Improving Side-channel Analysis through Semi-supervised Learning

The profiled side-channel analysis represents the most powerful category of side-channel attacks. In this context, the security evaluator (i.e., attacker) gains access to a profiling device to build a precise model that is used to attack another device in the attacking phase. Mostly, it is assumed that the attacker has significant capabilities in the profiling phase, whereas the attacking phase is very restricted. We step away from this assumption and consider an attacker restricted in the profiling phase, while the attacking phase is less limited. We propose the concept of semi-supervised learning for side-channel analysis, where the attacker uses a small number of labeled measurements from the profiling phase as well as the unlabeled measurements from the attacking phase to build a more reliable model. Our results show that the semi-supervised concept significantly helps the template attack (TA) and its pooled version (TAp). More specifically, for low noise scenario, the results for machine learning techniques and TA are often improved when only a small number of measurements is available in the profiling phase, while there is no significant difference in scenarios where the supervised set is large enough for reliable classification. For high noise scenarios, TAp and multilayer perceptron results are improved for the majority of inspected dataset sizes, while for high noise scenario with added countermeasures, we show a small improvement for TAp, Naive Bayes, and multilayer perceptron approaches for most inspected dataset sizes. Current results go in favor of using semi-supervised learning, especially the self-training approach, in side-channel attacks