Side-channel attacks and learning-vector quantization

  • Ehsan Saeedi
  • Yinan Kong
  • Md. Selim Hossain


The security of cryptographic systems is a major concern for cryptosystem designers, even though cryptography algorithms have been improved. Side-channel attacks, by taking advantage of physical vulnerabilities of cryptosystems, aim to gain secret information. Several approaches have been proposed to analyze side-channel information, among which machine learning is known as a promising method. Machine learning in terms of neural networks learns the signature (power consumption and electromagnetic emission) of an instruction, and then recognizes it automatically. In this paper, a novel experimental investigation was conducted on field-programmable gate array (FPGA) implementation of elliptic curve cryptography (ECC), to explore the efficiency of side-channel information characterization based on a learning vector quantization (LVQ) neural network. The main characteristics of LVQ as a multi-class classifier are that it has the ability to learn complex non-linear input-output relationships, use sequential training procedures, and adapt to the data. Experimental results show the performance of multi-class classification based on LVQ as a powerful and promising approach of side-channel data characterization.

Key words

Side-channel attacks Elliptic curve cryptography Multi-class classification Learning vector quantization 

CLC number



Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bartkewitz, T., Lemke-Rust, K., 2013. Efficient template attacks based on probabilistic multi-class support vector machines. LNCS, 7771: 263–276. Scholar
  2. Blake, I.F., Seroussi, G., Smart, N., 1999. Elliptic Curves in Cryptography. Cambridge University Press. Scholar
  3. Cybenko, G., 1989. Approximation by superpositions of a sigmoidal function. Math. Contr. Signals Syst., 2(4): 303–314. Scholar
  4. de Mulder, E., Buysschaert, P., Ors, S.B., et al., 2005. Electromagnetic analysis attack on an FPGA implementation of an elliptic curve cryptosystem. Int. Conf. on Computer as a Tool, p.1879–1882. Scholar
  5. Duda, R.O., Hart, P.E., Stork, D.G., 2011. Pattern Classification. John Wiley & Sons.Google Scholar
  6. Flotzinger, D., Kalcher, J., Pfurtscheller, G., 1992. EEG classification by learning vector quantization. Biomed. Eng., 37(12): 303–309 (in German). Scholar
  7. Gersho, A., 1979. Asymptotically optimal block quantization. IEEE Trans. Inform. Theory, 25(4): 373–380. Scholar
  8. Haykin, S.S., 2009. Neural Networks and Learning Machines. Pearson Education, Upper Saddle River.Google Scholar
  9. Heuser, A., Zohner, M., 2012. Intelligent machine homicide. Int. Workshop on Constructive Side-Channel Analysis and Secure Design, p.249–264. Scholar
  10. Heyszl, J., Mangard, S., Heinz, B., et al., 2012a. Localized electromagnetic analysis of cryptographic implementations. Cryptographers’ Track at the RSA Conf., p.231–244. Scholar
  11. Heyszl, J., Merli, D., Heinz, B., et al., 2012b. Strengths and limitations of high-resolution electromagnetic field measurements for side-channel analysis. Int. Conf. on Smart Card Research and Advanced Applications, p.248–262. Scholar
  12. Itoh, K., Izu, T., Takenaka, M., 2002. Address-bit differential power analysis of cryptographic schemes OK-ECDH and OK-ECDSA. LNCS, 2523: 129–143. Scholar
  13. Koblitz, N., 1987. Elliptic curve cryptosystems. Math. Comput., 48(177): 203–209. Scholar
  14. Kocher, P., Jaffe, J., Jun, B., 1999. Differential power analysis. Annual Int. Cryptology Conf., p.388–397. Scholar
  15. Kohonen, T., 1988. An introduction to neural computing. Neur. Networks, 1(1): 3–16. Scholar
  16. Kohonen, T., 1990a. Improved versions of learning vector quantization. Int. Joint Conf. on Neural Networks, p.545–550. Scholar
  17. Kohonen, T., 1990b. Statistical pattern recognition revisited. In: Eckmiller, R. (Ed.), Advanced Neural Computers. North-Holland, Amsterdam, p.137–144. Scholar
  18. Kopf, B., Durmuth, M., 2009. A provably secure and efficient countermeasure against timing attacks. 22nd IEEE Computer Security Foundations Symp., p.324–335. Scholar
  19. Li, C., Lee, C., 2011. A robust remote user authentication scheme using smart card. Inform. Technol. Contr., 40(3): 236–245. Scholar
  20. Ma, C., Wang, D., Zhang, Q., 2012. Cryptanalysis and improvement of Sood et al.’s dynamic ID-based authentication scheme. Int. Conf. on Distributed Computing and Internet Technology, p.141–152. Scholar
  21. Ma, C., Wang, D., Zhao, S., 2014. Security flaws in two improved remote user authentication schemes using smart cards. Int. J. Commun. Syst., 27(10): 2215–2227. Scholar
  22. Mangard, S., Oswald, E., Popp, T., 2007. Power Analysis Attacks: Revealing the Secrets of Smart Cards. Springer Science & Business Media. Scholar
  23. Mäntysalo, J., Torkkolay, K., Kohonen, T., 1992. LVQbased speech recognition with high-dimensional context vectors. Int. Conf. on Spoken Language Processing, p.539–542.Google Scholar
  24. Miller, V.S., 1986. Use of elliptic curves in cryptography. Conf. on the Theory and Application of Cryptographic Techniques, p.417–426. Scholar
  25. Msgna, M., Markantonakis, K., Mayes, K., 2014. Precise instruction-level side channel profiling of embedded processors. Int. Conf. on Information Security Practice and Experience, p.129–143. Scholar
  26. Orlando, J., Mann, R., Haykin, S., 1990. Radar Classification of Sea-Ice Using Traditional and Neural Classifiers. Proc. Int. Joint Conf. on Neural Networks, II-263.Google Scholar
  27. Pregenzer, M., Pfurtscheller, G., Flotzinger, D., 1996. Automated feature selection with a distinction sensitive learning vector quantizer. Neurocomputing, 11(1): 19–29. Scholar
  28. Prouff, E., 2014. Constructive Side-Channel Analysis and Secure Design. Springer Berlin Heidelberg. Scholar
  29. Saeedi, E., Kong, Y., 2014. Side channel information analysis based on machine learning. 8th Int. Conf. on Signal Processing and Communication Systems, p.1–7. Scholar
  30. Saeedi, E., Hossain, M.S., Kong, Y., 2015. Multi-class SVMs analysis of side-channel information of elliptic curve cryptosystem. Int. Symp. on Performance Evaluation of Computer and Telecommunication Systems, p.1–6. Scholar
  31. Tillich, S., Herbst, C., 2008. Attacking state-of-the-art software countermeasures: a case study for AES. Int. Workshop on Cryptographic Hardware and Embedded Systems, p.228–243. Scholar
  32. Wang, D., Wang, P., 2015. Offline dictionary attack on password authentication schemes using smart cards. LNCS, 7807: 221–237. Scholar
  33. Wang, D., Ma, C., Zhang, Q., et al., 2013. Secure passwordbased remote user authentication scheme against smart card security breach. J. Networks, 8(1): 148–155.Google Scholar
  34. Wang, D., He, D., Wang, P., et al., 2015a. Anonymous twofactor authentication in distributed systems: certain goals are beyond attainment. IEEE Trans. Depend. Sec. Comput., 12(4): 428–442. Scholar
  35. Wang, D., Wang, N., Wang, P., et al., 2015b. Preserving privacy for free: efficient and provably secure two-factor authentication scheme with user anonymity. Inform. Sci., 321: 162–178. Scholar
  36. Yeh, K., 2015. A lightweight authentication scheme with user untraceability. Front. Inform. Technol. Electron. Eng., 16(4): 259–271. Scholar
  37. Zador, P.L., 1982. Asymptotic quantization error of continuous signals and the quantization dimension. IEEE Trans. Inform. Theory, 28(2): 139–149. Scholar

Copyright information

© Zhejiang University and Springer-Verlag GmbH Germany, part of Springer Nature 2017

Authors and Affiliations

  1. 1.Department of EngineeringMacquarie UniversitySydneyAustralia

Personalised recommendations