Machine-learning assisted side-channel attacks on RNS ECC implementations using hybrid feature engineering

Naila Mukhtar, Louiza Papachristodoulou*, Apostolos P. Fournaris, Lejla Batina, Yinan Kong

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

3 Citations (Scopus)

Abstract

Machine learning-based side-channel attacks have recently been introduced to recover the secret information from protected software and hardware implementations. Limited research exists for public-key algorithms, especially on non-traditional implementations like those using Residue Number System (RNS). Template attacks were proven successful on RNS-based Elliptic Curve Cryptography (ECC), only if the aligned portion is used for templates. In this study, we present a systematic methodology for the evaluation of ECC cryptosystems with and without countermeasures (both RNS-based and traditional ones) against ML-based side-channel attacks using two attack models on full length aligned and unaligned leakages. RNS-based ECC datasets are evaluated using four machine learning classifiers and comparison is provided with existing state-of-the-art template attacks. Moreover, we analyze the impact of raw features and advanced hybrid feature engineering techniques. We discuss the metrics and procedures that can be used for accurate classification on the imbalanced datasets. The experimental results demonstrate that, for ECC RNS datasets, the efficiency of simple machine learning algorithms is better than the complex deep learning techniques when such datasets are limited in size. This is the first study presenting a complete methodology for ML side-channel attacks on public key algorithms.

Original languageEnglish
Title of host publicationConstructive side-channel analysis and secure design
Subtitle of host publication13th International Workshop, COSADE 2022, Leuven, Belgium, April 11-12, 2022, proceedings
EditorsJosep Balasch, Colin O'Flynn
Place of PublicationCham, Switzerland
PublisherSpringer, Springer Nature
Pages3-28
Number of pages26
ISBN (Electronic)9783030997663
ISBN (Print)9783030997656
DOIs
Publication statusPublished - 2022
Event13th International Workshop on Constructive Side-Channel Analysis and Secure Design, COSADE 2022 - Leuven, Belgium
Duration: 11 Apr 202212 Apr 2022

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume13211
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference13th International Workshop on Constructive Side-Channel Analysis and Secure Design, COSADE 2022
Country/TerritoryBelgium
CityLeuven
Period11/04/2212/04/22

Keywords

  • Elliptic curve cryptography
  • Side-channel attacks
  • Machine learning
  • Feature engineering

Fingerprint

Dive into the research topics of 'Machine-learning assisted side-channel attacks on RNS ECC implementations using hybrid feature engineering'. Together they form a unique fingerprint.

Cite this