DOI QR코드

DOI QR Code

Recent advances in deep learning-based side-channel analysis

  • Jin, Sunghyun (School of Cyber Security, Korea University) ;
  • Kim, Suhri (School of Cyber Security, Korea University) ;
  • Kim, HeeSeok (Department of Information Security, College of Science and Technology, Korea University) ;
  • Hong, Seokhie (School of Cyber Security, Korea University)
  • Received : 2019.03.28
  • Accepted : 2019.07.29
  • Published : 2020.04.03

Abstract

As side-channel analysis and machine learning algorithms share the same objective of classifying data, numerous studies have been proposed for adapting machine learning to side-channel analysis. However, a drawback of machine learning algorithms is that their performance depends on human engineering. Therefore, recent studies in the field focus on exploiting deep learning algorithms, which can extract features automatically from data. In this study, we survey recent advances in deep learning-based side-channel analysis. In particular, we outline how deep learning is applied to side-channel analysis, based on deep learning architectures and application methods. Furthermore, we describe its properties when using different architectures and application methods. Finally, we discuss our perspective on future research directions in this field.

Acknowledgement

Supported by : Military Crypto Research Center

References

  1. P.C. Kocher, Timing attacks on implementations of diffie-hellman, rsa, dss, and other systems, in Proc. Annu. Int. Cryptology Conf., Santa Barbara, CA, USA, 1996, pp.104-113.
  2. P. Kocher, J. Jaffe, and B. Jun, Differential power analysis, in Ann. Int. Cryptol. Conf., Santa Barbara, CA, USA, Aug. 1999, pp. 388-397.
  3. S. Mangard, E. Oswald, and T. Popp, Power analysis attacks: Revealing the secrets of smart cards, Springer Science & Business Media, Heidelberg, 2008.
  4. L. Lerman, Z. Martinasek, and O. Markowitch, Robust profiled attacks: should the adversary trust the dataset? IET Inf. Secur. 11 (2016), no. 4, 188-194. https://doi.org/10.1049/iet-ifs.2015.0574
  5. Z. Martinasek et al., k-nearest neighbors algorithm in profiling power analysis attack, Radioeng. 25 (2016), no. 2, 365-382. https://doi.org/10.13164/re.2016.0365
  6. S. Picek et al., The curse of class imbalance and conflicting metrics with machine learning for side-channel evaluations, IACR Trans. Cryptogr. Hardw. Embed. Syst. 1 (2018), no. 8, 209-237.
  7. B. Hettwer, S. Gehrer, and T. Güneysu, Applications of machine learning techniques in side-channel attacks: a survey, J. Cryptogr. Eng. (2019), https://doi.org/10.1007/s13389-019-00212-8. https://doi.org/10.1007/s13389-019-00212-8
  8. I. Goodfellow, Y. Bengio, and A. Courville, Deep learning, MIT Press, 2016. https://www.deeplearningbook.org/.
  9. Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature 521 (2015), no. 7553, 436-444. https://doi.org/10.1038/nature14539
  10. S. Mahdavifar and A. A. Ghorbani, Application of deep learning to cybersecurity: a survey, Neurocomput. 347 (2019), 149-176. https://doi.org/10.1016/j.neucom.2019.02.056
  11. K. Hornik, Approximation capabilities of multilayer feedforward networks, Neural Netw. 4 (1991), no. 2, 251-257. https://doi.org/10.1016/0893-6080(91)90009-T
  12. G. Hinton, N. Srivastava, and K. Swersky, Neural networks for machine learning lecture 6a overview of mini-batch gradient descent, Neural Netw. Machine Learn., Coursera MOOC, 2012. https://www.cs.toronto.edu/-hinton/coursera/lecture6/lec6.pdf.
