Publication:
Lightweight block cipher security evaluation based on machine learning classifiers and active s-boxes

dc.citedby3
dc.contributor.authorLee T.R.en_US
dc.contributor.authorTeh J.S.en_US
dc.contributor.authorJamil N.en_US
dc.contributor.authorYan J.L.S.en_US
dc.contributor.authorChen J.en_US
dc.contributor.authorid57219420025en_US
dc.contributor.authorid56579944200en_US
dc.contributor.authorid36682671900en_US
dc.contributor.authorid57219413724en_US
dc.contributor.authorid36561132000en_US
dc.date.accessioned2023-05-29T09:11:08Z
dc.date.available2023-05-29T09:11:08Z
dc.date.issued2021
dc.descriptionDecision trees; Lyapunov methods; Machine learning; Nearest neighbor search; Security of data; Active S-box; Block ciphers; Cryptanalyse; Differential cryptanalysis; Feistel ciphers; Generalized feistel; Light-weight cryptography; Machine learning models; S-boxes; Security evaluation; Cryptographyen_US
dc.description.abstractMachine learning has recently started to gain the attention of cryptographic researchers, notably in block cipher cryptanalysis. Most of these machine learning-based approaches are black box attacks that are cipher-specific. Thus, more research is required to understand the capabilities and limitations of machine learning when being used to evaluate block cipher security. We contribute to this body of knowledge by investigating the capability of linear and nonlinear machine learning classifiers in evaluating block cipher security. We frame block cipher security evaluation as a classification problem, whereby the machine learning models attempt to classify a given block cipher output as secure or insecure based on the number of active S-boxes. We also train the machine learning models with common block cipher features such as truncated differences, the number of rounds, and permutation pattern. Various experiments were performed on small-scale (4-branch) generalized Feistel ciphers to identify the best performing machine learning model for the given security evaluation problem. Results show that nonlinear machine learning models outperform linear models, achieving a prediction accuracy of up to 93% when evaluating inputs from ciphers that they have seen before during training. When evaluating inputs from other unseen ciphers, nonlinear models again outperformed linear models with an accuracy of up to 71%. We then showcase the feasibility of our approach when used to evaluate a real-world 16-branch generalized Feistel cipher, TWINE. By training the best performing nonlinear classifiers (k-nearest neighbour and decision tree) using data from other similar ciphers, the nonlinear classifiers achieved a 74% accuracy when evaluating differential data generated from TWINE. In addition, the trained classifiers were capable of generalizing to a larger number of rounds than they were trained for. Our findings showcase the feasibility of using simple machine learning classifiers as a security evaluation tool to assess block cipher security. � 2013 IEEE.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.1109/ACCESS.2021.3116468
dc.identifier.epage134064
dc.identifier.scopus2-s2.0-85116977335
dc.identifier.spage134052
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85116977335&doi=10.1109%2fACCESS.2021.3116468&partnerID=40&md5=c088382b2319778a2e89ac987c60ccec
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/26490
dc.identifier.volume9
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofAll Open Access, Gold
dc.sourceScopus
dc.sourcetitleIEEE Access
dc.titleLightweight block cipher security evaluation based on machine learning classifiers and active s-boxesen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections