Browse > Article
http://dx.doi.org/10.13089/JKIISC.2020.30.6.1271

Robust Deep Learning-Based Profiling Side-Channel Analysis for Jitter  

Kim, Ju-Hwan (Department of Mathematics, Kookmin University)
Woo, Ji-Eun (Department of Information Security, Cryptology, and Mathematics, Kookmin University)
Park, So-Yeon (Department of Information Security, Cryptology, and Mathematics, Kookmin University)
Kim, Soo-Jin (Department of Information Security, Cryptology, and Mathematics, Kookmin University)
Han, Dong-Guk (Department of Financial Information Security, Kookmin University)
Publication Information
Journal of the Korea Institute of Information Security & Cryptology / v.30, no.6, 2020 , pp. 1271-1278 More about this Journal
Abstract
Deep learning-based profiling side-channel analysis is a powerful analysis method that utilizes the neural network to profile the relationship between the side-channel information and the intermediate value. Since the neural network interprets each point of the signal in a different dimension, jitter makes it much hard that the neural network with dimension-wise weights learns the relationship. This paper shows that replacing the fully-connected layer of the traditional CNN (Convolutional Neural Network) with global average pooling (GAP) allows us to design the inherently robust neural network inherently for jitter. We experimented with the ChipWhisperer-Lite board to demonstrate the proposed method: as a result, the validation accuracy of the CNN with a fully-connected layer was only up to 1.4%; contrastively, the validation accuracy of the CNN with GAP was very high at up to 41.7%.
Keywords
Side-Channel Analysis; Deep Learning; Jitter; Global Average Pooling; AES;
Citations & Related Records
연도 인용수 순위
  • Reference
1 S. Chari, J. R. Rao, and P. Rohatgi, "Template attacks," Cryptographic Hardware and Embedded Systems, CHES 2002, LNCS 2523, pp. 13-28, Aug. 2002.
2 W. Shindler, K. Lemke, and C. Paar, "A stochastic model for differential side channel cryptanalysis," Cryptographic Hardware and Embedded Systems, CHES 2005, LNCS 3659, pp. 30-46, Aug. 2005.
3 G. Hospodar, B. Gierlichs, E. D. Mulder, I. Verbaushede, and J. Vandewalle, "Machine learning in side-channel analysis: a first study," Journal of Cryptographic Engineering, pp. 293-302, Oct. 2011.   DOI
4 L. Lerman, R. Poussier, G. Bontempi, O. Markowitch, and F. X. Standaert, "Template attacks versus machine learning revisited and the curse of dimensionality in side-channel analysis," Journal of Cryptographic Engineering, pp. 301-313, Apr. 2017.
5 L. Lerman, G. Bontempi, and O. Markowitch, "A machine learning approach against a masked AES," Journal of Cryptographic Engineering, pp. 123-139, Jun. 2015.
6 K. Hornik, M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural Networks, pp. 359-366, Mar. 1989.
7 F. Rosenblatt, Principles of neurodynamics: perceptrons and the theory of brain mechanisms, Spartan books, Mar. 1961.
8 Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.   DOI
9 L. Wouters, V. Arribas, B. Gierlichs, and Bart Preneel, "Revisiting a methodology for efficient CNN architectures in profiling attacks," Transactions on Cryptographic Hardware and Embedded Systems, TCHES, pp. 147-168, Jun. 2020.
10 J. Kim, S. Kim, J. Woo, S. Park, and D. Han, "Deep learning-based side-channel analysis method with resistance to jitter," Korea Information Processing Society Conference, pp. 180-183, May. 2020.
11 M. Lin, Q. Chen, and S. Yan, "Network In Network," 2nd International Conference on Learning Representations, ICLR, Jul. 2014.
12 F. Standaert, T. Malkin, and M. Yung, "A unified framework for the analysis of side-channel key recovery attacks," Advanced in Cryptology, EUROCRYPT'09, LNCS 5479, pp. 443-461, Apr. 2009.
13 M. Dworkin, E. Barker, J. Nechvatal, J. Foti, L. Bassham, E. Roback, and J. Dray Jr., "Advanced Encryption Standard (AES)," NIST FIPS 197, Nov. 2001.
14 D. Kingma and J. Ba, "Adam: a method for stochastic optimization," 3rd International Conference on Learning Representations (ICLR), May. 2015.