LeaX: Class-Focused Explanations for Locating Leakage in Learning-based Profiling Attacks
Abstract
Machine learning can significantly improve power side-channel attacks that derive cryptographic keys from hardware devices. The attacker learns a model that maps side-channel information (e.g., a device’s power consumption) to the computation’s intermediate states/values, which in turn serve as evidence for the actual key. The model implicitly learns which portions of the power traces leak information and which are mere noise. This knowledge is of great interest to the designer of the cryptographic hardware. Knowing the “leakage points” allows them to tweak the implementation to prevent the leakage. The community has thus investigated the use of “Explainable AI” (XAI) to derive the machine-learning model’s knowledge about existing leakage. Unfortunately, with limited success for protected (masked) implementations as used in practice so far. We show that very much like for a side-channel attack itself, model analysis using XAI must focus on intermediate values rather than keys, accumulate evidence for all intermediates, and make an informed choice at the end. Doing so successfully, however, requires class-discriminative explanations—a fact overlooked up to now. We present a novel analysis method, LeaX, that uses this observation to precisely pinpoint leakage, especially for masked cryptographic implementations, which prior work has failed to do.
For further details please consult the conference publication. Also, please find more research on using XAI for computer security at https://xaisec.org.
Team
- Qi Lei
- Christian Wressnegger (Contact)
Publication
A detailed description of our work was presented at the 20th International Conference on Availability, Reliability and Security (ARES) in August 2025. If you would like to cite our work, please use the reference as provided below:
@InProceedings{Lei2025LeaX,
author = {Qi Lei and Christian Wressnegger},
booktitle = {Proc. of the 20th International Conference on Availability, Reliability and Security ({ARES})},
title = {{LeaX}: {C}lass-Focused Explanations for Locating Leakage in Learning-based Profiling Attacks},
year = 2025,
month = aug,
}