Neural network based attack on a masked implementation of AES

TLDR

Masked implementations of cryptographic algorithms are commonly used in commercial embedded devices to enhance resistance against side‑channel attacks. The study demonstrates that neural networks can recover both the mask and the secret key from a single attack trace, and proposes a PCA‑based preprocessing step to improve attack success. The attack employs neural networks trained on PCA‑processed traces from the publicly available DPA contest dataset, facilitating reproducibility. The resulting classifier accurately identifies the mask for each trace, effectively removing the mask’s protection and reducing the attack to that against an unprotected implementation, thereby showing robust and efficient side‑channel classification.

Abstract

Masked implementations of cryptographic algorithms are often used in commercial embedded cryptographic devices to increase their resistance to side channel attacks. In this work we show how neural networks can be used to both identify the mask value, and to subsequently identify the secret key value with a single attack trace with high probability. We propose the use of a pre-processing step using principal component analysis (PCA) to significantly increase the success of the attack. We have developed a classifier that can correctly identify the mask for each trace, hence removing the security provided by that mask and reducing the attack to being equivalent to an attack against an unprotected implementation. The attack is performed on the freely available differential power analysis (DPA) contest data set to allow our work to be easily reproducible. We show that neural networks allow for a robust and efficient classification in the context of side-channel attacks.