Litcius/Paper detail

Decision-Based Query Efficient Adversarial Attack via Adaptive Boundary Learning

Meng Shen, Changyue Li, Hao Yu, Qi Li, Liehuang Zhu, Ke Xu

2023IEEE Transactions on Dependable and Secure Computing12 citationsDOI

Abstract

Decision-based adversarial attacks pose a severe threat to real-world applications of Deep Neural Networks (DNNs), as attackers are assumed to have no prior knowledge about target model except hard labels of model outputs. Existing decision-based attacks require a large number of queries on the target model for a successful attack. In this paper, we propose DEAL, a decision-based query efficient adversarial attack based on adaptive boundary learning. DEAL relies on a local model named boundary learner, which is initialized through meta-learning mechanism to obtain the ability to adapt the decision boundaries to a new model. We conduct extensive experiments to evaluate the effectiveness of DEAL, which demonstrates that it outperforms 8 state-of-the-art attacks. Specifically for the evaluation on CIFAR-10 dataset, DEAL can achieve similar attack success rates with a maximum reduction in average number of queries of 51% in untargeted attacks and 14% in targeted attacks, respectively.

Topics & Concepts

Computer scienceAdversarial systemDecision boundaryArtificial intelligenceBoundary (topology)Machine learningArtificial neural networkAttack modelDecision modelDeep learningComputer securityClassifier (UML)Mathematical analysisMathematicsAdversarial Robustness in Machine LearningCardiac Arrest and Resuscitation