Side-channel analysis attacks based on deep learning network

Abstract

There has been a growing interest in the side-channel analysis (SCA) field based on deep learning (DL) technology. Various DL network or model has been developed to improve the efficiency of SCA. However, few studies have investigated the impact of the different models on attack results and the exact relationship between power consumption traces and intermediate values. Based on the convolutional neural network and the autoencoder, this paper proposes a Template Analysis Pre-trained DL Classification model named TAPDC which contains three sub-networks. The TAPDC model detects the periodicity of power trace, relating power to the intermediate values and mining the deeper features by the multi-layer convolutional net. We implement the TAPDC model and compare it with two classical models in a fair experiment. The evaluative results show that the TAPDC model with autoencoder and deep convolution feature extraction structure in SCA can more effectively extract information from power consumption trace. Also, Using the classifier layer, this model links power information to the probability of intermediate value. It completes the conversion from power trace to intermediate values and greatly improves the efficiency of the power attack.

Graphical abstract

Keywords

side-channel analysis / template attack / machine learning / deep learning

References

[1] Jaegeun M , Im Y Jung , Hyuk J P . IoT application protection against power analysis attack. Computers and Electrical Engineering, 2018, 67 : 566– 578

[2] Brier E, Clavier C, Olivier F. Correlation power analysis with a leakage model. In: Proceedings of International Conference on Cryptographic Hardware and Embedded Systems. 2004, 16–29

[3] Chang J , Wang H , Wang F , Zhang A , Ji Y . RKA security for identity-based signature scheme. IEEE Access, 2020, 8 : 17833– 17841

[4] Mangard S, Pramstaller N, Oswald E. Successfully attacking masked AES hardware implementations. In: Proceedings of International Conference on Cryptographic Hardware and Embedded Systems. 2005, 157–171

[5] Van Cleemput J , De Sutter B , De Bosschere B . Adaptive compiler strategies for mitigating timing side channel attacks. IEEE Transactions on Dependable and Secure Computing, 2020, 17( 1): 35– 49

[6] Yoshikawa M, Nozaki Y, Asahi K. Multiple rounds aware power analysis attack for a lightweight cipher SIMECK. In: Proceedings of IEEE Second International Conference on Big Data Computing Service & Applications. 2016, 252–256

[7] GO BS , Le DV , Song MG , Park M , Yu I K . Design and electromagnetic analysis of an induction-type coilgun system with a pulse power module. IEEE Transactions on Plasma Science, 2019, 47( 1): 971– 976

[8] Kocher P , Jaffe J , Jun B , Rohatgi P . Introduction to differential power analysis. Journal of Cryptographic Engineering, 2011, 1( 1): 5– 27

[9] Carlet C , Faugere J C , Goyet C , Renault G . Analysis of the algebraic side channel attack. Journal of Cryptographic Engineering, 2012, 2( 1): 45– 62

[10] Ghoshal A, Patranabis S, Mukhopadhyay D. Template-based fault injection analysis of block ciphers. In: Proceedings of International Conference on Security, Privacy, and Applied Cryptography Engineering. 2018, 21–36

[11] Wan W, Chen H, Chen J. The attack case of ECDSA on blockchain based on improved simple power analysis. In: Proceedings of International Conference on Artificial Intelligence and Security. 2019, 120–132

[12] Rivest R L. Cryptography and machine learning. In: Proceedings of Advances in Cryptology–ASIACRYPT. 1991, 427-439

[13] Hospodar G , Gierlichs B , Mulder E D , Verbauwhede I , Vandewalle J . Machine learning in side-channel analysis: a first study. Journal of Cryptographic Engineering, 2011, 1( 4): 293– 302

[14] Heuser A, Zohner M. Intelligent machine homicide-breaking cryptographic devices using support vector machines. In: Proceedings of Constructive Side-Channel Analysis and Secure Design. 2012, 249–264

[15] Bartkewitz T, Lemke-Rust K. Efficient template attacks based on probabilistic multi-class support vector machines. In: Proceedings of Smart Card Research and Advanced Applications. 2012, 263–276

[16] Lerman L, Poussier R, Bontempi G, Markowitch O, Standaert F X. Template attacks vs. machine learning revisited (and the curse of dimensionality in side-channel analysis). In: Proceedings of Constructive Side-Channel Analysis and Secure Design. 2015, 20–33

[17] Martinasek Z, Dzurenda P, Malina L. Profiling power analysis attack based on MLP in DPA contest V4.2. In: Proceedings of International Conference on Telecommunications and Signal Processing. 2016, 223–226

[18] Martinasek Z , Malina L , Trasy K . Profiling power analysis attack based on multi-layer perceptron network. Computational Problems in Science and Engineering, 2015, 343 : 317– 339

[19] Cagli E, Dumas C, Prouff E. Convolutional neural networks with data augmentation against jitter-based countermeasures. In: Proceedings of International Conference on Cryptographic Hardware and Embedded Systems. 2017, 45–68

[20] Maghrebi H, Portigliatti T, Prouff E. Breaking cryptographic implementations using deep learning techniques. In: Proceedings of International Conference on Security, Privacy, and Applied Cryptography Engineering. 2016, 3–26

[21] Prouff E , Strullu R , Benadjila R , Cagli E , Dumas C . Study of deep learning techniques for side-channel analysis and introduction to ASCAD database. Journal of Cryptographic Engineering, 2020, 10( 2): 163– 188

[22] Chen R , Wu W , Qi H , Wang J , Wang H . A stacked autoencoder neural network algorithm for breast cancer diagnosis with magnetic detection electrical impedance tomography. IEEE Access, 2020, 8 : 5428– 5437

RIGHTS & PERMISSIONS

Higher Education Press