Simon32/64神经网络差分区分器的优化
Optimization of Neural Differential Distinguishers for Simon32/64
DOI: 10.12677/mos.2025.144302, PDF,    国家自然科学基金支持
作者: 潘俊龙：上海理工大学光电信息与计算机工程学院，上海；刘 亚：上海理工大学光电信息与计算机工程学院，上海；香港狮子山网络安全实验室，香港；赵逢禹：上海出版印刷高等专科学校信息与智能工程系，上海；曲 博：港专学院网络空间科技学院，香港；刘先蓓：安徽财经大学统计与应用数学学院，安徽 蚌埠
关键词: Simon32/64；差分分析；神经区分器；倒数第二轮的多三面体输出差分；SENet；Simon32/64； Differential Analysis； Neural Distinguishers； Multiple 3-Polytope Output Difference Data Format in the Penultimate Round； SENet
摘要: Simon32/64是美国国安局推荐的轻量级分组密码，现有基于深度学习的差分分析研究多采用单一数据格式和网络模型，未充分挖掘其优化潜力。本文探讨五种输入数据格式与三种神经网络模型的协同效应对Simon32/64神经差分区分器性能的影响。首先，提出倒数第二轮的多三面体输出差分数据格式M3PODPR，并结合四种已有数据格式，与ResNet、带Inception模块的ResNet、SENet进行全组合实验，构建15种数据–模型组合架构，并分别在相同训练集大小和相同明文数据量下，构造神经区分器并进行性能测试。实验表明：在SENet和M3PODPR架构下，9到11轮Simon32/64神经差分区分器均取得最高准确率，优于所有其它组合架构，也优于现有Simon32/64神经区分器的其它结果。因此M3PODPR可有效提升神经区分器的准确率，为密码分析提供新的优化方向。
Abstract: Simon32/64 is a lightweight block cipher recommended by the National Security Agency (NSA). Existing studies on it against deep learning-based differential cryptanalysis primarily adopt a single data format and a network model, failing to fully exploit optimization potential. This paper investigates the synergistic effects of five input data formats and three neural network models on the performance of neural differential distinguishers for Simon32/64. Specifically, we propose the M3PODPR (Multiple 3-Polytope Output Difference Data Format in the Penultimate Round), evaluating the performance of M3PODPR and four existing data formats with ResNet, ResNet with Inception modules and SENet. A total of 15 data-model combinations are constructed and tested under identical training set sizes and plaintexts. Experimental results show that the SENet with M3PODPR architecture achieves the highest accuracy for 9 to 11 rounds of neural differential distinguishers for Simon32/64, outperforming all other combinations and existing results. Therefore, M3PODPR effectively enhances the accuracy of neural distinguishers, providing a new optimization direction for cryptanalysis.
文章引用：潘俊龙, 刘亚, 赵逢禹, 曲博, 刘先蓓. Simon32/64神经网络差分区分器的优化[J]. 建模与仿真, 2025, 14(4): 471-485. https://doi.org/10.12677/mos.2025.144302

参考文献

[1] Beaulieu, R., Shors, D., Smith, J., Treatman-Clark, S., Weeks, B. and Wingers, L. (2015) The SIMON and SPECK Lightweight Block Ciphers. Proceedings of the 52nd Annual Design Automation Conference, San Francisco, 7-11 June 2015, 1-6. [Google Scholar] [CrossRef] 
[2] 赵彦杰, 刘伟, 王伟, 等. 轻量级分组密码SIMON和SPECK的安全性分析[J]. 密码学报, 2017, 4(2): 75-85.
[3] 王旭姿. SIMON类型轻量级分组密码算法的安全性分析研究[D]: [博士学位论文]. 北京: 中国科学院大学, 2021.
[4] Biham, E. and Shamir, A. (1991) Differential Cryptanalysis of Des-Like Cryptosystems. Journal of Cryptology, 4, 3-72. [Google Scholar] [CrossRef] 
[5] Matsui, M. (1994) Linear Cryptanalysis Method for DES Cipher. In: Helleseth, T., Ed., Advances in Cryptology—EUROCRYPT’93, Springer, 386-397. [Google Scholar] [CrossRef] 
[6] 胡禹佳, 代政一, 孙兵. SIMON算法的差分-线性密码分析[J]. 信息网络安全, 2022, 22(9): 63-75.
[7] Gohr, A. (2019) Improving Attacks on Round-Reduced Speck32/64 Using Deep Learning. In: Boldyreva, A. and Micciancio, D., Eds., Advances in Cryptology—CRYPTO 2019, Springer, 150-179. [Google Scholar] [CrossRef] 
[8] Su, H., Zhu, X. and Ming, D. (2021) Polytopic Attack on Round-Reduced Simon32/64 Using Deep Learning. In: Wu, Y. and Yung, M., Eds., Information Security and Cryptology, Springer, 3-20. [Google Scholar] [CrossRef] 
[9] Hou, Z., Ren, J. and Chen, S. (2021) Improve Neural Distinguishers of SIMON and Speck. Security and Communication Networks, 2021, Article ID: 9288229. [Google Scholar] [CrossRef] 
[10] Bao, Z., Guo, J., Liu, M., Ma, L. and Tu, Y. (2022) Enhancing Differential-Neural Cryptanalysis. In: Agrawal, S. and Lin, D., Eds., Advances in Cryptology—ASIACRYPT 2022, Springer, 318-347. [Google Scholar] [CrossRef] 
[11] Chen, Y., Shen, Y., Yu, H. and Yuan, S. (2022) A New Neural Distinguisher Considering Features Derived from Multiple Ciphertext Pairs. The Computer Journal, 66, 1419-1433. [Google Scholar] [CrossRef] 
[12] Zhang, L., Wang, Z. and Wang, B. (2024) Improving Differential-Neural Cryptanalysis. IACR Communications in Cryptology, 1. [Google Scholar] [CrossRef] 
[13] He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef] 
[14] Szegedy, C., Liu, W., Jia, Y.Q., Sermanet, P., Reed, S., Anguelov, D., et al. (2015) Going Deeper with Convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 7-12 June 2015, 1-9. [Google Scholar] [CrossRef] 
[15] Hu, J., Shen, L. and Sun, G. (2018) Squeeze-and-Excitation Networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 7132-7141. [Google Scholar] [CrossRef] 
[16] Benamira, A., Gerault, D., Peyrin, T. and Tan, Q.Q. (2021) A Deeper Look at Machine Learning-Based Cryptanalysis. In: Canteaut, A. and Standaert, F.X., Eds., Advances in Cryptology—EUROCRYPT 2021, Springer, 805-835. [Google Scholar] [CrossRef] 

为你推荐