Paper 2021/959

The Best of Two Worlds: Deep Learning-assisted Template Attack

Lichao Wu and Guilherme Perin and Stjepan Picek

Abstract

In the last decade, machine learning-based side-channel attacks became a standard option when investigating profiling side-channel attacks. At the same time, the previous state-of-the-art technique, template attack, started losing its importance and was more considered a baseline to compare against. As such, most of the results reported that machine learning (and especially deep learning) could significantly outperform the template attack. This does not mean the template attack does not have certain advantages even when compared to deep learning. The most significant one is that it does not have any hyperparameters to tune, making it easier to use. We take another look at the template attack, and we devise a feature engineering phase allowing template attacks to compete or even outperform state-of-the-art deep learning-based side-channel attacks. More precisely, we show how a deep learning technique called the triplet model can be used to find highly efficient embeddings of input data, which can then be fed into the template attack resulting in powerful attacks.