  13. D. P. Kingma and J. Ba, Adam: a method for stochastic optimization, arXiv preprint arXiv:1412.6980, 2014. https://arxiv.org/abs/1412.6980.
  14. J. Bergstra and Y. Bengio, Random search for hyper-parameter optimization, J. Machine Learn. Res. 13 (2012), 281-305.
  15. S. R. Young et al. Optimizing deep learning hyper-parameters through an evolutionary algorithm, in Proc. Workshop Mach. Learn. High-Perform. Comput. Environ., New York, NY, USA, Nov. 2015, pp. 4:1-5.
  16. N. Tikhonov, On the stability of inverse problems, Dokl. Akad. Nauk SSSR 39 (1943), 195-198.
  17. R. Tibshirani, Regression shrinkage and selection via the lasso, J. Roy. Stat. Soc.: Ser. B (Methodol.) 58 (1996), no. 1, 267-288.
  18. N. Srivastava et al., Dropout: a simple way to prevent neural networks from overfitting, J. Mach. Learn. Res. 15 (2014), no. 1, 1929-1958.
  19. S. Ioffe and C, Szegedy. Batch normalization: accelerating deep network training by reducing internal covariate shift, arXiv preprint arXiv:1502.03167, 2015. https://arxiv.org/abs/1502.03167v2.
  20. N. Jaitly and G. E. Hinton, Vocal tract length perturbation (VTLP) improves speech recognition, in Proc. Int. Conf. Machine. Learning, Atlanta, GA, USA, 2013, pp. 1-5.
  21. D. H. Hubel and T. N. Wiesel, Receptive fields and functional architecture of monkey striate cortex, J. Phys. 195 (1968), no. 1, 215-243. https://doi.org/10.1113/jphysiol.1968.sp008455
  22. K. Fukushima, Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biol. Cybern. 36 (1980), no. 4, 193-202. https://doi.org/10.1007/BF00344251
  23. Y. LeCun et al., Handwritten digit recognition with a back-propagation network, in Proc. Adv. Neural Inf. Process. Syst, Denver, CO, USA, Nov. 1989, pp. 396-404.
  24. Y. LeCun et al., Gradient-based learning applied to document recognition, Proc. IEEE 86 (1998), no. 8, 2278-2324. https://doi.org/10.1109/5.726791
  25. A. Krizhevsky, I. Sutskever, and G. E. Hinton, Imagenet classification with deep convolutional neural networks, in Proc. Adv. Neural Inf. Process. Syst., Stateline, NV, USA, 2012, pp. 1097-1105.
  26. E. Brier, C. Clavier, and F. Olivier, Correlation power analysis with a leakage model, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst., Cambridge, MA, USA, Aug. 2004, pp. 16-29.
  27. B. Gierlichs et al., Mutual information analysis, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst., Washington, D.C., USA, Aug. 2008, pp. 426-442.
  28. J. G. van Woudenberg, M. F. Witteman, and B. Bakker, Improving differential power analysis by elastic alignment, Cryptogr. Track RSA Conf., San Francisco, CA, USA, Feb. 2011, pp. 104-119.
  29. R. A. Muijrers, J. G. van Woudenberg, and L. Batina, Ram: rapid alignment method, in Proc. Int. Conf. Smart Card Res. Adv. Applicat., Leuven, Belgium, Sept. 2011, pp. 266-282.
  30. S. Chari, J. R. Rao, and P. Rohatgi, Template attacks, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst., Redwood Shores, CA, USA, Aug, 2002, pp. 13-28.
  31. W. Schindler, K. Lemke, and C. Paar, A stochastic model for differential side channel cryptanalysis, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst., Edinburgh, UK, 2005, pp. 30-46.
  32. C. Archambeau et al., Template attacks in principal subspaces, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst., Yokohama, Japan, Oct. 2006, pp. 1-14.
