To address the low classification accuracy of traditional convolutional neural distinguishers on ciphertext data, neural distinguisher based on convolutional network and self-attention structure is proposed. Firstly, a multi-scale convolutional network is designed to learn local features of ciphertext sequences. Secondly, the self-attention mechanism is introduced after the multi-scale convolutional network to enhance the ability of the neural distinguisher to capture long-range dependencies in ciphertext sequences. Finally, the neural distinguisher is trained on multiple ciphertext datasets. Experimental results show that the proposed neural distinguisher achieves higher classification accuracy than the previously superior neural distinguisher SE-ResNet on all eight ciphertext datasets. In particular, on 13-round SIMON64, the classification accuracy of the neural distinguisher is imperoved by 3.92% compared with that of SE-ResNet, demonstrating its more powerful ciphertext feature extraction capability.
GohrA. Improving attacks on round-reduced Speck32/64 using deep learning[C]//Advances in cryptology-CRYPTO 2019. Cham, Switzerlang: Springer, 2019:150-179.
ChenY, ShenY T, YuH B, et al. A new neural distinguisher considering features derived from multiple ciphertext pairs[J]. The Computer Journal, 2023,66(6):1419-1433.
[8]
BeaulieuR, Treatman-ClarkS, ShorsD, et al. The SIMON and SPECK lightweight block ciphers[C]//Proceedings of the 2015 52nd ACM/EDAC/IEEE design automation conference. Piscataway, USA: IEEE, 2015:1-6.
[9]
BogdanovA, KnudsenL R, LeanderG, et al. PRESENT: an ultra-lightweight block cipher[C]//Proceedings of the cryptographic hardware and embedded systems-CHES 2007. Berlin, Germany: Springer, 2007:450-466.
MouhaN, MenninkB, Van HerrewegeA, et al. Chaskey: an efficient MAC algorithm for 32-bit microcontrollers[C]//Proceedings of the selected areas in cryptography-SAC 2014. Cham, Switzerland: Springer, 2014:306-323.
[12]
HuangS Y, WangX Y, XuG W, et al. Conditional cube attack on reduced-round keccak sponge function[C]//Advances in cryptology-EUROCRYPT 2017. Cham, Switzerland: Springer, 2017:259-288.
[13]
LiuJ S, RenJ J, ChenS Z. A deep learning aided differential distinguisher improvement framework with more lightweight and universality[J]. Cybersecurity, 2023,6(1):47.
[14]
CholletF. Xception: deep learning with depthwise separable convolutions[C]//Proceedings of the 2017 IEEE conference on computer vision and pattern recognition. Piscataway, USA: IEEE, 2017:1800-1807.
[15]
YueX T, WuW Q. Improved neural differential distinguisher model for lightweight cipher speck[J]. Applied Sciences, 2023,13(12):6994.
[16]
BelliniE, GeraultD, HambitzerA, et al. A cipher-agnostic neural training pipeline with automated finding of good input differences[J]. IACR Transactions on Symmetric Cryptology, 2023:184-212.
[17]
WangG, WangG L. Enhanced related-key differential neural distinguishers for SIMON and SIMECK block ciphers[J]. PeerJ Computer Science, 2024,10:e2566.
[18]
HouY F, LiuJ, HanS X, et al. Improving deep learning-based neural distinguisher with multiple ciphertext pairs for speck and Simon[J]. Scientific Reports, 2025,15:13696.
[19]
ZhaoZ H, JiaY X, ZhangZ H. Multi-scale convolution multi-graph attention neural networks for traffic flow forecasting[C]//Proceedings of the 2024 16th international conference on machine learning and computing. New York, USA: ACM, 2024:176-184.
[20]
VaswaniA, ShazeerN, ParmarN, et al. Attention is all you need[C]//Advances in neural information processing systems. Red Hook, USA: Curran Associates Inc., 2017:5998-6008.
[21]
HeK M, ZhangX Y, RenS Q, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE conference on computer vision and pattern recognition. Piscataway, USA: IEEE, 2016:770-778.
[22]
ChenY, ShenY T, YuH B. Neural-aided statistical attack for cryptanalysis[J]. The Computer Journal, 2023,66(10):2480-2498.
[23]
HongD, LeeJ K, KimD C, et al. LEA: a 128-bit block cipher for fast encryption on common processors[C]//Proceedings of the Information security applications. Cham, Switzerland: Springer, 2014:3-27.
[24]
NeedhamR M, WheelerD J. Tea extensions[R]. Camberdge, England: Computer Laboratory, University of Cambridge, 1997.