Intra-class CutMix data augmentation based deep learning side channel attacks

Abstract

CutMix data augmentation can provide a large amount of augmented data for DL-SCA (deep learning side channel attacks) by generating new power traces. However, traces generated by CutMix may lose dependency with the new label, which may reduce the accuracy of the training model. In light of this, we propose an improved intra-class CutMix data augmentation method. Firstly, the original traces are classified by the label. Then, the original traces are selected by the same label constraint to generate new traces according to CutMix, which can ensure the dependency between the generated trace and its label. Furthermore, in order to maintain balance among different classified datasets, the traces are generated sequentially according to distinct labels. Finally, based on the augmented traces, the Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN) models can be constructed and trained to recover the key of AES. In order to verify the effectiveness of the proposed method, we conduct experimental evaluations using the MLP and CNN models based on DPA-contest v4 dataset and ASCAD dataset. The test results show that the traces generated with the intra-class CutMix method can be very similar to the original traces, and the MLP and CNN models can be effectively trained based on the generated traces to recover the key of AES. Besides, compared with existing data augmentation methods, the proposed method can complete secret key recovery with faster convergence and fewer traces.