Shift-invariance Robustness of Convolutional Neural Networks in Side-channel Analysis

ePrint Report: Shift-invariance Robustness of Convolutional Neural Networks in Side-channel Analysis

Marina Krček, Lichao Wu, Guilherme Perin, Stjepan Picek

Convolutional neural networks (CNNs) offer unrivaled performance in profiling side-channel analysis. This claim is corroborated by numerous results where CNNs break targets protected with masking and hiding countermeasures. One hiding countermeasure is commonly investigated in related works - desynchronization (misalignment). The conclusions usually state that CNNs can break desynchronization as they are shift-invariant. This paper investigates that claim in more detail …

analysis channel claim cnns countermeasures eprint report masking networks neural networks offer performance profiling report results robustness side-channel