Power analysis attack: an approach based on machine learning

Lerman, Liran; Bontempi, Gianluca; Markowitch, Olivier

doi:10.1504/ijact.2014.062722

Cited by 113 publications

(86 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The stochastic approach exploiting Linear Regression (LR) is a frequently considered alternative [22]. More recently, solutions relying on Machine Learning (ML) have also been investigated [2,11,13,12,16,17,19]. These previous works support the claim that ML-based attacks are effective and lead to successful key recoveries.…”

Section: Introductionmentioning

confidence: 97%

Template Attacks vs. Machine Learning Revisited (and the Curse of Dimensionality in Side-Channel Analysis)

Lerman

Poussier

Bontempi

et al. 2015

Constructive Side-Channel Analysis and Secure Design

Self Cite

View full text Add to dashboard Cite

Abstract. Template attacks and machine learning are two popular approaches to profiled side-channel analysis. In this paper, we aim to contribute to the understanding of their respective strengths and weaknesses, with a particular focus on their curse of dimensionality. For this purpose, we take advantage of a well-controlled simulated experimental setting in order to put forward two important intuitions. First and from a theoretical point of view, the data complexity of template attacks is not sensitive to the dimension increase in side-channel traces given that their profiling is perfect. Second and from a practical point of view, concrete attacks are always affected by (estimation and assumption) errors during profiling. As these errors increase, machine learning gains interest compared to template attacks, especially when based on random forests.

show abstract

Section: Introductionmentioning

confidence: 97%

Template Attacks vs. Machine Learning Revisited (and the Curse of Dimensionality in Side-Channel Analysis)

Lerman

Poussier

Bontempi

et al. 2015

Constructive Side-Channel Analysis and Secure Design

Self Cite

View full text Add to dashboard Cite

show abstract

“…Yang et al [37] proposed MLP in order to create a power consumption model of a cryptographic device in CPA. Lerman et al [38], [39] compared a template attack with a binary machine learning approach, based on non-parametric methods.…”

Section: Related Workmentioning

confidence: 99%

k-Nearest Neighbors Algorithm in Profiling Power Analysis Attacks

Malina¹,

Zeman²,

Martinasek³

et al. 2016

RADIOENGINEERING

View full text Add to dashboard Cite

show abstract

“…putIntoCluster(trace, clusters, manipInst) 7: end for 8: HW = prediction(attacked trace, clusters, manipInst) 9: byteV alue = recoverKey(HW ) {enumeration by brute force} Lerman et al [11] and Hospodar et al [8] discussed the role of machine learning in TA. They showed that a machine learning procedure is able to outperform conventional TA.…”

Section: Algorithm 1 Ssta Algorithm: Pseudo-codementioning

confidence: 99%

Semi-Supervised Template Attack

Lerman

Medeiros

Veshchikov

et al. 2013

Constructive Side-Channel Analysis and Secure Design

Self Cite

View full text Add to dashboard Cite

Abstract. Side channel attacks take advantage of the information leakage in a cryptographic device. A template attack is a family of side channel attacks which is reputed to be extremely effective. This kind of attacks supposes that the attacker can fully control a cryptographic device before attacking a similar one. In this paper, we propose a method based on a semi-supervised learning strategy to relax this assumption. The effectiveness of our proposal is confirmed by software simulations as well as by experiments on a 8-bit microcontroller.

show abstract

Power analysis attack: an approach based on machine learning

Cited by 113 publications

References 32 publications

Template Attacks vs. Machine Learning Revisited (and the Curse of Dimensionality in Side-Channel Analysis)

Template Attacks vs. Machine Learning Revisited (and the Curse of Dimensionality in Side-Channel Analysis)

k-Nearest Neighbors Algorithm in Profiling Power Analysis Attacks

Semi-Supervised Template Attack

Contact Info

Product

Resources

About