Towards Private Deep Learning-Based Side-Channel Analysis Using Homomorphic Encryption Opportunities and Limitations

被引：2

作者：

Schmid, Fabian ^{[1
]}

Mukherjee, Shibam ^{[1
,5
]}

Picek, Stjepan ^{[2
]}

Stoettinger, Marc ^{[3
]}

De Santis, Fabrizio ^{[4
]}

Rechberger, Christian ^{[1
]}

机构：

[1] Graz Univ Technol, Graz, Austria

[2] Radboud Univ Nijmegen, Nijmegen, Netherlands

[3] RheinMain Univ Appl Sci, Wiesbaden, Germany

[4] Siemens AG, Munich, Germany

[5] Know Ctr GmbH, Graz, Austria

来源：

CONSTRUCTIVE SIDE-CHANNEL ANALYSIS AND SECURE DESIGN, COSADE 2024 | 2024年 / 14595卷

关键词：

Side-channel Analysis; Deep Learning; Neural Networks; Homomorphic Encryption; Private AI;

D O I：

10.1007/978-3-031-57543-3_8

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This work investigates using Homomorphic Encryption (HE) to assist the security evaluation of cryptographic devices without revealing side-channel information. For the first time, we evaluate the feasibility of execution of deep learning-based side-channel analysis on standard server equipment using an adapted HE protocol. By examining accuracy and execution time, it demonstrates the successful application of private SCA on both unprotected and protected cryptographic implementations. This contribution is a first step towards confidential side-channel analysis. Our study is limited to the honest-but-curious trust model, where we could reconstruct the secret of an unprotected AES implementation in seconds and of a masked AES implementation in under 17 min.

引用

页码：133 / 154

页数：22

共 48 条

[1] Deep Learning with Differential Privacy
Abadi, Martin
Chu, Andy
Goodfellow, Ian
McMahan, H. Brendan
Mironov, Ilya
Talwar, Kunal
Zhang, Li
[J]. CCS'16: PROCEEDINGS OF THE 2016 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2016, : 308 - 318
[2] Al Badawi A, 2019, Arxiv, DOI arXiv:1908.06972
[3] Albrecht M.R., 2019, Tech. Paper 2019/939, P939
[4] On the concrete hardness of Learning with Errors
Albrecht, Martin R.
Player, Rachel
Scott, Sam
[J]. JOURNAL OF MATHEMATICAL CRYPTOLOGY, 2015, 9 (03) : 169 - 203
[5] [Anonymous], 2023, Microsoft SEAL (release 4.1)
[6] Barker E, 2016, Recommendation for Key Management, Part 1: General., DOI [DOI 10.6028/NIST.SP.800-57PT1R4, 10.6028/NIST.SP.800-57pt1r4., 10.6028/NIST.SP.800-57pt1r4]
[7] Brakerski Zvika, 2014, ACM Transactions on Computation Theory, V6, DOI 10.1145/2633600
[8] Fully Homomorphic Encryption without Modulus Switching from Classical GapSVP
Brakerski, Zvika
[J]. ADVANCES IN CRYPTOLOGY - CRYPTO 2012, 2012, 7417 : 868 - 886
[9] Bursztein E., 2023, Generic attacks against cryptographic hardware through long-range deep learning
[10] Convolutional Neural Networks with Data Augmentation Against Jitter-Based Countermeasures Profiling Attacks Without Pre-processing
Cagli, Eleonora
Dumas, Cecile
Prouff, Emmanuel
[J]. CRYPTOGRAPHIC HARDWARE AND EMBEDDED SYSTEMS - CHES 2017, 2017, 10529 : 45 - 68

← 1 2 3 4 5 →