Paper 2022/457
Improving Differential-Neural Distinguisher Model For DES, Chaskey and PRESENT
Liu Zhang and Zilong Wang
Abstract
In CRYPTO'19, Gohr proposed a new cryptanalysis strategy using machine learning algorithms. Combining the differential-neural distinguisher with a differential path and integrating the advanced key recovery procedure, Gohr achieved a 12-round key recovery attack on Speck32/64. Chen and Yu improved prediction accuracy of differential-neural distinguisher considering derived features from multiple-ciphertext pairs instead of single-ciphertext pairs. By modifying the kernel size of initial convolutional layer to capture more dimensional information, the prediction accuracy of differential-neural distinguisher can be improved for for three reduced symmetric ciphers. For DES, we improve the prediction accuracy of (5-6)-round differential-neural distinguisher and train a new 7-round differential-neural distinguisher. For Chaskey, we improve the prediction accuracy of (3-4)-round differential-neural distinguisher. For PRESENT, we improve the prediction accuracy of (6-7)-round differential-neural distinguisher. The source codes are available in https://drive.google.com/drive/folders/1i0RciZlGZsEpCyW-wQAy7zzJeOLJNWqL?usp=sharing.
Metadata
- Available format(s)
-
PDF
- Publication info
- Preprint. Minor revision.
- Keywords
- Differential-Neural DistinguisherInception BlocksDESChaskeyPRESENT
- Contact author(s)
- 17lzhang3 @ gmail com
- History
- 2022-04-14: revised
- 2022-04-12: received
- See all versions
- Short URL
- https://ia.cr/2022/457
- License
-
CC BY
BibTeX
@misc{cryptoeprint:2022/457,
author = {Liu Zhang and Zilong Wang},
title = {Improving Differential-Neural Distinguisher Model For DES, Chaskey and PRESENT},
howpublished = {Cryptology ePrint Archive, Paper 2022/457},
year = {2022},
note = {\url{https://eprint.iacr.org/2022/457}},
url = {https://eprint.iacr.org/2022/457}
}
