User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

On the Performance of Convolutional Neural Networks for Side-Channel Analysis

Primary tabs

download
  • Open access
  • PDF
  • 1.87 M
Legay, Axel [UCL] Picek, Stjepan [Delft University of Technology, Mekelweg 2, Delft, The Netherlands] Samiotis, Ioannis Petros [Delft University of Technology, Mekelweg 2, Delft, The Netherlands] Jaehun, Kim [Delft University of Technology, Mekelweg 2, Delft, The Netherlands] Heuser, Annelie [CNRS, IRISA, Rennes, France] Bhasin, Shivam [Physical Analysis and Cryptographic Engineering, Temasek Laboratories, Nanyang Technological University, Singapore, Singapore]

In this work, we ask a question whether Convolutional Neural Networks are more suitable for side-channel attacks than some other machine learning techniques and if yes, in what situations. Our results point that Convolutional Neural Networks indeed outperform machine learning in several scenarios when considering accuracy. Still, often there is no compelling reason to use such a complex technique. In fact, if comparing techniques without extra steps like preprocessing, we see an obvious advantage for Convolutional Neural Networks when the level of noise is small, and the number of measurements and features is high. The other tested settings show that simpler machine learning techniques, for a significantly lower computational cost, perform similarly or sometimes even better. The experiments with guessing entropy indicate that methods like Random Forest or XGBoost could perform better than Convolutional Neural Networks for the datasets we investigated.

