Non-profiled Deep-Learning-Based Power Analysis of the SM4 and DES Algorithms

MA Xiangliang; LI Bing; WANG Hong; WU Di; ZHANG Lizhen; HUANG Kezhen; DUAN Xiaoyi

doi:10.1049/cje.2021.04.003

Volume 30 Issue 3

May 2021

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2021 > 30(3): 500-507

MA Xiangliang, LI Bing, WANG Hong, et al., “Non-profiled Deep-Learning-Based Power Analysis of the SM4 and DES Algorithms,” Chinese Journal of Electronics, vol. 30, no. 3, pp. 500-507, 2021, doi: 10.1049/cje.2021.04.003

Citation:

MA Xiangliang, LI Bing, WANG Hong, et al., “Non-profiled Deep-Learning-Based Power Analysis of the SM4 and DES Algorithms,” Chinese Journal of Electronics, vol. 30, no. 3, pp. 500-507, 2021, doi: 10.1049/cje.2021.04.003

Citation:

PDF( 5333 KB)

Non-profiled Deep-Learning-Based Power Analysis of the SM4 and DES Algorithms

doi: 10.1049/cje.2021.04.003

1. School of Integrated Circuits, Tsinghua University, Beijing 100084, China;
2. National Research Center for Information Technology Security, Beijing 100084, China;
3. China Cybersecurity Review Technology and Certification Center, Beijing 100020, China;
4. Trusted Computing and Information Assurance Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing 100190, China;
5. University of Chinese Academy of Sciences, Beijing 100049, China;
6. Department of Electronics and Information Engineering, Beijing Electronic Science and Technology Institute, Beijing 100070, China

Funds:

This work is supported by the National Key Research and Development Program of China(No.2018YFB0904901, No.2019QY1302), and National Natural Science Foundation of China (No.61802404).

Received Date: 2019-11-11

Abstract

Abstract

Power analysis methods are commonly used for evaluating the security of cryptographic devices. They are characteristically low-cost and display a high success rate and the ability to obtain important device information, e.g., keys. Given the current wide application of deep-learning technology, there is a growing tendency to incorporate power-analysis technology in development. This study investigates non-profiled deep-learning-based power analysis. The labels used in this attack are uncertain, and the attack conditions required are greatly reduced. We choose the Recurrent neural network (RNN), multilayer perceptron, and convolutional neural network algorithms, which use the same network structure, to recover the keys for the SM4 software and DES hardware implementations. We propose combining the RNN algorithm with power analysis, and validate the benefits experimentally. The experimental results show that they all successfully recover the correct key for the SM4 software implementation, although the RNN algorithm by itself achieves a better effect. This conclusion also applies to attacks on the DES hardware implementation but is limited to labels based on the bit model.
- Non-profiled deep learning,
- Power analysis,
- SM4,
- DES,
- Key recovery

FullText(HTML)

References(13)

References

P.C Kocher, J.Jaffe and B.Jun, “Differential power analysis”, Proc. of 19th Annual International Cryptology Conference, Santa Barbara, California, USA, pp.388–397, 1999.

D.D Lin and T.j Cao, Applied Cryptography, Beijing: Science Press, China, pp.63–73, 2009.

X.L Ma, H Wang, B Li, et al., “A power analysis method against backdoor instruction in chips”, Acta Electronica Sinica, Vol.47, No.3, pp.686–691, 2019.

X.L Ma, B Li, W X, et al., “Reverse-analysis of S-box for GIFT-like algorithms based on independent component analysis technology”, Journal of Computer Research and Development, Vol.55, No.10, pp.177–185, 2018.

T. Benjamin, “Non-profiled deep learning-based side-channel attacks”, https://eprint.iacr.org/2018/196, 2018-2-18.

L Zhang and W.L Wu, “Differential fault analysis on SMS4”, Chinese Journal of Computers, Vol.29, No.9, pp.1596–1602, 2006.

L Lerman, G Bontempi and O Markowitch, “A machine learning approach against a masked AES”, Journal of Cryptographic Engineering, Vol.5, No.2, pp.123–139, 2014.

H.Maghrebi, T.Portigliatti and E.Prouff, “Breaking cryptographic implementations using deep learning techniques”, International Conference on Security, Privacy, and Applied Cryptography Engineering, Springer, Cham, pp.3–26, 2016.

E.Cagli, C.Dumas and E.Prouff, “Convolutional neural networks with data augmentation against jitter-based countermeasures”, Proc. of Cryptographic Hardware and Embedded Systems – CHES 2017, Taipei, China, pp.45–68, 2017.

B.Timon, “Non-profiled deep learning-based side-channel attacks with sensitivity analysis”, IACR Transactions on Cryptographic Hardware and Embedded Systems, Vol.2019, No.2, pp.107–131, 2019.

S.Chari, J.R Rao and P.Rohatgi, “Template attacks”, Proc. of Cryptographic Hardware and Embedded Systems – CHES 2002, San Francisco, USA, pp.13–28, 2002.

P.Emmanuel, S.Remi and B.Ryad, “Study of deep learning techniques for side-channel analysis and introduction to ascad database”, https://eprint.iacr.org/2018/196, 2020-6-4.

B. Shuai, Z. Zuo, G. Wang, et al., “Dag-recurrent neural networks for scene labeling”, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp.3620–3629, 2016.

Relative Articles

Supplements(0)

Cited By

Proportional views