TY - GEN
T1 - Machine-learning assisted side-channel attacks on RNS ECC implementations using hybrid feature engineering
AU - Mukhtar, Naila
AU - Papachristodoulou, Louiza
AU - Fournaris, Apostolos P.
AU - Batina, Lejla
AU - Kong, Yinan
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Elliptic curve cryptography
KW - Side-channel attacks
KW - Machine learning
KW - Feature engineering
UR - http://www.scopus.com/inward/record.url?scp=85127632021&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-99766-3_1
DO - 10.1007/978-3-030-99766-3_1
M3 - Conference proceeding contribution
AN - SCOPUS:85127632021
SN - 9783030997656
T3 - Lecture Notes in Computer Science
SP - 3
EP - 28
BT - Constructive side-channel analysis and secure design
A2 - Balasch, Josep
A2 - O'Flynn, Colin
PB - Springer, Springer Nature
CY - Cham, Switzerland
T2 - 13th International Workshop on Constructive Side-Channel Analysis and Secure Design, COSADE 2022
Y2 - 11 April 2022 through 12 April 2022
ER -