I Know What Your Layers Did: Layer-wise Explainability of Deep Learning Side-channel Analysis

ePrint Report: I Know What Your Layers Did: Layer-wise Explainability of Deep Learning Side-channel Analysis

Guilherme Perin, Lichao Wu, Stjepan Picek

Masked cryptographic implementations can be vulnerable to higher-order attacks. For instance, deep neural networks have proven effective for second-order profiling side-channel attacks even in a black-box setting (no prior knowledge of masks and implementation details). While such attacks have been successful, no explanations were provided for understanding why a variety of deep neural networks can (or cannot) learn high-order …

analysis channel deep learning eprint report side-channel