WCSE

An Enhanced Convolutional Neural Network in Side-Channel Attacks and Visualization

Abstract— In recent years, the convolutional neural networks (CNNs) have received a lot of interest in the side-channel community. Based on the architecture of Residual Network, we build an enhanced CNN model called attention network. To enhance the power of feature representation of the attention network, we investigate an attention mechanism - Convolutional Block Attention Module (CBAM). By CBAM, attention network can attend to the informative points of the input traces and suppresses the irrelevant points. Finally, a new visualization method, named Class Gradient Visualization (CGV) is proposed to recognize which points of the input traces have a positive influence on the predicted result of the neural networks.

Index Terms— cryptography, side-channel attack, convolutional neural network, attention mechanism, visualization

Minhui Jin, Mengce Zheng, Honggang Hu, Nenghai Yu
Key Laboratory of Electromagnetic Space Information, CAS
University of Science and Technology of China, CHINA

[Download]

Cite: Minhui Jin, Mengce Zheng, Honggang Hu, Nenghai Yu, "An Enhanced Convolutional Neural Network in Side-Channel Attacks and Visualization " Proceedings of 2020 the 10th International Workshop on Computer Science and Engineering (WCSE 2020), pp. 30-36, Shanghai, China, 19-21 June, 2020.