Peek into the Black-Box: Interpretable Neural Network using SAT Equations in Side-Channel Analysis

ePrint Report: Peek into the Black-Box: Interpretable Neural Network using SAT Equations in Side-Channel Analysis

Trevor Yap, Adrien Benamira, Shivam Bhasin, Thomas Peyrin

Deep neural networks (DNN) have become a significant threat to the security of cryptographic implementations with regards to side-channel analysis (SCA), as they automatically combine the leakages without any preprocessing needed, leading to a more efficient attack. However, these DNNs for SCA remain mostly black-box algorithms that are very difficult to interpret. Benamira \textit{et al.} recently proposed …

analysis box channel eprint report network neural network sat side-channel