DOI:
https://doi.org/10.64539/sjer.v2i4.2026.491Keywords:
Deep Learning, Differential Analysis, Block Cipher, Neural Distinguisher, GIFT-128, ASCONAbstract
Differential analysis is a pivotal method for assessing the security of block ciphers; it distinguishes a cipher from a random permutation by tracing the propagation of plaintext differences. Traditional analytical methods face limitations when applied to complex algorithms, whereas the feature extraction capabilities of deep learning have opened up new avenues for cryptanalysis. To facilitate the security assessment of block ciphers, this paper proposes a novel construction method for a neural differential distinguisher that integrates traditional differential analysis with deep learning techniques. Regarding dataset construction, a multi-ciphertext-pair triplet input format is adopted to preserve differential features while capturing correlations across ciphertext pairs. The network architecture is based on Convolutional Neural Networks (CNNs) and incorporates a Residual Shrinkage Network to construct a deep dilated structure and a multi-scale feature fusion mechanism. Experimental results on the GIFT-128 and ASCON-PERMUTATION lightweight permutation-based cryptographic algorithm demonstrate the efficacy of this approach: for GIFT-128, the 6-round distinguisher reached a maximum accuracy of 99.70%, and the 7-round distinguisher reached 95.47% when using 32 ciphertext pairs; for the 4-round analysis of ASCON, the accuracy rate reached a maximum of 53.54%. These results validate the effectiveness of deep learning methods in the analysis of cryptographic security.
References
[1] E. Biham and A. Shamir, “Differential cryptanalysis of DES-like cryptosystems,” Journal of Cryptology, vol. 4, pp. 3–72, 1991. https://doi.org/10.1007/BF00630563.
[2] X. Lai, “Higher order derivatives and differential cryptanalysis,” Communications and Cryptography, 1994, pp. 227–233. https://doi.org/10.1007/978-1-4615-2694-0_23.
[3] E. Biham, A. Biryukov, and A. Shamir, “Cryptanalysis of Skipjack reduced to 31 rounds using impossible differentials,” in Advances in Cryptology EUROCRYPT ’99. Berlin: Springer, 1999, vol. 1592, pp. 12–23. https://doi.org/10.1007/3-540-48910-X_2.
[4] E. Biham, “New types of cryptanalytic attacks using related keys,” Journal of Cryptology, vol. 7, pp. 229–246, 1994. https://doi.org/10.1007/BF00203965.
[5] A. Gohr, “Improving attacks on round-reduced Speck32/64 using deep learning,” in Advances in Cryptology—CRYPTO 2019, 2019, pp. 150–179. https://doi.org/10.1007/978-3-030-26951-7_6.
[6] Y. Chen and H. Yu, “A new neural distinguisher model considering derived features from multiple ciphertext pairs,” The Computer Journal, vol. 66, no. 6, pp. 1419–1433, 2023. https://doi.org/10.1093/comjnl/bxac019.
[7] Z. Hou, J. Ren, and S. Chen, “Improved neural distinguisher for cryptanalysis,” [Online]. Available: https://eprint.iacr.org/2021/1017.
[8] J. Lu, G. Liu, B. Sun, et al., “Improved (related-key) differential-based neural distinguishers for SIMON and SIMECK block ciphers,” The Computer Journal, vol. 67, no. 2, pp. 537–547, 2024. https://doi.org/10.1093/comjnl/bxac195.
[9] Z. Bao, J. Lu, Y. Yao, L. Zhang, “More insight on deep learning-aided cryptanalysis,” in Proceedings of the International Conference on the Theory and Application of Cryptology and Information Security. Singapore: Springer, 2023, pp. 436–467. https://doi.org/10.1007/978-981-99-8727-6_15.
[10] D. Shen et al., “Neural differential distinguishers for GIFT-128 and ASCON,” Journal of Information Security and Applications, vol. 82, p. 103758, 2024. https://doi.org/10.1016/j.jisa.2024.103758.
[11] L. Zhang, Z. L. Wang, and B. C. Wang, “Improving differential-neural cryptanalysis,” IACR Communications in Cryptology, vol. 1, no. 3, p. 13, 2024. https://doi.org/10.62056/ay11wa3y6.
[12] G. Wang, G. Wang, and S. Sun, “Investigating and enhancing the neural distinguisher for differential cryptanalysis,” IEICE Transactions on Information and Systems, vol. 107, pp. 1016–1028, 2024. https://doi.org/10.1587/transinf.2024EDP7011.