  33. F.-X. Standaert and C. Archambeau, Using subspace-based template attacks to compare and combine power and electromagnetic information leakages, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst., Washington, D.C., USA, Aug. 2008, pp. 411-425.
  34. O. Choudary and M. G. Kuhn, Efficient template attacks, in Proc. Int. Conf. Smart Card Res. Adv. Applicat., Berlin, Germany, Nov. 2013, pp. 253-270.
  35. S. Chari et al. Towards sound approaches to counteract power-analysis attacks, in Proc. Annu. Int. Cryptol. Conf. (CRYPTO), Santa Barbara, CA, USA, Aug. 1999, pp. 398-412.
  36. L. Goubin and J. Patarin, Des and differential power analysis the "duplication" method, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst. (CHES), Worcester, MA, USA, Aug. 1999, pp. 158-172.
  37. J.-S. Coron and I. Kizhvatov, An efficient method for random delay generation in embedded software, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst., Lausanne, Switzerland, Sept. 2009, pp. 156-170.
  38. J-S. Coron and I. Kizhvatov, Analysis and improvement of the random delay countermeasure of CHES 2009, in Int. Workshop Cryptogr. Hardw. Embed. Syst., Santa Barbara, USA, Aug. 2010, pp. 95-109.
  39. N. Veyrat-Charvillon et al., Shuffling against side-channel attacks: A comprehensive study with cautionary note, in Proc. Int. Conf. Theory Appl. Cryptol. Inf. Sec. (ASIACRYPT), Beijing, China, Dec. 2012, pp. 740-757.
  40. K. Tiri, M. Akmal, and I. Verbauwhede, A dynamic and differential cmos logic with signal independent power consumption to withstand differential power analysis on smart cards, in Proc. Eur. Solid-State Circ. Conf., Florence, Italy, Sept. 2002, pp. 403-406.
  41. T. Popp and S. Mangard., Masked dual-rail pre-charge logic: DPAresistance without routing constraints, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst. (CHES), Edinburgh, UK, Aug. 2005, pp. 172-186.
  42. C. Chen et al. Balanced encoding to mitigate power analysis: a case study, in Proc. Int. Conf. Smart Card Res. Adv. Appl. (CARDIS), Paris, France, Nov. 2014, pp. 49-63.
  43. H. Maghrebi, V. Servant, and J. Bringer, There is wisdom in harnessing the strengths of your enemy: customized encoding to thwart side-channel attacks, in Proc. Int. Conf. Fast Softw. Encrypt. (FSE), Bochum, Germany, Mar. 2016, pp. 223-243.
  44. G. Becker et al. Test vector leakage assessment (TVLA) methodology in practice, in Proc. Int. Cryptogr. Module Conf. 1001 (2013).
  45. T. S. Messerges. Using second-order power analysis to attack DPA resistant software, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst. (CHES), Worcester, MA, USA, Aug. pp. 238-251.
  46. E. Prouff, M. Rivain, and R. Bevan, Statistical analysis of second order differential power analysis, IEEE Trans. Comput. 58 (2009), no. 6, 799-811. https://doi.org/10.1109/TC.2009.15
  47. C. Clavier, J. S. Coron, and N. Dabbous, Differential power analysis in the presence of hardware countermeasures, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst. (CHES), Worcester, MA, USA, Aug. 2000, pp. 252-263.
  48. S. Nagashima et al., DPA using phase-based waveform matching against random-delay countermeasure, in Proc. IEEE Int. Symp. Cir. Syst., New Orleans, LA, USA, May 2007, pp. 1807-1810.
  49. F. Durvaux et al., Efficient removal of random delays from embedded software implementations using hidden markov models, in Proc. Int. Conf. Smart Card Res. Adv. Appl. (CARDIS), Graz, Austria, Nov. 2012, pp. 123-140.
