Electromagnetic side_channel attack based on PSO Directed Acyclic Graph SVM

doi:10.1016/S1005-8885(15)60674-4

Acta Metallurgica Sinica(English letters) ›› 2015, Vol. 22 ›› Issue (5): 10-15.doi: 10.1016/S1005-8885(15)60674-4

• Wireless • Previous Articles Next Articles

Electromagnetic side_channel attack based on PSO Directed Acyclic Graph SVM

1. School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China 2. School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454000, China 3. Institute of North Electronic Equipment, Beijing 100191,China 4. School of Opto-electronic Information Science and Technology, Yantai University, Yantai 264005, China

Received:2015-04-13 Revised:2015-09-20 Online:2015-10-30 Published:2015-10-30
Contact: Zhang Hongxin E-mail:hongxinzhang@263.net
Supported by:
The work was supported by the National Natural Science Foundation of China (61571063, 61202399, 61171051).

Abstract

Abstract:

Machine learning has a powerful potential for performing the template attack (TA) of cryptographic device. To improve the accuracy and time consuming of electromagnetic template attack (ETA), a multi-class directed acyclic graph support vector machine (DAGSVM) method is proposed to predict the Hamming weight of the key. The method needs to generate K(K 1)/2 binary support vector machine (SVM) classifiers and realizes the K-class prediction using a rooted binary directed acyclic graph (DAG) testing model. Further, particle swarm optimization (PSO) is used for optimal selection of DAGSVM model parameters to improve the performance of DAGSVM. By exploiting the electromagnetic emanations captured while a chip was implementing the RC4 algorithm in software, the computation complexity and performance of several multi-class machine learning methods, such as DAGSVM, one-versus-one (OVO)SVM, one-versus-all (OVA)SVM, Probabilistic neural networks (PNN), K-means clustering and fuzzy neural network (FNN) are investigated. In the same scenario, the highest classification accuracy of Hamming weight for the key reached 100%, 95.33%, 85%, 74%, 49.67% and 38% for DAGSVM, OVOSVM, OVASVM, PNN, K-means and FNN, respectively. The experiment results demonstrate the proposed model performs higher predictive accuracy and faster convergence speed.

Key words:

directed acyclic graph support vector machine (DAGSVM)|particle swarm optimization (PSO)|side-channel attack|electromagnetic emanations

CLC Number:

References

1. Standaert F X, Koeune F, Schindler W. How to compare profiled side-channel attacks? Proceedings of the 7th International Workshop on Applied Cryptography and Network Security (ACNS’09), Jun 2-5, 2009, Paris, France. LNCS 5536. Heidelberg, Germany: Springer, 2009: 485-498

2. Chari S, Rao J R, Rohatgi P. Template attacks. Proceedings of the 4th International Workshop on Cryptographic Hardware and Embedded Systems (CHES’02), Aug 13-15, 2002, Redwood Shores, CA, USA. LNCS 2523. Berlin, Germany: Springer-Verlag, 2002:172-186

3. Hospodar G, Mulder E D, Gierlichs B, et al. Least squares support vector machines for side-channel analysis. Darmstadt, Germany: CASED (Center for Advanced Security Research Darmstadt), 2011: 99-104

4. Hospodar G, Gierlichs B, De Mulder E, et al. Machine learning in side-channel analysis: A first study. Journal of Cryptographic Engineering, 2011,1(4): 293-302

5. Martinasek Z, Zeman V. Innovative method of the power analysis. Radioengineering, 2013, 22(2): 17-20

6. Zeng Z, Gu D W, Liu J R, et al. An improved side-channel attack based on support vector machine. Proceedings of the 10th International Conference of Computational Intelligence and Security (CIS’14), Sept 21-25, 2014, Kunming, China. Piscataway, NJ, USA: IEEE, 2014: 676-680

7. Gandolfi K, Mourtel C, Olivier F. Electromagnetic analysis: Concrete results. Proceedings of the 3rd International Workshop on Cryptographic Hardware and Embedded Systems (CHES’01), May 14-16, 2001, Paris, France. LNCS 2162. Berlin, Germany: Springer-Verlag, 2001: 251-261

8. Wu Q, Fan J L. Smooth support vector machine based on piecewise function. Journal of China Universities of Posts and Telecommunications, 2013, 20(5): 122-128

9. Liu C C, Chuang K W. An outdoor time scenes simulation scheme based on support vector regression with radial basis function on DCT domain. Image and Vision Computing, 2009, 27(10): 1626-1636

10. Wen X X, Meng X R. Network health evaluation based on SVM and cloud model. Journal of Beijing University of Posts and Telecommunications, 2012, 35(1): 10-14 (in Chinese)

11. Zhao Z C. Combining SVM and CHMM classifiers for porno video recognition. Journal of China Universities of Posts and Telecommunications, 2012, 19(3): 100-106

12. Li H. Statistical learning method. Beijing, China: Tsinghua University Press, 2012: 95-115 (in Chinese)

13. Wang T H, Zhao D Y, Feng Y S. Two-stage multiple kernel learning with multiclass kernel polarization. Knowledge-Based Systems, 2013, 48: 10-16

14. Lee Y, Lee J. Binary tree optimization using genetic algorithm for multiclass support vector machine. Expert Systems with Applications, 2015, 42(8): 3843-3851

15. Barbieri R, Barbieri N, de Lima K F. Some applications of the PSO for optimization of acoustic filters. Applied Acoustics, 2015, 89: 62-70

16. Guo S Z, Wang T, Zhao X J. Principles and methodologies of side-channel analysis in cryptography. Beijing, China: Science Press, 2014: 76-92 (in Chinese)

Metrics

Comments

Copyright © 2020 The Journal of China Universities of Posts and Telecommunications
　 Adress: P.O. Box 231,Beijing University of Posts and Telecommunications,10 Xi Tucheng Road,Beijing 100876,P.R.China　Post Code: 100081
Tel：86-010-62282493　Fax： 86-010-62283461　E-mail: jchupt@bupt.edu.cn
Support by: Beijing Magtech Co.Ltd

Electromagnetic side_channel attack based on PSO Directed Acyclic Graph SVM

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 1

Recommended Articles

Metrics

Comments