crta
Hrvatska znanstvena Sekcija img
bibliografija
3 gif
 Home
 About the project
 FAQ
 Contact
4 gif
Browsing
Basic search
Advanced search
Statistical data
Other bibliographies
Similar projects
 Catalogues and databases

Bibliographic record number: 877196

Journal

Authors: Picek, Stjepan; Heuser, Annelie; Jović, Alan; Ludwig, Simone A.; Guilley, Sylvain; Jakobović, Domagoj; Mentens, Nele
Title: Side-Channel Analysis and Machine Learning: A Practical Perspective
( Side-Channel Analysis and Machine Learning: A Practical Perspective )
Source: Proceedings of the International Joint Conference on Neural NetworksAnchorage : The Printing House, Inc, IEEE , 2017. 4095-4102 (ISBN: 978-1-5090-6181-5).
Meeting: IEEE International Joint Conference on Neural Networks (IJCNN)
Location and date: Anchorage, Aljaska, SAD, 14.-19.05.2017.
Keywords: side-channel analysis ; machine learning techniques ; profiling ; parameter tuning ; data mining
( side-channel analysis ; machine learning techniques ; profiling ; parameter tuning ; data mining )
Abstract:
The field of side-channel analysis has made significant progress over time. Side-channel analysis is now used in practice in design companies as well as in test laboratories, and the security of products against side-channel attacks has significantly improved. However, there are still some remaining issues to be solved for side-channel analysis to become more effective. Side-channel analysis consists of two steps, commonly referred to as identification and exploitation. The identification consists of understanding the leakage and building suitable models. The exploitation consists of using the identified leakage models to extract the secret key. In scenarios where the model is poorly known, it can be approximated in a profiling phase. There, machine learning techniques are gaining value. In this paper, we conduct extensive analysis of several machine learning techniques, showing the importance of proper parameter tuning and training. In contrast to what is perceived as common knowledge in unrestricted scenarios, we show that some machine learning techniques can significantly outperform template attacks when properly used. We therefore stress that the traditional worst case security assessment of cryptographic implementations, that mainly includes template attacks, might not be accurate enough. Besides that, we present a new measure called the Data Confusion Factor that can be used to assess how well machine learning techniques will perform on a certain dataset.
Type of meeting: Predavanje
Type of presentation in a journal: Full-text (1500 words and more)
Type of peer-review: International peer-review
Project / theme: HRZZ-IP-2014-09-4882
Original language: eng
Category: Znanstveni
Research fields:
Computer science
Full paper text: 877196.IJCNN2017_final.pdf (tekst priložen 18. Srp. 2017. u 08:19 sati)
URL: http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7958416
Contrib. to CROSBI by: Alan Jović (Alan.Jovic@irb.hr), 25. Svi. 2017. u 11:34 sati



Print version   za tiskati


upomoc
foot_4