Side-channel Attack Using Word Embedding and Long Short Term Memories
DOI:
https://doi.org/10.13052/jwe1540-9589.2127Keywords:
Side-channel attack, Word Embedding, Long Short Term MemoriesAbstract
Side-channel attack (SCA) based on machine learning has proved to be a valid technique in cybersecurity, especially subjecting to the symmetric-key crypto implementations in serial operation. At the same time, parallel-encryption computing based on Field Programmable Gate Arrays (FPGAs) grows into a new influencer, but the attack results using machine learning are exiguous. Research on the traditional SCA has been mostly restricted to pre-processing: Signal Noisy Ratio (SNR) and Principal Component Analysis (PCA), etc. In this work, firstly, we propose to replace Points of Interests (POIs) and dimensionality reduction by utilizing word embedding, which converts power traces into sensitive vectors. Secondly, we combined sensitive vectors with Long Short Term Memories (LSTM) to execute SCA based on FPGA crypto-implementations. In addition, compared with traditional Template Attack (TA), Multiple Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN). The result shows that the proposed model can not only reduce the manual operation, such as parametric assumptions and dimensionality setting, which limits their range of application, but improve the effectiveness of side-channel attacks as well.
Downloads
References
Giraud C. An RSA Implementation Resistant to Fault Attacks and to Simple Power Analysis[J]. IEEE Transactions on Computers, 2006, 55(9):1116–1120.
Kocher P C. Timing attacks on implementations of diffehellman, RSA, DSS, and another systems[J]. Adances in Cryptography-CRYPTO’96, 1996.
Kocher P C, Jaffe J, Jun B. Differential Power Analysis[M]. Springer US, 2007.
Chari S, Rao J R, Rohatgi P. Template Attacks[J]. International Workshop on Cryptographic Hardware & Embedded Systems, 2002.
Schindler W, Lemke K, Paar C. A Stochastic Model for Differential Side Channel Cryptanalysis[C]// Cryptographic Hardware and Embedded Systems – CHES 2005, 7th International Workshop, Edinburgh, UK, August 29 – September 1, 2005, Proceedings. Springer-Verlag, 2005.
T Bartkewitz, K Lemkerust. Efficient Template Attacks Based on Probabilistic Multi-class Support Vector Machines[M]. Springer Berlin Heidelberg, 2013.
Olivier, Markowitch, Liran, et al. Power analysis attack: an approach based on machine learning[J]. International journal of applied cryptography: IJACT, 2014, 3(2):97–115.
Ramezanpour K, Ampadu P, Diehl W. SCAUL: Power Side-Channel Analysis with Unsupervised Learning[J]. IEEE Transactions on Computers, 2020, PP(99):1–1.
Jin M, Zheng M, Hu H, et al. An Enhanced Convolutional Neural Network in Side-Channel Attacks and Its Visualization[J]. 2020.
Zhang H, Zhou Y. Template Attack vs. Stochastic Model: An Empirical Study on the Performances of Profiling Attacks in Real Scenarios[J]. Microprocessors and Microsystems, 2019, 66(APR.):43–54.
Benadjila R, Prouff E, Strullu R, et al. Deep learning for side-channel analysis and introduction to ASCAD database[J]. Journal of Cryptographic Engineering, 2019, 10(Feb).
Golder A, Das D, Danial J, et al. Practical Approaches Towards Deep-Learning Based Cross-Device Power Side Channel Attack[J]. 2019.
Cagli E, Dumas C, Prouff E. Convolutional Neural Networks with Data Augmentation Against Jitter-Based Countermeasures[C]// International Conference on Cryptographic Hardware and Embedded Systems. Springer, Cham, 2017.
Moini S, Tian S, Szefer J, et al. Remote Power Side-Channel Attacks on CNN Accelerators in FPGAs[J]. 2020.
Ramezanpour K, Ampadu P, Diehl W. SCAUL: Power Side-Channel Analysis with Unsupervised Learning[J]. IEEE Transactions on Computers, 2020, PP(99):1–1.
Won Y S, Han D G, Jap D, et al. Non-Profiled Side-Channel Attack based on Deep Learning using Picture Trace[J]. IEEE Access, 2021, PP(99):1–1.
J Wei, Y Zhang, Zhou Z, et al. Leaky DNN: Stealing Deep-learning Model Secret with GPU Context-switching Side-channel[C]// IEEE/IFIP International Conference on Dependable Systems and Networks (DSN). IEEE, 2020.
Hochreiter S, Schmidhuber J. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8):1735–1780.
Paguada S, Batina L, Armendariz I. Toward practical autoencoder-based side-channel analysis evaluations[J]. Computer Networks, 2021(4):108230.
Wold S, Esbensen K, Geladi P. Principal component analysis[J]. Chemometrics & Intelligent Laboratory Systems, 1987, 2(1–3):37–52.
Kwon D, Kim H, Hong S. Non-Profiled Deep Learning-Based Side-Channel Preprocessing With Autoencoders[J]. IEEE Access, 2021, PP(99):1–1.
Bojanowski P, Grave E, Joulin A, et al. Enriching Word Vectors with Subword Information[J]. Transactions of the Association for Computational Linguistics, 2017, 5:135–146.
Bengio Y, Réjean Ducharme, Vincent P, et al. A Neural Probabilistic Language Model.[J]. Journal of Machine Learning Research, 2003.
CHURCH, Ward K. Word2Vec[J]. Natural Language Engineering, 2017, 23(01):155–162.
Graves A, Mohamed A R, Hinton G. Speech recognition with deep recurrent neural networks[C]// Acoustics, Speech, and Signal Processing, 1988. ICASSP-88. 1988 International Conference on. IEEE, 2013.
