Abstract
While several works have explored the application of deep learning for efficient profiled side-channel analysis, explainability, or, in other words, what neural networks learn remains a rather untouched topic. As a first step, this paper explores the Singular Vector Canonical Correlation Analysis (SVCCA) tool to interpret what neural networks learn while training on different side-channel datasets, by concentrating on deep layers of the network. Information from SVCCA can help, to an extent, with several practical problems in a profiled side-channel analysis like portability issue and criteria to choose a number of layers/neurons to fight portability, provide insight on the correct size of training dataset and detect deceptive conditions like over-specialization of networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bhasin, S., Jap, D., Chattopadhyay, A., Picek, S., Heuser, A., Ranjan Shrivastwa, R.: Mind the portability: a warriors guide through realistic profiled side-channel analysis. Cryptology ePrint Archive, Report 2019/661 (2019). https://eprint.iacr.org/2019/661
Cagli, E., Dumas, C., Prouff, E.: Convolutional neural networks with data augmentation against Jitter-based countermeasures. In: Fischer, W., Homma, N. (eds.) CHES 2017. LNCS, vol. 10529, pp. 45–68. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66787-4_3
Chari, S., Rao, J.R., Rohatgi, P.: Template attacks. In: Kaliski, B.S., Koç, K., Paar, C. (eds.) CHES 2002. LNCS, vol. 2523, pp. 13–28. Springer, Heidelberg (2003). https://doi.org/10.1007/3-540-36400-5_3
Das, D., Golder, A., Danial, J., Ghosh, S., Raychowdhury, A., Sen, S.: X-DeepSCA: cross-device deep learning side channel attack. In: Proceedings of the 56th Annual Design Automation Conference 2019 on - DAC 2019, vol. 1, pp. 1–6. ACM Press, New York (2019)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5) (2018). https://doi.org/10.1145/3236009
Hettwer, B., Gehrer, S., Tim, G.: Deep neural network attribution methods for leakage analysis and symmetric key recovery. CoRR, pp. 1–17 (2019)
Kim, J., Picek, S., Heuser, A., Bhasin, S., Hanjalic, A.: Make some noise. Unleashing the power of convolutional neural networks for profiled side-channel analysis. IACR Trans. Cryptograph. Hardw. Embedded Syst. 2019(3), 148–179 (2019)
Krizhevsky, A., Nair, V., Hinton, G.: CIFAR-10 (Canadian Institute for Advanced Research) (2009). http://www.cs.toronto.edu/~kriz/cifar.html
Maghrebi, H., Portigliatti, T., Prouff, E.: Breaking cryptographic implementations using deep learning techniques. In: Carlet, C., Hasan, M.A., Saraswat, V. (eds.) SPACE 2016. LNCS, vol. 10076, pp. 3–26. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49445-6_1
Masure, L., Dumas, C., Prouff, E.: Gradient visualization for general characterization in profiling attacks. In: Polian, I., Stöttinger, M. (eds.) COSADE 2019. LNCS, vol. 11421, pp. 145–167. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-16350-1_9
Moradi, A., Guilley, S., Heuser, A.: Detecting hidden leakages. In: Boureanu, I., Owesarski, P., Vaudenay, S. (eds.) ACNS 2014. LNCS, vol. 8479, pp. 324–342. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-07536-5_20
Morcos, A., Raghu, M., Bengio, S.: Insights on representational similarity in neural networks with canonical correlation. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 31, pp. 5727–5736. Curran Associates, Inc. (2018)
Perin, G.: Deep learning model generalization in side-channel analysis. Cryptology ePrint Archive, Report 2019/978 (2019). https://eprint.iacr.org/2019/978
Perin, G., Ege, B., Chmielewski, L.: Neural network model assessment for side-channel analysis. Cryptology ePrint Archive, Report 2019/722 (2019). https://eprint.iacr.org/2019/722
Picek, S., Heuser, A., Alippi, C., Regazzoni, F.: When theory meets practice: a framework for robust profiled side-channel analysis. Cryptology ePrint Archive, Report 2018/1123 (2018). https://eprint.iacr.org/2018/1123
Picek, S., Heuser, A., Guilley, S.: Profiling side-channel analysis in the restricted attacker framework. Cryptology ePrint Archive, Report 2019/168 (2019). https://eprint.iacr.org/2019/168
Picek, S., Heuser, A., Jovic, A., Batina, L.: A systematic evaluation of profiling through focused feature selection. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 1–14 (2019). https://doi.org/10.1109/TVLSI.2019.2937365
Picek, S., Heuser, A., Jovic, A., Bhasin, S., Regazzoni, F.: The curse of class imbalance and conflicting metrics with machine learning for side-channel evaluations. IACR Trans. Cryptograph. Hardw. Embedded Syst. 2019(1), 209–237 (2018). https://tches.iacr.org/index.php/TCHES/article/view/7339
Picek, S., et al.: Side-channel analysis and machine learning: a practical perspective. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 4095–4102. IEEE (2017)
Prouff, E., Strullu, R., Benadjila, R., Cagli, E., Dumas, C.: Study of deep learning techniques for side-channel analysis and introduction to ascad database. Cryptology ePrint Archive, Report 2018/053 (2018). https://eprint.iacr.org/2018/053
Raghu, M., Gilmer, J., Yosinski, J., Sohl-Dickstein, J.: SVCCA: singular vector canonical correlation analysis for deep learning dynamics and interpretability. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30, pp. 6076–6085. Curran Associates, Inc. (2017)
Standaert, F.-X., Malkin, T.G., Yung, M.: A unified framework for the analysis of side-channel key recovery attacks. In: Joux, A. (ed.) EUROCRYPT 2009. LNCS, vol. 5479, pp. 443–461. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-01001-9_26
TELECOM ParisTech SEN research group: DPA Contest (4th edition) (2011). http://www.dpacontest.org/v4/index.php
Timon, B.: Non-profiled deep learning-based side-channel attacks with sensitivity analysis. IACR Trans. Cryptograph. Hardw. Embedded Syst. 2019(2), 107–131 (2019). https://tches.iacr.org/index.php/TCHES/article/view/7387
Acknowledgment
The authors acknowledge the support from the ’National Integrated Centre of Evaluation’ (NICE); a facility of Cyber Security Agency, Singapore (CSA).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A Additional Figures
A Additional Figures
In this section, we depict the results for hidden layers we omitted from the paper’s main body due to their similar behavior as those already presented. In Fig. 9, we depict the correlation results for the second hidden layer of an MLP in the intermediate value leakage model. Similarly, Fig. 10 shows results for the MLP2 architecture, the Hamming weight leakage model for hidden layers 2 and 3.
In Fig. 12, we show the results for the label-based inspection approach for the MLP2 architecture. We consider a scenario where both device and keys differ for the intermediate value leakage model for hidden layers 2 and 3.
Figure 13 gives correlation results for CNN for the first fully-connected layers for both the Hamming weight and intermediate value leakage models.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
van der Valk, D., Picek, S., Bhasin, S. (2021). Kilroy Was Here: The First Step Towards Explainability of Neural Networks in Profiled Side-Channel Analysis. In: Bertoni, G.M., Regazzoni, F. (eds) Constructive Side-Channel Analysis and Secure Design. COSADE 2020. Lecture Notes in Computer Science(), vol 12244. Springer, Cham. https://doi.org/10.1007/978-3-030-68773-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-68773-1_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68772-4
Online ISBN: 978-3-030-68773-1
eBook Packages: Computer ScienceComputer Science (R0)