  50. L. Lerman, G. Bontempi, and O. Markowitch, Side channel attack: an approach based on machine learning, in Proc. Int. Workshop Construct. Side-Channel Anal. Secure Design (COSADE), Darmstadt, Germany, 2011, pp. 29-41.
  51. G. Hospodar et al., Machine learning in side-channel analysis: a first study, J. Cryptogr. Eng. 1 (2011), no. 4, 293-302. https://doi.org/10.1007/s13389-011-0023-x
  52. T. Bartkewitz and K. Lemke-Rust, Efficient template attacks based on probabilistic multi-class support vector machines, in Proc. Int. Conf. Smart Card Res. Adv. Appl. (CARDIS), Graz, Austria, Nov. 2012, pp. 263-276.
  53. A. Heuser and M. Zohner, Intelligent machine homicide, in Proc. Int. Workshop Construct. Side-Channel Anal. Secure Design (COSADE), Darmstadt, Germany, May 2012, pp. 249-264.
  54. J. Heyszl et al., Clustering algorithms for non-profiled single-execution attacs on exponentiations, in Proc. Int. Conf. Smart Card Res. Adv. Appl. (CARDIS), Berlin, Germany, Nov. 2013, pp. 79-93.
  55. L. Lerman, G. Bontempi, and O. Markowitch, A machine learning approach against a masked AES, in Proc. Int. Conf. Smart Card Res. Adv. Appl. (CARDIS), Berlin, Germany, Nov. 2013, pp. 61-75.
  56. R. Specht et al., Improving non-profiled attacks on exponentiations based on clustering and extracting leakage from multi-channel high-resolution em measurements, in Proc. Int. Workshop Construct. Side-Channel Anal. Secure Design (COSADE), Berlin, Germany, Apr. 2015, pp. 3-19.
  57. S. Yang et al., Back propagation neural network based leakage characterization for practical security analysis of cryptographic implementations, in Proc. Int. Conf. Inf. Secur. Cryptol. (ICISC), Seoul, Rep. of Korea, Nov. 2011, pp. 169-185.
  58. C. Whitnall and E. Oswald, Profiling DPA: efficacy and efficiency trade-offs, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst. (CHES), Santa Barbara, CA, USA, Aug. 2013, pp. 37-54.
  59. A. Moradi and F. X. Standaert, Moments-correlating DPA, in Proc. ACM Workshop Theory Implement. Secur. (ACM), Vienna, Austria, Oct. 2016, pp. 5-15.
  60. Z. Martinasek and V. Zeman, Innovative method of the power analysis, Radioengineering 2 (2013), no. 2, 586-594.
  61. Z. Martinasek, J. Hajny, and L. Malina, Optimization of power analysis using neural network, in Proc. Int. Conf. Smart Card Res. Adv. Applicat. (CARDIS), Berlin, Germany, Nov. 2014, pp. 94-107.
  62. R. Gilmore, N. Hanley, and M. O'Neill, Neural network based attack on a masked implementation of AES, in Proc. IEEE Int. Symp. Hardw. Orient. Secur. Trust (HOST), Washington, DC, USA, May 2015, pp. 106-111.
  63. P. Saravanan et al., Power analysis attack using neural networks with wavelet transform as pre-processor, in Proc. Int. Symp. VLSI Design Test, Coimbatore, India, July 2014, pp. 1-6.
  64. H. Maghrebi, T. Portigliatti, and E. Prouff, Breaking cryptographic implementations using deep learning techniques, in Proc. Int. Conf. Secur. Privacy Appl. Cryptogr. Eng. (SPACE), Hyderabad, India, Dec. 2016, pp. 3-26.
  65. Z. Martinasek and L. Malina, Comparison of profiling power analysis attacks using templates and multi-layer perceptron network, 1st Int. Conf. Math. Method Sci. Eng. (MMCTSE), 2014, pp. 134-139.
  66. Z. Martinasek et al., Power analysis attack based on the MLP in DPA contest v4, in Proc. Int. Conf. Telecommun. Signal Process., Prague, Czech Republic, July 2015, pp. 154-158.
  67. Z. Martinasek, P. Dzurenda, and L. Malina, Profiling power analysis attack based on mlp in DPA contest v4.2, in Proc. Int. Conf. Telecommun. Signal Process. (TSP), Vienna, Austria, June 2016, pp. 223-226.