Document type Communication à un colloque (Conference Paper) – Présentation orale avec comité de sélection
Access type Accès libre
Publication date 2018
Language Anglais
Conference "Space 2018", Indian Institute of Technology, Kanpur (du 17/12/2018 au 19/12/2018)
Journal information "Security, Privacy, and Applied Cryptography Engineering" - , p. pp 157-176 (2018)
Peer reviewed yes
Publisher Springer International Publishing (Cham)
Publication status Publié
Affiliation UCL - SST/ICTM/INGI - Pôle en ingénierie informatique
Keywords Side-channel analysis ; Machine learning ; Deep learning ; Convolutional Neural Networks
Links
  1. Ronen Eyal, Shamir Adi, Weingarten Achi-Or, OFlynn Colin, IoT Goes Nuclear: Creating a ZigBee Chain Reaction, 10.1109/sp.2017.14
  2. Chari Suresh, Rao Josyula R., Rohatgi Pankaj, Template Attacks, Cryptographic Hardware and Embedded Systems - CHES 2002 (2003) ISBN:9783540004097 p.13-28, 10.1007/3-540-36400-5_3
  3. Heuser Annelie, Rioul Olivier, Guilley Sylvain, Good Is Not Good Enough : Deriving Optimal Distinguishers from Communication Theory, Advanced Information Systems Engineering (2014) ISBN:9783642387081 p.55-74, 10.1007/978-3-662-44709-3_4
  4. Lerman Liran, Poussier Romain, Bontempi Gianluca, Markowitch Olivier, Standaert François-Xavier, Template Attacks vs. Machine Learning Revisited (and the Curse of Dimensionality in Side-Channel Analysis), Constructive Side-Channel Analysis and Secure Design (2015) ISBN:9783319214757 p.20-33, 10.1007/978-3-319-21476-4_2
  5. Schindler Werner, Lemke Kerstin, Paar Christof, A Stochastic Model for Differential Side Channel Cryptanalysis, Cryptographic Hardware and Embedded Systems – CHES 2005 (2005) ISBN:9783540284741 p.30-46, 10.1007/11545262_3
  6. Choudary Omar, Kuhn Markus G., Efficient Template Attacks, Smart Card Research and Advanced Applications (2014) ISBN:9783319083018 p.253-270, 10.1007/978-3-319-08302-5_17
  7. Mitchell, T.M.: Machine Learning, 1st edn. McGraw-Hill Inc., New York (1997)
  8. Heuser Annelie, Zohner Michael, Intelligent Machine Homicide, Constructive Side-Channel Analysis and Secure Design (2012) ISBN:9783642299117 p.249-264, 10.1007/978-3-642-29912-4_18
  9. Hospodar Gabriel, Gierlichs Benedikt, De Mulder Elke, Verbauwhede Ingrid, Vandewalle Joos, Machine learning in side-channel analysis: a first study, 10.1007/s13389-011-0023-x
  10. Lerman Liran, Bontempi Gianluca, Markowitch Olivier, Power analysis attack: an approach based on machine learning, 10.1504/ijact.2014.062722
  11. Lerman Liran, Bontempi Gianluca, Markowitch Olivier, A machine learning approach against a masked AES : Reaching the limit of side-channel attacks with a learning model, 10.1007/s13389-014-0089-3
  12. Lerman Liran, Medeiros Stephane Fernandes, Bontempi Gianluca, Markowitch Olivier, A Machine Learning Approach Against a Masked AES, Smart Card Research and Advanced Applications (2014) ISBN:9783319083018 p.61-75, 10.1007/978-3-319-08302-5_5
  13. Picek Stjepan, Heuser Annelie, Guilley Sylvain, Template attack versus Bayes classifier, 10.1007/s13389-017-0172-7
  14. Gilmore Richard, Hanley Neil, O'Neill Maire, Neural network based attack on a masked implementation of AES, 10.1109/hst.2015.7140247
  15. Heuser Annelie, Picek Stjepan, Guilley Sylvain, Mentens Nele, Lightweight Ciphers and their Side-channel Resilience, 10.1109/tc.2017.2757921
  16. Heuser Annelie, Picek Stjepan, Guilley Sylvain, Mentens Nele, Side-Channel Analysis of Lightweight Ciphers: Does Lightweight Equal Easy?, Radio Frequency Identification and IoT Security (2017) ISBN:9783319620237 p.91-104, 10.1007/978-3-319-62024-4_7
  17. Picek Stjepan, Heuser Annelie, Jovic Alan, Ludwig Simone A., Guilley Sylvain, Jakobovic Domagoj, Mentens Nele, Side-channel analysis and machine learning: A practical perspective, 10.1109/ijcnn.2017.7966373
  18. Picek Stjepan, Heuser Annelie, Jovic Alan, Legay Axel, Climbing Down the Hierarchy: Hierarchical Classification for Machine Learning Side-Channel Attacks, Progress in Cryptology - AFRICACRYPT 2017 (2017) ISBN:9783319573380 p.61-78, 10.1007/978-3-319-57339-7_4
  19. Maghrebi Houssem, Portigliatti Thibault, Prouff Emmanuel, Breaking Cryptographic Implementations Using Deep Learning Techniques, Security, Privacy, and Applied Cryptography Engineering (2016) ISBN:9783319494449 p.3-26, 10.1007/978-3-319-49445-6_1
  20. Cagli Eleonora, Dumas Cécile, Prouff Emmanuel, Convolutional Neural Networks with Data Augmentation Against Jitter-Based Countermeasures, Lecture Notes in Computer Science (2017) ISBN:9783319667867 p.45-68, 10.1007/978-3-319-66787-4_3
  21. Chollet, F., et al.: Keras (2015). https://github.com/fchollet/keras
  22. Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). Software available from tensorflow.org
  23. Wolpert David H., The Lack of A Priori Distinctions Between Learning Algorithms, 10.1162/neco.1996.8.7.1341
  24. Bellman, R.E.: Dynamic Programming. Dover Publications, Incorporated, Mineola (2003)
  25. Hughes G., On the mean accuracy of statistical pattern recognizers, 10.1109/tit.1968.1054102
  26. Hornik Kurt, Approximation capabilities of multilayer feedforward networks, 10.1016/0893-6080(91)90009-t
  27. Friedman Nir, Geiger Dan, Goldszmidt Moises, 10.1023/a:1007465528199
  28. Collobert Ronan, Bengio Samy, Links between perceptrons, MLPs and SVMs, 10.1145/1015330.1015415
  29. Friedman Jerome H., machine., 10.1214/aos/1013203451
  30. Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. CoRR abs/1603.02754 (2016)
  31. Breiman Leo, 10.1023/a:1010933404324
  32. LeCun, Y., Bengio, Y., et al.: Convolutional networks for images, speech, and time series. In: The Handbook of Brain Theory and Neural Networks, vol. 3361, no. 10 (1995)
  33. Van Den Oord, A., et al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)
  34. Demuth, H.B., Beale, M.H., De Jess, O., Hagan, M.T.: Neural Network Design. Martin Hagan (2014)
  35. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs/1412.6980 (2014)
  36. Standaert François-Xavier, Malkin Tal G., Yung Moti, A Unified Framework for the Analysis of Side-Channel Key Recovery Attacks, Advances in Cryptology - EUROCRYPT 2009 (2009) ISBN:9783642010002 p.443-461, 10.1007/978-3-642-01001-9_26
  37. TELECOM ParisTech SEN research group: DPA Contest, 4th edn (2013–2014). http://www.DPAcontest.org/v4/
  38. TELECOM ParisTech SEN research group: DPA Contest, 2nd edn (2009–2010). http://www.DPAcontest.org/v2/
  39. Coron Jean-Sébastien, Kizhvatov Ilya, An Efficient Method for Random Delay Generation in Embedded Software, Lecture Notes in Computer Science (2009) ISBN:9783642041372 p.156-170, 10.1007/978-3-642-04138-9_12
  40. James Gareth, Witten Daniela, Hastie Trevor, Tibshirani Robert, An Introduction to Statistical Learning, ISBN:9781461471370, 10.1007/978-1-4614-7138-7
  41. Klambauer, G., Unterthiner, T., Mayr, A., Hochreiter, S.: Self-normalizing neural networks. arXiv preprint arXiv:1706.02515 (2017)
  42. Strobl Carolin, Boulesteix Anne-Laure, Zeileis Achim, Hothorn Torsten, Bias in random forest variable importance measures: Illustrations, sources and a solution, 10.1186/1471-2105-8-25
  43. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015)
  44. Timon, B.: Non-profiled deep learning-based side-channel attacks. Cryptology ePrint Archive, Report 2018/196 (2018). https://eprint.iacr.org/2018/196
Bibliographic reference Legay, Axel ; Picek, Stjepan ; Samiotis, Ioannis Petros ; Jaehun, Kim ; Heuser, Annelie ; et. al. On the Performance of Convolutional Neural Networks for Side-Channel Analysis.Space 2018 (Indian Institute of Technology, Kanpur, du 17/12/2018 au 19/12/2018). In: Security, Privacy, and Applied Cryptography Engineering, , p. pp 157-176 (2018)
Permanent URL http://hdl.handle.net/2078.1/218725