Multi-class SVMs analysis of side-channel information of elliptic curve cryptosystem

Ehsan Saeedi, Md Selim Hossain, Yinan Kong

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

7 Citations (Scopus)

Abstract

Cryptosystems, even after recent algorithmic improvements, can be vulnerable to side-channel attacks (SCA) In this paper, we investigate one of the powerful class of SCAs based on machine learning techniques in the forms of Principal Component Analysis (PCA) and multi-class classification. For this purpose, a support vector machine (SVM) is investigated as a robust and efficient multi-class classifier along with a propel kernel function and its appropriate parameters. Our experiment performed on data leakage of a FPGA implementation of elliptio curve cryptography (ECC), and the results, validated by cross validation approach, compare the efficiency of different kernel functions and the influence of function parameters.

Original languageEnglish
Title of host publication2015 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS)
EditorsMohammad S. Obaidat, Franco Davoli, Jose L Marzo, Joel Rodrigues, Malamati Louta, Imadeldin Mahgoub, Jose Saldana
Place of PublicationChicago, IL
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-6
Number of pages6
ISBN (Electronic)9781510810600
ISBN (Print)9781467373517
DOIs
Publication statusPublished - 2015
Event2015 International Symposium on Performance Evaluation of Computer and Telecommunication Systems, SPECTS 2015 - Chicago, United States
Duration: 26 Jul 201529 Jul 2015

Publication series

NameSimulation Series
PublisherThe Society for Modeling and Simulation International (SCS)
Number9
Volume47
ISSN (Print)0735-9276

Other

Other2015 International Symposium on Performance Evaluation of Computer and Telecommunication Systems, SPECTS 2015
Country/TerritoryUnited States
CityChicago
Period26/07/1529/07/15

Fingerprint

Dive into the research topics of 'Multi-class SVMs analysis of side-channel information of elliptic curve cryptosystem'. Together they form a unique fingerprint.

Cite this