  68. TELECOM ParisTech-SEN Research Group, DPA contest (4th ed.), 2013-2014, http://www.DPAcontest.org/v4/.
  69. E. Cagli, C. Dumas, and E. Prouff, Convolutional neural networks with data augmentation against jitter-based countermeasures, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst. (CHES), Taipei, Taiwan, Sept. 2017, pp. 45-68.
  70. B. Hettwer, S. Gehrer, and T. Güneysu, Profiled power analysis attacks using convolutional neural networks with domain knowledge, in Proc. Int. Conf. Select. Areas Cryptogr. (SAC). Calgary, Canada, 2018, pp. 479-498.
  71. G. Yang et al., Convolutional neural network based side-channel attacks in time-frequency representations, in Proc. Int. Conf. Smart Card Res. Adv. Appl. (CARDIS), Montpellier, France, Nov. 2018, pp. 1-17.
  72. J. Kim et al., Make some noise: Unleashing the power of convolutional neural networks for profiled side-channel analysis, Cryptology ePrint-Archive Report 2018/1023, 2018, https://eprint.iacr.org/2018/1023.
  73. J.-S. Coron, Resistance against differential power analysis for elliptic curve cryptosystems, in Proc. Int. Workshop Cryptogr. Hardw. Embed. Syst. (CHES), Worcester, MA, USA, Aug. 1999, pp. 292-302.
  74. M. Carbone et al., Deep learning to evaluate secure rsa implementations, IACR Trans. Cryptogr. Hardw. Embed. Syst. 2 (2019), no. 5, 132-161.
  75. S. Picek et al., On the performance of convolutional neural networks for side-channel analysis, in Proc. Int. Conf. Secur. Privacy Appl. Cryptogr. Eng., Kanpur, India, Dec. 2018, pp. 157-176.
  76. Y. Zotkin, F. Olivier, and E. Bourbao (eds.), Deep learning vs. template attacks in front of fundamental targets: experimental study, Cryptology ePrint Archive Report 2018/1213, 2018, https://eprint.iacr.org/2018/1213.
  77. E. Prouff et al., Study of deep learning techniques for side-channel analysis and introduction to ascad database, Cryptology ePrint, Archive, Report 2018 (2018/53), https://eprint.iacr.org/2018/053.
  78. B. Timon, Non-profiled deep learning-based side-channel attacks with sensitivity analysis, IACR Trans. Cryptogr. Hardw. Embed. Syst. 2 (2019), no. 4, 107-131.
  79. L. Masure, C. Dumas, and E. Prouff, Gradient visualization for general characterization in profiling attacks, Cryptology ePrint Archive, Report 2018/1196, 2018, https://eprint.iacr.org/2018/1196.
  80. B. Hettwer, S. Gehrer, and T. Güneysu, Deep neural network attribution methods for leakage analysis and symmetric key recovery, Cryptology ePrint Archive, Report 2019/143, 2019, https://eprint.iacr.org/2019/143
  81. A. Vedaldi, A. Zisserman, and K. Simonyan, Deep inside convolutional networks: Visualising image classification models and saliency maps, arXiv preprint arXiv:1312.6034, 2013. https://arxiv.org/abs/1312.6034.
  82. S. Bach et al., On pixel-wise explanations for non-linear classier decisions by layer-wise relevance propagation, PLoS ONE 10 (2015), no. 7, e0130140. https://doi.org/10.1371/journal.pone.0130140. https://doi.org/10.1371/journal.pone.0130140
  83. M. D. Zeiler and R. Fergus, Deep inside convolutional networks: Visualising image classification models and saliency maps, arXiv preprint arXiv:1311.2901, 2013. https://arxiv.org/abs/1311.2901.
  84. P. Robyns, P. Quax, and W. Lamotte, Improving cema using correlation optimization, IACR Trans. Cryptogr. Hardw. Embed. Syst. (TCHES) 1 (2019), no. 1, 1-24.