Paper 2022/1195
A Deep Neural Differential Distinguisher for ARX based Block Cipher
Abstract
Over the last few years, deep learning is becoming the most trending topic for the classical cryptanalysis of block ciphers. Differential cryptanalysis is one of the primary and potent attacks on block ciphers. Here we apply deep learning techniques to model differential cryptanalysis more easily. In this paper, we report a generic tool using deep neural classifier that assists to find differential distinguishers for block ciphers with reduced round. We apply this approach for the differential cryptanalysis of ARX- based encryption schemes HIGHT, LEA, and SPARX. The result shows that our deep learning based distinguishers work with high accuracy for 14-round HIGHT, 13-Round LEA and 11-round SPARX. We also achieve an improvement of the lower bound of data complexity for these three ARX based ciphers.
Metadata
- Available format(s)
-
PDF
- Category
- Attacks and cryptanalysis
- Publication info
- Preprint.
- Keywords
- HIGHT LEA SPARX Neural Distinguisher Deep Learning Differential Cryptanalysis
- Contact author(s)
-
debranjan crl @ gmail com
mandal up98 @ gmail com
mainakcacsgu @ gmail com
abhij @ cse iitkgp ac in
drc @ cse iitkgp ac in - History
- 2022-09-12: approved
- 2022-09-10: received
- See all versions
- Short URL
- https://ia.cr/2022/1195
- License
-
CC BY-NC-SA
BibTeX
@misc{cryptoeprint:2022/1195, author = {Debranjan Pal and Upasana Mandal and Mainak Chaudhury and Abhijit Das and Dipanwita Roy Chowdhury}, title = {A Deep Neural Differential Distinguisher for ARX based Block Cipher}, howpublished = {Cryptology ePrint Archive, Paper 2022/1195}, year = {2022}, note = {\url{https://eprint.iacr.org/2022/1195}}, url = {https://eprint.iacr.org/2022/1195} }