Staff View: On the security of lightweight block ciphers against neural distinguishers: Observations on LBC-IoT and SLIM

On the security of lightweight block ciphers against neural distinguishers: Observations on LBC-IoT and SLIM

Interest in the application of deep learning in cryptography has increased immensely in recent years. Several works have shown that such attacks are not only feasible but, in some cases, are superior compared to classical cryptanalysis techniques. However, due to the black-box nature of deep learnin...

Full description

Saved in:

Bibliographic Details
Main Authors:	Teng W.J., Teh J.S., Jamil N.
Other Authors:	57193064876
Format:	Article
Published:	Elsevier Ltd 2024
Subjects:	Block cipher Deep learning Differential cryptanalysis Lightweight cryptography Neural distinguisher Neural network Internet of things Lyapunov methods Security of data Block ciphers Distinguishers Light-weight cryptography Lightweight block ciphers Neural-networks Round functions Round key Cryptography
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.uniten.dspace-34094
record_format	dspace
spelling	my.uniten.dspace-340942024-10-14T11:17:56Z On the security of lightweight block ciphers against neural distinguishers: Observations on LBC-IoT and SLIM Teng W.J. Teh J.S. Jamil N. 57193064876 56579944200 36682671900 Block cipher Deep learning Differential cryptanalysis Lightweight cryptography Neural distinguisher Neural network Deep learning Internet of things Lyapunov methods Security of data Block ciphers Deep learning Differential cryptanalysis Distinguishers Light-weight cryptography Lightweight block ciphers Neural distinguisher Neural-networks Round functions Round key Cryptography Interest in the application of deep learning in cryptography has increased immensely in recent years. Several works have shown that such attacks are not only feasible but, in some cases, are superior compared to classical cryptanalysis techniques. However, due to the black-box nature of deep learning models, more work is required to understand how they work in the context of cryptanalysis. In this paper, we contribute towards the latter by first constructing neural distinguishers for 2 different block ciphers, LBC-IoT and SLIM that share similar properties. We then show that, unlike classical differential cryptanalysis (on which neural distinguishers are based), the position where the round keys are included in round functions can have a significant impact on distinguishing probability. We explore this further to investigate if different choices of where the round key is introduced can lead to better resistance against neural distinguishers. We compare several variants of the round function to showcase this phenomenon, which is useful for securing future block cipher designs against deep learning attacks. As an additional contribution, the neural distinguisher for LBC-IoT was also applied in a practical-time key recovery attack on up to 8 rounds. Results show that even with no optimizations, the attack can consistently recover the correct round key with an attack complexity of around 224 full encryptions. To the best of our knowledge, this is the first third-party cryptanalysis results for LBC-IoT to date. � 2023 Elsevier Ltd Final 2024-10-14T03:17:56Z 2024-10-14T03:17:56Z 2023 Article 10.1016/j.jisa.2023.103531 2-s2.0-85163701461 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85163701461&doi=10.1016%2fj.jisa.2023.103531&partnerID=40&md5=9c7b0991af00647dd4771b7744a78c55 https://irepository.uniten.edu.my/handle/123456789/34094 76 103531 Elsevier Ltd 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/
topic	Block cipher Deep learning Differential cryptanalysis Lightweight cryptography Neural distinguisher Neural network Deep learning Internet of things Lyapunov methods Security of data Block ciphers Deep learning Differential cryptanalysis Distinguishers Light-weight cryptography Lightweight block ciphers Neural distinguisher Neural-networks Round functions Round key Cryptography
spellingShingle	Block cipher Deep learning Differential cryptanalysis Lightweight cryptography Neural distinguisher Neural network Deep learning Internet of things Lyapunov methods Security of data Block ciphers Deep learning Differential cryptanalysis Distinguishers Light-weight cryptography Lightweight block ciphers Neural distinguisher Neural-networks Round functions Round key Cryptography Teng W.J. Teh J.S. Jamil N. On the security of lightweight block ciphers against neural distinguishers: Observations on LBC-IoT and SLIM
description	Interest in the application of deep learning in cryptography has increased immensely in recent years. Several works have shown that such attacks are not only feasible but, in some cases, are superior compared to classical cryptanalysis techniques. However, due to the black-box nature of deep learning models, more work is required to understand how they work in the context of cryptanalysis. In this paper, we contribute towards the latter by first constructing neural distinguishers for 2 different block ciphers, LBC-IoT and SLIM that share similar properties. We then show that, unlike classical differential cryptanalysis (on which neural distinguishers are based), the position where the round keys are included in round functions can have a significant impact on distinguishing probability. We explore this further to investigate if different choices of where the round key is introduced can lead to better resistance against neural distinguishers. We compare several variants of the round function to showcase this phenomenon, which is useful for securing future block cipher designs against deep learning attacks. As an additional contribution, the neural distinguisher for LBC-IoT was also applied in a practical-time key recovery attack on up to 8 rounds. Results show that even with no optimizations, the attack can consistently recover the correct round key with an attack complexity of around 224 full encryptions. To the best of our knowledge, this is the first third-party cryptanalysis results for LBC-IoT to date. � 2023 Elsevier Ltd
author2	57193064876
author_facet	57193064876 Teng W.J. Teh J.S. Jamil N.
format	Article
author	Teng W.J. Teh J.S. Jamil N.
author_sort	Teng W.J.
title	On the security of lightweight block ciphers against neural distinguishers: Observations on LBC-IoT and SLIM
title_short	On the security of lightweight block ciphers against neural distinguishers: Observations on LBC-IoT and SLIM
title_full	On the security of lightweight block ciphers against neural distinguishers: Observations on LBC-IoT and SLIM
title_fullStr	On the security of lightweight block ciphers against neural distinguishers: Observations on LBC-IoT and SLIM
title_full_unstemmed	On the security of lightweight block ciphers against neural distinguishers: Observations on LBC-IoT and SLIM
title_sort	on the security of lightweight block ciphers against neural distinguishers: observations on lbc-iot and slim
publisher	Elsevier Ltd
publishDate	2024
_version_	1814060057298468864
score	13.222552

On the security of lightweight block ciphers against neural distinguishers: Observations on LBC-IoT and SLIM

Similar Items