Assessing Lightweight Block Cipher Security using Linear and Nonlinear Machine Learning Classifiers

Ting Rong Lee; Je Sen Teh; Norziana Jamil; Jasy Liew Suet Yan; Jiageng Chen

Paper 2020/1235

Assessing Lightweight Block Cipher Security using Linear and Nonlinear Machine Learning Classifiers

Ting Rong Lee, Je Sen Teh, Norziana Jamil, Jasy Liew Suet Yan, and Jiageng Chen

Abstract

In this paper, we investigate the use of machine learning classifiers to assess block cipher security from the perspective of differential cryptanalysis. These classifiers were trained using common block cipher features (number of rounds, permutation pattern, truncated input and output differences), making our approach generalizable to an entire class of ciphers. Each data sample represents a truncated differential path, for which the level of security is labelled as secure or insecure by the trained classifier based on the number of differentially active S-boxes. We trained six machine learning classifiers (linear and nonlinear) to perform the security prediction task using a dataset generated from a small-scale generalized Feistel structure (GFS) cipher as a proof-of-concept. Prediction accuracy was further refined by determining the best way to represent features in the dataset during training. We then studied how well these classifiers perform the prediction tasks on ciphers that they were trained on (seen) and those that they were not (unseen). When applied on seen ciphers, the classifiers achieved prediction accuracy results of up to 93% whereas for unseen cipher variants, accuracy results of up to 71% were obtained. Our findings indicate that nonlinear classifiers are better suited for the prediction task. Next, we applied the proposed approach to a full-scale lightweight GFS block cipher, TWINE. By training the best performing nonlinear classifiers (k-nearest neighbour and decision tree classifiers) using data from five other GFS ciphers, we obtained an accuracy of up to 74% when labelling data from TWINE. In addition, the trained classifiers could generalize to a larger number of rounds of TWINE despite being trained using data obtained from fewer rounds. These findings showcase the feasibility of using machine learning classifiers, notably nonlinear variants, as a tool to assess block cipher security.

Note: As of publishing this ePrint, the manuscript has been submitted to IEEE Access for consideration.

Metadata

Available format(s): PDF
Category: Secret-key cryptography
Publication info: Published elsewhere. IEEE Access
DOI: 10.1109/ACCESS.2021.3116468
Keywords: Block ciphers cryptanalysis machine learning
Contact author(s): jesen_teh @ hotmail com
jesen_teh @ usm my
History: 2021-10-04: last of 11 revisions; 2020-10-09: received; See all versions
Short URL: https://ia.cr/2020/1235
License: CC BY

BibTeX

@misc{cryptoeprint:2020/1235,
      author = {Ting Rong Lee and Je Sen Teh and Norziana Jamil and Jasy Liew Suet Yan and Jiageng Chen},
      title = {Assessing Lightweight Block Cipher Security using Linear and Nonlinear Machine Learning Classifiers},
      howpublished = {Cryptology {ePrint} Archive, Paper 2020/1235},
      year = {2020},
      doi = {10.1109/ACCESS.2021.3116468},
      url = {https://eprint.iacr.org/2020/1235}
}