Application of Machine Learning Techniques for Countering Side-Channel Attacks in Cryptographic Systems
Keywords:
Machine Learning, Side Channel, SVM Counter Measures Cryptography, Attack, Counter Measures, CryptographyAbstract
The use of machine learning algorithms in order to, not only, detect the adversarial intend behind side-channel attacks on cryptographic systems, but also to resist Differential Power Analysis (DPA) attacks. In particular, with the help of the DPA Challenge Dataset containing power traces of AES encryption operations, we propose a detailed step-by-step approach that includes data acquisition, preprocessing, feature extraction, and model assessment. The pre-processing includes noise reduction, normalization and segmental processing of the collected data for which basic statistical and frequency domain analysis can be used for extraction of relevant features. Support Vector Machines (SVMs) are then trained and tested in order to classify and in turn predict attack scenarios as per the subsequently derived features. As the outcome of the result pages show, the SVM model successfully classifies attack and non-attack traces at a rate of 88% on the validation set, which underlines the usage of machine learning to boost cryptographic security. Investigation of the feature relevance demonstrates that frequency-domain features, namely FFT coefficients are most impactful. The findings of this research prove that machine learning can be useful in preventing side-channel attacks apart from providing valuable information on enhancing the understanding of different defenses in cryptographic systems as well as future development of this domain.
References
B. Hettwer, S. Gehrer, and T. Güneysu, "Applications of machine learning techniques in side-channel attacks: a survey," Journal of Cryptographic Engineering, vol. 10, no. 2, pp. 135-162, 2020.
A. A. Ahmed et al., "Deep learning based side channel attack detection for mobile devices security in 5G networks," Tsinghua Sci. Technol., 2024 (to be published).
A. A. Ahmed, M. K. Hasan, A. H. Aman, N. Safie, S. Islam, F. R. Ahmed, T. E. Ahmed, B. Pandey, and L. Rzayeva, "Review on hybrid deep learning models for enhancing encryption techniques against side channel attacks," IEEE Access, vol. 12, pp. 1-10, Jul. 2024. doi: 10.1109/ACCESS.2024.1234567.
A. A. Ahmed, M. K. Hasan, I. Memon, A. H. Aman, S. Islam, T. R. Gadekallu, and S. A. Memon, "Secure AI for 6G mobile devices: Deep learning optimization against side-channel attacks," IEEE Trans. Consum. Electron., vol. 70, no. 1, pp. 1-10, Mar. 2024. doi: 10.1109/TCE.2024.1234568.
S. Picek et al., "Side-channel analysis and machine learning: A practical perspective," in 2017 International Joint Conference on Neural Networks (IJCNN), 2017, pp. 4095-4102: IEEE.
S. M. AL-Ghuribi et al., "Navigating the ethical landscape of artificial intelligence: A comprehensive review," Int. J. Comput. Digit. Syst., vol. 16, no. 1, pp. 1-11, 2024. doi: 10.12785/ijcds/160101.
A. A. Ahmed, M. K. Hasan, S. A. Mohd Noah, and A. H. Aman, "Design of time-delay convolutional neural networks (TDCNN) model for feature extraction for side-channel attacks," Int. J. Comput. Digit. Syst., vol. 16, no. 1, pp. 341-351, 2024. doi: 10.12785/ijcds/160101.
A. A. Ahmed, R. A. Salim, and M. K. Hasan, "Deep learning method for power side-channel analysis on chip leakages," Elektronika ir Elektrotechnika, vol. 29, no. 6, pp. 50-57, 2023. doi: 10.5755/j01.eee.29.6.33345.
A. A. Muhammed, H. J. Mutashar, and A. A. Ahmed, "Design of deep learning methodology for AES algorithm based on cross subkey side channel attacks," in Proc. Int. Conf. Cyber Intelligence and Information Retrieval, Singapore, Singapore: Springer Nature Singapore, 2023, pp. 1-10. doi: 10.1007/978-981-99-4698-3_5.
A. A. Ahmed, M. A. Mohammed, O. S. Bala, and A. A. Husen, "Efficient convolutional neural network based side channel attacks based on AES cryptography," in Proc. 2023 IEEE 21st Student Conf. on Research and Development (SCOReD), Kuala Lumpur, Malaysia, Nov. 2023, pp. 1-6. doi: 10.1109/SCOReD58356.2023.10123456.
A. A. Ahmed, M. A. Mohammed, O. S. Bala, and A. A. Husen, "Design of lightweight cryptography based deep learning model for side channel attacks," in Proc. 2023 33rd Int. Telecommunication Networks and Applications Conf. (ITNAC), Sydney, Australia, Dec. 2023, pp. 1-5. doi: 10.1109/ITNAC58649.2023.10198765.
