Hoang, V. and Do, N. and Doan, V.S. (2022) Efficient Non-profiled Side Channel Attack Using Multi-output Classification Neural Network. IEEE Embedded Systems Letters. p. 1. ISSN 19430663
Full text not available from this repository. (Upload)Abstract
Differential Deep Learning Analysis (DDLA) is the first deep learning based non-profiled side-channel attack (SCA) on embedded systems. However, DDLA requires many training processes to distinguish the correct key. In this letter, we introduce a non-profiled SCA technique using multi-output classification to mitigate the aforementioned issue. Specifically, a multi-output multi-layer 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 and 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. IEEE
Item Type: | Article |
---|---|
Divisions: | Institutes > Institute of System Integration |
Identification Number: | 10.1109/LES.2022.3213443 |
Uncontrolled Keywords: | Computer architecture; deep learning; Deep learning; Embedded systems; embedded systems; multi-loss; multi-output; Neural networks; Proposals; Side channel attacks; Side-channel attacks; Training |
URI: | http://eprints.lqdtu.edu.vn/id/eprint/10575 |