target DNNs through injecting a backdoor trigger into training examples, which can cause the target DNNs misclassify an input attached with the backdoor trigger. Existing backdoor detection methods often require the access to the original poisoned training data, the parameters of the target DNNs, or the predictive confidence for each given input, which are impractical in many real-world applications, e.g., on-device deployed DNNs. We address the black-box hard-label backdoor detection problem where the DNN is fully black-box and only its final output label is accessible. We approach this problem from the optimization perspective and show that the objective of backdoor detection is bounded by an adversarial objective. Further theoretical and empirical studies reveal that this adversarial objective leads to a solution with highly skewed distribution; a singularity is often observed in the adversarial map of a backdoor-infected example, which we call the adversarial singularity phenomenon. Based on this observation, we propose the adversarial extreme value analysis(AEVA) to detect backdoors in black-box neural networks. AEVA is based on an extreme value analysis of the adversarial map, computed from the monte-carlo gradient estimation. Evidenced by extensive experiments across multiple popular tasks and backdoor attacks, our approach is shown effective in detecting backdoor attacks under the black-box hard-label scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2110.14880