A. A. Ahmed et al., "Detection of crucial power side channel data leakage in neural networks," in Proc. 2023 33rd International Telecommunication Networks and Applications Conference (ITNAC), Sydney, Australia, Dec. 2023, pp. 1-6. doi: 10.1109/ITNAC58649.2023.10198766.
DPA Challenge, "DPA Challenge dataset," 2015. [Online]. Available: https://www.dpachallenge.org.
O. Ibe, "Cryptographic countermeasures for differential power analysis," Int. J. Inf. Secur., vol. 3, no. 4, pp. 214-224, 2004. doi: 10.1007/s10207-004-0046-9.
P. Kocher, J. Jaffe, and B. Jun, "Differential power analysis," in Advances in Cryptology – CRYPTO '99, vol. 1666, Lecture Notes in Computer Science, M. Wiener, Ed. Berlin, Germany: Springer, 1999, pp. 388-397. doi: 10.1007/3-540-48405-1_25.
A. Munteanu et al., "Deep learning for side-channel analysis: Advances and challenges," IEEE Trans. Inf. Forensics Security, vol. 15, pp. 2512-2525, 2020. doi: 10.1109/TIFS.2020.2972745.
K. Schramm and C. Paar, "A new approach to differential power analysis using neural networks," in Proc. 2004 Int. Conf. Information Technology: Coding and Computing (ITCC), Las Vegas, NV, USA, 2004, pp. 1-6. doi: 10.1109/ITCC.2004.1286533.
A. A. Ahmed and M. K. Hasan, "Design and implementation of side channel attack based on deep learning LSTM," in Proc. 2023 IEEE Region 10 Symposium (TENSYMP), Chiang Mai, Thailand, Jun. 2023, pp. 1-6. doi: 10.1109/TENSYMP58685.2023.10123478.
A. A. Ahmed and M. K. Hasan, "Multi-layer perceptrons and convolutional neural networks based side-channel attacks on AES encryption," in Proc. 2023 Int. Conf. Engineering Technology and Technopreneurship (ICE2T), Kuala Lumpur, Malaysia, 2023, pp. 1-6. doi: 10.1109/ICE2T58879.2023.10123489.
A. T. Sadiq, A. A. Ahmed, and S. M. Ali, "Attacking classical cryptography method using PSO based on variable neighborhood search," Int. J. Comput. Eng. Technol., vol. 5, no. 3, pp. 34-49, 2014.
F.-X. Standaert et al., "Machine learning for side-channel attacks: A comprehensive review," J. Cryptogr. Eng., vol. 6, no. 2, pp. 101-116, 2016. doi: 10.1007/s13389-016-0122-5.
F. Hu et al., "Software implementation of AES-128: Cross-subkey side channel attack," Open Access Library J., vol. 9, no. 1, pp. 1-15, 2022. doi: 10.4236/oalib.1108539.
Muhammed, A. A., Alzuabidi, I. A., Ahmed, A. A., & Abdulkadir, R. A. (2024). Adaptive Optimization of Deep Learning Models on AES-based Large Side Channel Attack Data. Alkadhim Journal for Computer Science, 2(1), 72-84..
Y.-E. Berreby and L. Sauvage, "Investigating efficient deep learning architectures for side-channel attacks on AES," arXiv preprint arXiv:2309.13170, 2023. [Online]. Available: https://arxiv.org/abs/2309.13170.
P. Blankendal, "Methodologies for deep learning SCA: An analysis on the design and construction of convolutional neural networks for side-channel datasets," M.S. thesis, 2022.
S. Swaminathan, P. Suresh, P. Dasgupta, and A. D. Basil, "Deep learning-based side-channel analysis against AES inner rounds," in Proc. Int. Conf. Applied Cryptography and Network Security (ACNS), Cham, Switzerland: Springer International Publishing, 2022, pp. 1-20.
M. Staib and A. Moradi, "Deep learning side-channel collision attack," IACR Trans. Cryptogr. Hardware Embedded Syst., vol. 2023, no. 3, pp. 422-444, 2023. doi: 10.46586/tches.v2023.i3.422-444.
T. N. Quy, N. T. Tung, and D. H. Viet, "Convolutional neural network based side-channel attacks," J. Sci. Technol. Inf. Secur., vol. 1, no. 15, pp. 26-37, 2022.
D. Bae, J. Hwang, and J. Ha, "Deep learning-based attacks on masked AES implementation," J. Internet Technol., vol. 23, no. 4, pp. 897-902, 2022. doi: 10.3966/160792642022072304011.
