A machine learning approach to predicting block cipher security

Forecasting; Machine learning; Security of data; Turing machines; Block ciphers; Feistel structures; Hyperparameters; Machine learning approaches; Permutation patterns; Prediction accuracy; Security margins; Training data; Cryptography

Saved in:
Bibliographic Details
Main Authors: Lee T.R., Teh J.S., Yan J.L.S., Jamil N., Yeoh W.-Z.
Other Authors: 57219420025
Format: Conference Paper
Published: Institute for Mathematical Research (INSPEM) 2023
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-25664
record_format dspace
spelling my.uniten.dspace-256642023-05-29T16:12:25Z A machine learning approach to predicting block cipher security Lee T.R. Teh J.S. Yan J.L.S. Jamil N. Yeoh W.-Z. 57219420025 56579944200 57219413724 36682671900 57205056525 Forecasting; Machine learning; Security of data; Turing machines; Block ciphers; Feistel structures; Hyperparameters; Machine learning approaches; Permutation patterns; Prediction accuracy; Security margins; Training data; Cryptography Existing attempts in applying machine learning to cryptanalysis has seen limited success. This paper introduces an alternative approach in applying machine learning to block cipher cryptanalysis. Rather than trying to extract secret keys, machine learning classifiers are trained to predict a cipher's security margin with respect to the number of active s-boxes. Prediction is based on cipher features such as the number of rounds, permutation pattern, and truncated differences. Experiments are performed on a simplified generalised Feistel structure (GFS) block cipher. Prediction accuracy is optimised by refining how cipher features are represented as training data, and tuning hyperparameters. Results show that the machine learning classifiers are able formulate a relationship between the cipher features and security. When used to predict an unseen cipher (a cipher whose data was not used for training), an accuracy of up to 62% was obtained, depicting the feasibility of the proposed approach. � 2020 ACM. Final 2023-05-29T08:12:25Z 2023-05-29T08:12:25Z 2020 Conference Paper 2-s2.0-85092623519 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85092623519&partnerID=40&md5=366c9a75e525541dccdaf7fff0f7681e https://irepository.uniten.edu.my/handle/123456789/25664 122 132 Institute for Mathematical Research (INSPEM) Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
description Forecasting; Machine learning; Security of data; Turing machines; Block ciphers; Feistel structures; Hyperparameters; Machine learning approaches; Permutation patterns; Prediction accuracy; Security margins; Training data; Cryptography
author2 57219420025
author_facet 57219420025
Lee T.R.
Teh J.S.
Yan J.L.S.
Jamil N.
Yeoh W.-Z.
format Conference Paper
author Lee T.R.
Teh J.S.
Yan J.L.S.
Jamil N.
Yeoh W.-Z.
spellingShingle Lee T.R.
Teh J.S.
Yan J.L.S.
Jamil N.
Yeoh W.-Z.
A machine learning approach to predicting block cipher security
author_sort Lee T.R.
title A machine learning approach to predicting block cipher security
title_short A machine learning approach to predicting block cipher security
title_full A machine learning approach to predicting block cipher security
title_fullStr A machine learning approach to predicting block cipher security
title_full_unstemmed A machine learning approach to predicting block cipher security
title_sort machine learning approach to predicting block cipher security
publisher Institute for Mathematical Research (INSPEM)
publishDate 2023
_version_ 1806428078273986560
score 13.209306