OccPoIs: Points of Interest based on Neural Network's Key Recovery in Side-Channel Analysis through Occlusion

ePrint Report: OccPoIs: Points of Interest based on Neural Network's Key Recovery in Side-Channel Analysis through Occlusion

Trevor Yap, Shivam Bhasin, Stjepan Picek

Deep neural networks (DNNs) represent a powerful technique for assessing cryptographic security concerning side-channel analysis (SCA) due to their ability to aggregate leakages automatically, rendering attacks more efficient without preprocessing. Nevertheless, despite their effectiveness, DNNs employed in SCA are predominantly black-box algorithms, posing considerable interpretability challenges.
In this paper, we propose a novel technique called Key Guessing …

analysis channel cryptographic security eprint report interest key network networks neural network neural networks recovery report sca security side-channel