Broader but More Efficient: Broad Learning in Power Side-channel Attacks

Side-channel attacks (SCAs) seriously threaten the security of cryptographic hardwares and embedded systems, especially following the introduction of deep learning techniques, with their powerful feature extraction capability that enables attackers to analyze the key information more efficiently. However, deep learning models in side-channel attacks also face with the problems of excessive model complexity and long training time. In this paper, we introduce Broad Learning Systems (BLS) to power side-channel attacks (SCAs) and then construct an efficient model of broad learning for power SCAs from the core of BLS. Then we optimize the model by making full use of the excellent features of incremental learning and feature extraction of BLS. Finally, we verify the effectiveness of the optimization model in diverse side-channel attack scenarios, achieving stable accuracy levels above 85% while significantly reducing time consumption compared to other models. This fully illustrates the superiority of our scheme.