Paper 2019/1474

Remove Some Noise: On Pre-processing of Side-channel Measurements with Autoencoders

Lichao Wu and Stjepan Picek

Abstract

In the profiled side-channel analysis, deep learning-based techniques proved to be very successful even when attacking targets protected with countermeasures. Still, there is no guarantee that deep learning attacks will always succeed. Various countermeasures make attacks significantly more complicated, and those countermeasures can be further combined to make the attacks even more challenging. An intuitive solution to improve the performance of attacks would be to reduce the effect of countermeasures. In this paper, we investigate whether we can consider certain types of hiding countermeasures as noise and then use a deep learning technique called the denoising autoencoder to remove that noise. We conduct a detailed analysis of five different types of noise and countermeasures either separately or combined and show that in all scenarios, denoising autoencoder improves the attack performance significantly.