Side-channel Attack Using Word Embedding and Long Short Term Memories

Authors

  • Zixin Liu State Key Laboratory of Nuclear Resources and Environment East China University of Technology Nanchang 330013, Jiangxi, China
  • Zhibo Wang Software college, East China University of Technology Nanchang 330000, China
  • Mingxing Ling State Key Laboratory of Nuclear Resources and Environment East China University of Technology Nanchang 330013, Jiangxi, China

DOI:

https://doi.org/10.13052/jwe1540-9589.2127

Keywords:

Side-channel attack, Word Embedding, Long Short Term Memories

Abstract

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

Download data is not yet available.

Author Biographies

Zixin Liu, State Key Laboratory of Nuclear Resources and Environment East China University of Technology Nanchang 330013, Jiangxi, China

Zixin Liu, male, born in 1985, a member of the Communist Party of China, lecturer, graduate degree. 2009.6 graduated from School of Software, East China Normal University, majoring in software engineering. Since September 2009, he has been a teacher at software academy, East China University of Technology. He has been engaged in the research of hardware Side-channel attack, artificial intelligence and digital geological crossover application.

Zhibo Wang, Software college, East China University of Technology Nanchang 330000, China

Zhibo Wang, male, born in February 1984, PhD, supervisor of postgraduate, Dr 2017.6 graduated from Wuhan university of software engineering, is mainly engaged in large data analysis, block chain technology in areas such as research, including such as SCI, EI retrieval, papers published more than 20 articles, apply for a patent for invention 6, 13 utility model patents (including authorized 10), 3 software Copyrights (3 have been authorized). Presided over and participated in many provincial and ministerial research projects.

Mingxing Ling, State Key Laboratory of Nuclear Resources and Environment East China University of Technology Nanchang 330013, Jiangxi, China

Mingxing Ling, male, Ph.D., distinguished Professor and researcher of East China Institute of Technology. He has been selected as the innovation Leader of “Double Thousand Plan” of Jiangxi Province, Young JingGang Scholar, Outstanding Youth of Guangdong Natural Science Foundation, Top Young Talents of Science and Technology Innovation of Guangdong Special Support Program, member of Youth Innovation Promotion Association of Chinese Academy of Sciences and other talent programs. His research interests include supernormal enrichment and mineralization mechanism of key metals, plate subduction and magmatic activity and mineralization in eastern China, metal isotope technology and geological application. He has presided over more than 10 projects of national Natural Science Foundation of China and National Key Research and development Program.

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.

Downloads

Published

2022-01-04

Issue

Section

Articles