[13] B. Seok and C. Lee, “A novel approach to construct a good dataset for differential-neural cryptanalysis,” IEEE Transactions on Dependable and Secure Computing, vol. 22, no. 1, pp. 246–262, 2024. https://doi.org/10.1109/TDSC.2024.3387662.
[14] Y. Banga, Y. Mahmood, N. Al Mudawi, N. Innab, N. Iqbal, and H. Diab, “Where octagonal geometry meets chaos: A new S-box for advanced cryptographic systems,” PLoS One, vol. 20, no. 6, Jun. 2025. https://doi.org/10.1371/journal.pone.0320457.
[15] Y. S. Vaz, J. C. B. Mattos, and R. I. Soares, “High throughput-to-area AES: The role of small S-box in lightweight cryptographic design,” in Proc. 2025 IEEE 16th Latin American Symposium on Circuits and Systems (LASCAS), 2025. https://doi.org/10.1109/LASCAS64004.2025.10966232.
[16] P. S. Curlin, J. Heiges, C. Chan, and T. S. Lehman, “A survey of hardware-based AES S-boxes: Area, performance, and security,” ACM Computing Surveys, vol. 57, no. 9, Apr. 2025. https://doi.org/10.1145/3724114.
[17] A. H. Zahid, M. J. Arshad, M. Ahmad, N. F. Soliman, and W. El-Shafai, “Dynamic S-box generation using novel chaotic map with nonlinearity tweaking,” Computers, Materials and Continua, vol. 75, no. 2, pp. 3011–3026, 2023. https://doi.org/10.32604/cmc.2023.037516.
[18] S. Banik et al., “GIFT: A small present: Towards reaching the limit of lightweight encryption,” in Proceedings of Cryptographic Hardware and Embedded Systems. Springer, 2017, pp. 321–345. https://doi.org/10.1007/978-3-319-66787-4_16.
[19] C. Dobraunig, M. Eichlseder, F. Mendel, et al., “Ascon v1.2: Lightweight authenticated encryption and hashing,” Journal of Cryptology, vol. 34, pp. 1–42, 2021. https://doi.org/10.1007/s00145-021-09398-9.
[20] M. F. Khan, K. Saleem, T. Shah, M. M. Hazzazi, I. Bahkali, and P. K. Shukla, “Block cipher’s substitution box generation based on natural randomness in underwater acoustics and knight’s tour chain,” Computational Intelligence and Neuroscience, vol. 2022, 2022. https://doi.org/10.1155/2022/8338508.
[21] S. Alali, M. K. Jamil, R. Ali, R. Alotaibi, and W. Albalawi, “Degree, closeness and eigenvector for the construction of cryptographically secure S-boxes,” Ain Shams Engineering Journal, vol. 16, no. 10, Oct. 2025. https://doi.org/10.1016/j.asej.2025.103559.
[22] J. Ye and Y. Chen, “SC-SA: Byte-oriented lightweight stream ciphers based on S-box substitution,” Symmetry, vol. 16, no. 8, Aug. 2024. https://doi.org/10.3390/sym16081051.
[23] S. S. Jamal, R. Ali, M. K. Jamil, S. A. Nooh, F. Alblehai, and Gulraiz, “Secure S-box construction with 1D chaotic maps and finite field theory for block cipher encryption,” Alexandria Engineering Journal, vol. 125, pp. 278–296, Jun. 2025. https://doi.org/10.1016/j.aej.2025.03.109.
[24] M. R. Saleem, A. H. Zahid, and G. Mustafa, “Dynamic S-box construction based on a novel chaotic map and twitching approach,” Mehran University of Engineering and Technology Research Journal, vol. 44, no. 4, pp. 101–119, 2025. https://doi.org/10.22581/muet1982.0354.
[25] M. Ahmad, H. Zhou, T. Bibi, and H. Ali, “A review of cryptographic solutions and forensic readiness in IoT and network security,” International Journal of Science, Engineering and Technology, vol. 14, no. 2, 2026. https://doi.org/10.5281/zenodo.19449141.
[26] A. Benamira, D. Gerault, T. Peyrin, et al., “A deeper look at machine learning-based cryptanalysis,” in Advances in Cryptology—EUROCRYPT 2021. Cham: Springer, 2021, pp. 436–467. https://doi.org/10.1007/978-3-030-77870-5_28.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Ahmad, Hua Zhou, Muhammad Usman, Tanzeela Bibi, Haider Ali, Maryum Shahzadi, Farah Javed
This work is licensed under a Creative Commons Attribution 4.0 International License.
