Exploiting the advantages of the multi-output multi-loss neural network can significantly enhance the performance of side-channel attacks in a non-profiled context.
Abstract:
Differential deep learning analysis (DDLA) is the first deep-learning-based nonprofiled side-channel attack (SCA) on embedded systems. However, DDLA requires many trainin...Show MoreMetadata
Abstract:
Differential deep learning analysis (DDLA) is the first deep-learning-based nonprofiled side-channel attack (SCA) on embedded systems. However, DDLA requires many training processes to distinguish the correct key. In this letter, we introduce a nonprofiled SCA technique using multi-output classification to mitigate the aforementioned issue. Specifically, a multi-output multilayer perceptron and a multi-output convolutional neural network are introduced against various SCA protected schemes, such as masking, noise generation, and trace de-synchronization countermeasures. The experimental results on different power side channel datasets have clarified that our model performs the attack up to 9–30 times faster than DDLA in the case of masking and de-synchronization countermeasures, respectively. In addition, regarding combined masking and noise generation countermeasure, our proposed model achieves a higher success rate of at least 20% in the cases of the standard deviation equal to 1.0 and 1.5.
Exploiting the advantages of the multi-output multi-loss neural network can significantly enhance the performance of side-channel attacks in a non-profiled context.
Published in: IEEE Embedded Systems Letters ( Volume: 15, Issue: 3, September 2023)