Side-Channel Gray-Box Attack for DNNs
- 27 July 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 68 (1) , 501-505
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.Keywords
Funding Information
- National Natural Science Foundation of China (61873241, 61973273, 61572439)
- Zhejiang Provincial Natural Science Foundation of China (LR19F030001)
This publication has 17 references indexed in Scilit:
- Practical Black-Box Attacks against Machine Learning2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Leave Your Phone at the Door2016
- Deep Residual Learning for Image Recognition2016
- The Limitations of Deep Learning in Adversarial Settings2016
- Deep learningNature, 2015
- A fault induction technique based on voltage underfeeding with application to attacks against AES and RSAJournal of Systems and Software, 2013
- EM Side-Channel Attacks on Commercial Contactless Smartcards Using Low-Cost EquipmentLecture Notes in Computer Science, 2009
- Electromagnetic Analysis: Concrete Results2001
- Timing Attacks on Implementations of Diffie-Hellman, RSA, DSS, and Other Systems1996