%0 Journal Article %A SONG Shijie %A CHEN Kaiyan %A ZHANG Yang %T Security Evaluation Framework of Deep Learning Side Channel Analysis from Information Entropy %D 2021 %R 10.3778/j.issn.1002-8331.2005-0221 %J Computer Engineering and Applications %P 138-146 %V 57 %N 17 %X

Deep Learning Side Channel Analysis/Attack(DLSCA)based on deep learning is very effective for decryption in various side channel attack scenarios. But DLSCA still has security evaluation problems. This paper is based on the power analysis of AES symmetric encryption algorithm, and explains the reason why traditional machine learning performance metrics such as Accuracy can not evaluate from information entropy. The key information is defined to find out the relationship between side channel security evaluation and the performance of the DNN model during a training phase. Associated with the key information, a DLSCA security evaluation framework is set up.

%U http://cea.ceaj.org/EN/10.3778/j.issn.1002-8331.2005-0221