DESIGN OF SYMMETRIC CRYPTOGRAPHIC DIFFERENTIAL DISTINGUISHER BASED ON DEEP LEARNING
DOI:
https://doi.org/10.28925/2663-4023.2024.26.674Keywords:
deep learning, cryptanalysis, Gore's model, symmetric cryptographic differential discriminator, Speck32/64.Abstract
Research in the field of cryptanalysis demonstrates that differential discriminators based on neural networks significantly outperform traditional methods in identifying weaknesses in simple encryption algorithms. This is due to their ability to detect complex patterns in data that may go unnoticed by classical approaches. However, despite their high performance, there are limitations in terms of the accuracy of the discrimination and the maximum number of rounds that can be compromised for certain ciphers. The purpose of this study is to overcome these shortcomings by optimizing the architecture of the neural network (NN) and the structure of the input data, according to the Gohr model. As part of this work, several key components of the differential discriminator were improved: the convolutional module, the residual module, and the prediction module. The optimization of these components allowed to significantly increase the efficiency in recognizing differential patterns in ciphertexts. In addition, special attention was paid to optimizing the structure of the input data, which made it possible to more accurately identify the characteristics of the ciphertext and information about the encryption structure. The results of the study, conducted on the example of cryptanalysis of the Speck32/64 cipher, confirm the improvements achieved: the accuracy of the differential distinguisher has increased by 5-7 rounds, and the recognition capability has been extended to 8 cipher rounds. These achievements demonstrate the high efficiency of the proposed approach, which has significant potential for further research in the field of cryptanalysis. Due to the importance of information system security, the results of this study can significantly affect the development of new cryptanalysis methods and the improvement of encryption algorithms, which, in turn, can lead to increased data protection reliability in the modern digital environment. The results of the study, conducted on the example of cryptanalysis of the Speck32/64 cipher, confirm the improvements achieved: the accuracy of the differential distinguisher has increased by 5-7 rounds, and the recognition capability has been extended to 8 cipher rounds. These achievements demonstrate the high efficiency of the proposed approach, which has significant potential for further research in the field of cryptanalysis. Due to the importance of information system security, the results of this study can significantly affect the development of new cryptanalysis methods and the improvement of encryption algorithms, which, in turn, can lead to an increase in the reliability of data protection in the modern digital environment.
Downloads
References
Gohr, A. (2019). Improving attacks on round-reduced Speck32/64 using deep learning. In: Advances in Cryptology – CRYPTO 2019. LNCS, vol. 11693, 150–179. https://doi.org/10.1007/978-3-030-26951-7_6
Baksi, A., et al. (2020). Machine Learning Assisted Differential Distinguishers for Lightweight Ciphers (Extended Version). In: Classical and Physical Security of Symmetric Key Cryptographic Algorithms. Computer Architecture and Design Methodologies, 141–162. https://doi.org/10.1007/978-981-16-6522-6_6
Jain, A., Kohli, V., & Mishra, G. (2020). Deep learning based differential distinguisher for lightweight cipher PRESENT. Cryptology ePrint Archive.
Wang, M. (2008). Differential cryptanalysis of reduced-round PRESENT. In: Cryptology – AFRICACRYPT 2008. AFRICACRYPT 2008. Lecture Notes in Computer Science, vol. 5023, 40–49. https://doi.org/10.1007/978-3-540-68164-9_4
Bellini, E., & Rossi, M. (2021). Performance comparison between deep learning-based and conventional cryptographic distinguishers, Intelligent Computing, LNNS, vol. 285, 681–701. https://doi.org/10.1007/978-3-030-80129-8_48
Lyu, L., Tu, Y., & Zhang, Y. (2022). Improving the Deep-Learning-Based Differential Distinguisher and Applications to Simeck. In: IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD), 465–470. https://doi.org/10.1007/978-3-030-80129-8_48
Su, H. C., Zhu, X. Y., & Ming, D. (2021). Polytopic attack on round-reduced simon32/64 using deep learning. International Conference on Information Security and Cryptology. LNCS, vol. 12612, 3–20. https://doi.org/10.1007/978-3-030-71852-7_1
Benamira, A., Gerault, D., Peyrin, T., & Tan, Q. Q. (2021). A Deeper Look at Machine Learning-Based Cryptanalysis. Advances in Cryptology – EUROCRYPT 2021. EUROCRYPT 2021, LNCS, vol. 12696, 805–835. https://doi.org/10.1007/978-3-030-77870-5_28
Sun, L., Gerault, D., Benamira, A., & Peyrin, T. (2020). Neurogift: Using a machine learning based sat solver for cryptanalysis. In: Cyber Security Cryptography and Machine Learning: Fourth International Symposium, CSCML 2020, LNCS, vol. 12161, 62–84. https://doi.org/10.1007/978-3-030-49785-9_5
Hou, Z., Ren, J., & Chen, S. (2021). Cryptanalysis of round-reduced SIMON32 based on deeplearning. Cryptology ePrint Archive.
Chen, Y., Shen, Y., Yu, H., & Yuan, S. (2023). A New Neural Distinguisher Considering Features Derived from Multiple Ciphertext Pairs. The Computer Journal, 66(6), 1419–1433. https://doi.org/10.1093/comjnl/bxac019
Rajan, R., et al. (2022). Deep Learning-Based Differential Distinguisherfor Lightweight Cipher GIFT-COFB. Machine Intelligence and Smart Systems: Proceedings of MISS 2021, 397–406. https://doi.org/10.1007/978-981-16-9650-3_31
Beaulieu, R., et al. (2015). The SIMON and SPECK families of lightweight block ciphers. DAC’15: Proceedings of the 52nd Annual Design Automation Conference, 175, 1–6. https://doi.org/10.1145/2744769.2747946
Biham, E., Shamir, A. (1991). Differential cryptanalysis of DES-like cryptosystems. Journal of CRYPTOLOGY, 4(1), 3–72.
Sarker, I. H. (2021). Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN Computer Science, 2 (6), 1–20. https://doi.org/10.1007/s42979-021-00815-1
He, K., et al. (2016). Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition, 770–778. https://doi.org/10.1109/CVPR.2016.90
Gohr, A. (2019). Improving attacks on round-reduced Speck32/64 using deep learning. CRYPTO 2019, LNCS, vol. 11693, 150–179. https://doi.org/10.1007/978-3-030-26951-7_6
Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-Excitation Networks. The Conference on Computer Vision and Pattern Recognition, IEEE, 7132–7141. https://doi.org/10.1109/CVPR.2018.00745
Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding machine learning: From theory to algorithms. Cambridge university press.
Chen, Y., & Yu, H. (2021). A New Neural Distinguisher Model Considering Derived Features from Multiple Ciphertext Pairs. The Computer Journal.
Hou, Z., Ren, J., & Chen, S. (2021). Improve neural distinguisher for cryptanalysis. Cryptology ePrint Archive.
Hulak, H. M., Zhiltsov, O. B., Kyrychok, R. V., Korshun, N. V., & Skladannyi, P. M. (2024). Information and cyber security of the enterprise. Textbook. Lviv: Publisher Marchenko T. V.
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Сюе Цзян, Валерій Лахно, Андрій Сагун , Сергій Мамченко
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
