Application of Deep Learning Methods in Cryptanalysis
Keywords:
Deep Learning, Neural Networks, Cryptanalysis, Stream Cipher, RC4, RC4A, Trivium, TRIAD, Black-Box Model, Keystream, Bias Detection, Machine Learning, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), LSTM, Differential Cryptanalysis, Side-Channel Analysis, Cryptography.Abstract
This article presents a theoretical and experimental investigation of the applicability of deep learning techniques in modern cryptanalysis. Traditional cryptanalytic methods are computationally intensive, as they require detecting complex nonlinear relationships between the key, plaintext, and ciphertext. Deep learning methods, in contrast, operate directly on raw data, independently extract meaningful features, and automatically detect statistical deviations (bias), making them an effective tool for identifying vulnerabilities in cryptographic systems.
References
Bahdanau, D.; Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014, https://arxiv.org/ abs/1409.0473 [Accessed on 01 Aug 2020].
Chen, C.; Seff, A.; Kornhauser, A. & Xiao, J. Deepdriving: Learning affordance for direct perception in autonomous driving. In Proceedings of the International Conference on Computer Vision, IEEE, 2015, pp. 2722-2730. doi: 10.1109/iccv.2015.312
Deng, L. & Yu, D. Deep learning: methods and applications. Foundations and trends in signal processing, Now Publishers Inc. Hanover, MA, USA, 2014, 7(3–4), pp. 197-387. doi: 10.1561/9781601988157
Rivest, R.L. Cryptography and machine learning. In Proceedings of the International Conference on the Theory and Application of Cryptology, Springer, Berlin, Heidelberg, 1991, pp. 427-439. doi: 10.1007/3-540-57332-1_36
Abadi, M. & Andersen, D.G. Learning to protect communications with adversarial neural cryptography. arXiv preprint arXiv:1610.06918, 2016, https://arxiv.org/ abs/1610.06918 [Accessed on 31 July 2020].
Hesamifard, E.; Takabi, H. & Ghasemi, M. Cryptodl: Deep neural networks over encrypted data. arXiv preprint arXiv:1711.05189, 2017, https://arxiv.org/abs/1711.05189 [Accessed on 12 July 2020]. doi: 10.1145/3292006.3300044
Picek, S.; Samiotis, I.P.; Kim, J.; Heuser, A.; Bhasin, S. & Legay, A. On the performance of convolutional neural networks for side-channel analysis. In Proceedings of the International Conference on Security, Privacy, and Applied Cryptography Engineering, Springer, Cham, 2018, pp. 157-176.
Wang, H. Side-channel analysis of aes based on deep learning. https://www.diva-portal.org/smash/get/ diva2:1325691/FULLTEXT01.pdf, 2019 [Accessed on 07 Aug 2020].
Gohr, A. Improving attacks on round-reduced speck32/64 using deep learning. In Proceedings of Annual International Cryptology Conference, Springer, 2019, pp. 150–179. doi: 10.1007/978-3-030-26951-7_6
Beaulieu, R.; Shors, D.; Smith, J.; Treatman-Clark, S.; Weeks, B. & Wingers, L. The SIMON and SPECK Families of Lightweight Block Ciphers. IACR Cryptol. ePrint Arch., 2013, p.404, https://eprint.iacr.org/2013/404. pdf [Accessed on 07 Aug 2020].
Baksi, A.; Breier, J.; Dong, X. & Yi, C. Machine learning assisted differential distinguishers for lightweight ciphers. IACR Cryptol. ePrint Arch., 2020, p.571, https:// eprint.iacr.org/2020/571.pdf [Accessed on 14 Oct 2020].
Jain, A.; Kohli, V. & Mishra, G. Deep learning based differential distinguisher for lightweight cipher PRESENT. Cryptology ePrint Archive, Report 2020/846. https:// eprint.iacr.org/2020/846. [Accessed on 14 Oct 2020].
Downloads
Published
How to Cite
License
Copyright (c) 2025 Ilhom Rahmatullayev, Baxtiyor Abduraximov
This work is licensed under a Creative Commons Attribution 4.0 International License.
