Back to Search Start Over

Enhancing an Embedded Processor Core for Efficient and Isolated Execution of Cryptographic Algorithms.

Authors :
YUMBUL, KAZIM
SAVAŞ, ERKAY
Source :
Computer Journal; Oct2015, Vol. 58 Issue 10, p2368-2387, 20p
Publication Year :
2015

Abstract

We propose enhancing a reconfigurable and extensible embedded reduced instruction set computer (RISC) processor core with a protected zone for isolated execution of cryptographic algorithms. The protected zone is a collection of processor subsystems such as functional units optimized for high-speed execution of integer operations, a small amount of local memory for storing sensitive data during cryptographic computations, and special-purpose and cryptographic registers to execute instructions securely. We outline the principles for secure software implementations of cryptographic algorithms in a processor equipped with the proposed protected zone.We demonstrate the efficiency and effectiveness of our proposed zone by implementing the most-commonly used cryptographic algorithms in the protected zone; namely RSA, elliptic curve cryptography, pairingbased cryptography, Advanced Encryption Standard (AES) block cipher, and secure hash algorithm (SHA)-1 and SHA-256 cryptographic hash functions. In terms of time efficiency, our software implementations of cryptographic algorithms running on the enhanced core compare favorably with equivalent software implementations on similar processors reported in the literature. The protected zone is designed in such a modular fashion that it can easily be integrated into any RISC processor. The proposed enhancements for the protected zone are realized on an field programmabel gate array (FPGA) device. The implementation results on the FPGA confirm that its area overhead is relatively moderate in the sense that it can be used in many embedded processors. Finally, the protected zone is useful against cold-boot and micro-architectural side-channel attacks such as cache-based and branch prediction attacks. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
00104620
Volume :
58
Issue :
10
Database :
Complementary Index
Journal :
Computer Journal
Publication Type :
Academic Journal
Accession number :
110012480
Full Text :
https://doi.org/10.1093/comjnl/bxu040