Train Wisely: Multifidelity Bayesian Optimization Hyperparameter Tuning in Side-Channel Analysis

Trevor Yap Hong Eng; Shivam Bhasin; Léo Weissbart

Paper 2024/170

Train Wisely: Multifidelity Bayesian Optimization Hyperparameter Tuning in Side-Channel Analysis

Trevor Yap Hong Eng

, School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore, Temasek Laboratories, Nanyang Technological University, Singapore

Shivam Bhasin

, Temasek Laboratories, Nanyang Technological University, Singapore

Léo Weissbart

, Radboud University, Nijmegen, Netherlands

Abstract

Side-Channel Analysis (SCA) is critical in evaluating the security of cryptographic implementations. The search for hyperparameters poses a significant challenge, especially when resources are limited. In this work, we explore the efficacy of a multifidelity optimization technique known as BOHB in SCA. In addition, we proposed a new objective function called , which could be incorporated into any Bayesian Optimization used in SCA. We show the capabilities of both BOHB and on four different public datasets. Specifically, BOHB could obtain the least number of traces in CTF2018 when trained in the Hamming weight and identity leakage model. Notably, this marks the first reported successful recovery of the key for the identity leakage model in CTF2018.

Metadata

Available format(s): PDF
Category: Implementation
Publication info: Published elsewhere. Selected Areas in Cryptography 2024
Keywords: Side-channel Neural Network Deep Learning Profiling attack Hyperparameter Search
Contact author(s): trevor yap @ ntu edu sg
sbhasin @ ntu edu sg
l weissbart @ cs ru nl
History: 2024-10-29: revised; 2024-02-05: received; See all versions
Short URL: https://ia.cr/2024/170
License: CC BY

BibTeX

@misc{cryptoeprint:2024/170,
      author = {Trevor Yap Hong Eng and Shivam Bhasin and Léo Weissbart},
      title = {Train Wisely: Multifidelity Bayesian Optimization Hyperparameter Tuning in Side-Channel Analysis},
      howpublished = {Cryptology {ePrint} Archive, Paper 2024/170},
      year = {2024},
      url = {https://eprint.iacr.org/2024/170}
}