Reverse-Analysis of S-Box for SM4-Like Algorithms Based on Side Channel Technology [基于深度学习的类SM4算法S盒逆向分析]

作者：Ma X.-L.; Li B.; Yang D.; Huang K.-Z.; Duan X.-Y.^*

来源：Journal of Beijing University of Posts and Telecommunications, 2020, 43(5): 118-124.

DOI：10.13190/j.jbupt.2020-034

• Deep learning
• Reverse analysis
• S box
• SM4-like algorithm

In the profiled scenario, the common method of reverse analysis is the template attack based on multi-Gaussian distribution. The article applies the concept of deep learning to the field of reverse analysis for the first time under the same conditions, and proposes an S-box reverse analysis algorithm based on deep learning. By selecting the deep learning algorithm, loss function and label design method suitable for side channel reverse analysis, an S-box reverse recovery experiment is conducted for SM4-like algorithm. It is shown that it is feasible to employ deep learning method to carry out S-box reverse analysis, which can have better performance comparing to template attack under certain circumstances. Moreover, the predicting effect of multi-layer perception algorithm surpasses that of convolutional neural network algorithm. ? 2020, Editorial Department of Journal of Beijing University of Posts and Telecommunications. All right reserved.

• 单位
  中国科学院大学