Statistical Analysis and Comparison of Linear Regression Attacks on the Advanced Encryption Standard

Author(s)

Hiren J. Patel, Air Force Institute of Technology
Christine Schubert-Kabban, Air Force Institute of Technology
Rusty O. Baldwin, University of DaytonFollow
David P. Montminy, Air Force Institute of Technology

Document Type

Article

Publication Date

2015

Publication Source

International Journal of Information and Communication Technology

Abstract

This research investigates profiled linear regression-based attacks for extracting the advanced encryption standard (AES) secret key. Several methods from recent advancements are compared for their capability to correctly build the multivariate distribution for profiling. Attack performance shows greater than 98% success rate with as few as 100 training and test traces. In 8 out of 9 test cases examined, linear regression attacks using the coefficient of determination R², adjusted coefficient of determination R²_a and correlation power analysis (CPA) performed better than or equal to the original stochastic attack and attack using the symmetry metric. Our new method using R²_a is proven to suppress unimportant variables and enhance important ones better than other methods. It is successful when the microcontrollers and data collection hardware differ between training and test phases and is found to be more effective in noisy environments than CPA.

Inclusive pages

159-184

ISBN/ISSN

1466-6642

Comments

Permission documentation on file.

Copyright

Copyright © 2015, Inderscience

Publisher

Inderscience

Volume

7

Peer Reviewed

yes

Issue

2-3

eCommons Citation

Patel, Hiren J.; Schubert-Kabban, Christine; Baldwin, Rusty O.; and Montminy, David P., "Statistical Analysis and Comparison of Linear Regression Attacks on the Advanced Encryption Standard" (2015). Computer Science Faculty Publications. 104.
https://ecommons.udayton.edu/cps_fac_pub/104