Litcius/Paper detail

Side-Channel Gray-Box Attack for DNNs

Yun Xiang, Yongchao Xu, Yingjie Li, Wen Ma, Qi Xuan, Yi Liu

2020IEEE Transactions on Circuits & Systems II Express Briefs26 citationsDOI

Abstract

Deep neural networks are becoming increasingly popular. However, they are also vulnerable to adversarial attacks. The existing attack methods include white-box attack and black-box attack. The white-box attack assumes full model knowledge while the black-box one assumes none. In this brief, we propose a novel attack method between these two. Specifically, we have made the following contributions: (1) we propose the gray-box attack, which utilizes the side-channel attack to predict the model structure based on a pre-trained classifier and (2) we validate our method on real-world experiments. The experimental results show that our gray-box attack can significantly outperform the existing techniques.

Topics & Concepts

Computer scienceWhite boxBlack boxAdversarial systemGray (unit)Classifier (UML)Side channel attackDeep neural networksArtificial intelligenceMachine learningArtificial neural networkComputer securityCryptographyRadiologyMedicineAdversarial Robustness in Machine LearningAnomaly Detection Techniques and ApplicationsNetwork Security and Intrusion Detection
Side-Channel Gray-Box Attack for DNNs | Litcius