• search hit 1 of 1
Back to Result List

Efficient Template Attacks Based on Probabilistic Multi-class Support Vector Machines

  • Common template attacks are probabilistic relying on the multivariate Gaussian distribution regarding the noise of the device under attack. Though this is a realistic assumption, numerical problems are likely to occur in practice due to evaluation in higher dimensions. To avoid this, a feature selection is applied to identify points in time that contribute most information to an attack. An alternative to common template attacks is to apply machine learning in form of support vector machines (SVMs). Recent works brought out approaches that produce comparable results, respectively better in the presence of noise, but still not optimal in terms of efficiency and performance. In this work we show how to adapt the SVM template approach in order to considerably reduce the effort while carrying out the attack and how to better exploit the side-channel information under the assumption of an attack model with a strict order, e.g. Hamming weight model.

Export metadata

Additional Services

Share in Twitter Search Google Scholar Availability
Metadaten
Document Type:Conference Object
Language:English
Author:Timo Bartkewitz, Kerstin Lemke-Rust
Parent Title (English):Smart Card Research and Advanced Applications. 11th International Conference (CARDIS 2012). Graz, Austria, November 28-30, 2012. Revised Selected Papers
First Page:263
Last Page:276
ISBN:978-3-642-37287-2
DOI:https://doi.org/10.1007/978-3-642-37288-9_18
Publication year:2013
Tag:Machine Learning; Power Analysis; Support Vector Machine; Template Attacks
Departments, institutes and facilities:Fachbereich Informatik
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Entry in this database:2015/04/02