Machine Learning Assisted Differential Distinguishers For Lightweight Ciphers

被引:0
作者
Baksi, Anubhab [1 ]
Breier, Jakub [2 ,3 ]
Chen, Yi [4 ]
Dong, Xiaoyang [4 ]
机构
[1] Nanyang Technol Univ, Singapore, Singapore
[2] TU Graz SAL DES Lab, Silicon Austria Labs, Graz, Austria
[3] Graz Univ Technol, Graz, Austria
[4] Tsinghua Univ, Beijing, Peoples R China
来源
PROCEEDINGS OF THE 2021 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2021) | 2021年
关键词
gimli; ascon; knot; chaskey; distinguisher; machine learning; differential;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
At CRYPTO 2019, Gohr first introduces the deep learning based cryptanalysis on round-reduced SPECK. Using a deep residual network, Gohr trains several neural network based distinguishers on 8-round SPECK-32/64. The analysis follows an 'all-in-one' differential cryptanalysis approach, which considers all the output differences effect under the same input difference. Usually, the all-in-one differential cryptanalysis is more effective compared to the one using only one single differential trail. However, when the cipher is non-Markov or its block size is large, it is usually very hard to fully compute. Inspired by Gohr's work, we try to simulate the all-in-one differentials for non-Markov ciphers through machine learning. Our idea here is to reduce a distinguishing problem to a classification problem, so that it can be efficiently managed by machine learning. As a proof of concept, we show several distinguishers for four high profile ciphers, each of which works with trivial complexity. In particular, we show differential distinguishers for 8-round Gimli-Hash, Gimli-Cipher and Gimli-Permutation; 3-round Ascon-Permutation; 10-round Knot-256 permutation and 12-round Knot-512 permutation; and 4-round Chaskey-Permutation. Finally, we explore more on choosing an efficient machine learning model and observe that only a three layer neural network can be used. Our analysis shows the attacker is able to reduce the complexity of finding distinguishers by using machine learning techniques.
引用
收藏
页码:176 / 181
页数:6
相关论文
共 50 条
[41]   Recent Advances in Machine Learning for Differential Cryptanalysis [J].
Martinez, Isabella ;
Lopez, Valentina ;
Rambaut, Daniel ;
Obando, German ;
Gauthier-Umana, Valerie ;
Perez, Juan F. .
ADVANCES IN COMPUTING, CCC 2023, 2024, 1924 :45-56
[42]   Impossible Differential Cryptanalysis on Gimli/Xoodoo Ciphers [J].
Fan, Ting ;
Wei, Yongzhuang ;
Li, Lingchen .
JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2023, 45 (10) :3729-3736
[43]   Lightweight and Secure PUF Key Storage Using Limits of Machine Learning [J].
Yu, Meng-Day ;
M'Raihi, David ;
Sowell, Richard ;
Devadas, Srinivas .
CRYPTOGRAPHIC HARDWARE AND EMBEDDED SYSTEMS - CHES 2011, 2011, 6917 :358-+
[44]   Damage detection in lightweight bridges with traveling masses using machine learning [J].
Dadoulis, Georgios ;
Manolis, George D. ;
Katakalos, Konstantinos ;
Dragos, Kosmas ;
Smarsly, Kay .
ENGINEERING STRUCTURES, 2025, 322
[45]   MiniMalloc: A Lightweight Memory Allocator for Hardware-Accelerated Machine Learning [J].
Moffitt, Michael D. .
PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS, ASPLOS 2023, VOL 4, 2023, :238-252
[46]   Lightweight Machine Learning-Based Approach for Supervision of Fitness Workout [J].
Depari, A. ;
Ferrari, P. ;
Flammini, A. ;
Rinaldi, S. ;
Sisinni, E. .
2019 IEEE SENSORS APPLICATIONS SYMPOSIUM (SAS), 2019,
[47]   Lightweight Machine Learning Method for Real-Time Espresso Analysis [J].
Choi, Jintak ;
Lee, Seungeun ;
Kang, Kyungtae ;
Suh, Hyojoong .
ELECTRONICS, 2024, 13 (04)
[48]   A study on lightweight Extreme Learning Machine algorithm for edge-computing [J].
Mouri, Kouki ;
Kumaki, Takeshi .
2024 INTERNATIONAL TECHNICAL CONFERENCE ON CIRCUITS/SYSTEMS, COMPUTERS, AND COMMUNICATIONS, ITC-CSCC 2024, 2024,
[49]   Harnessing machine learning for predicting mechanical properties of lightweight Mg alloys [J].
Jain, Sandeep ;
Jain, Reliance ;
Patel, Mahesh ;
Sahoo, Baidehish ;
Bhowmik, Ayan .
MATERIALS LETTERS, 2025, 378
[50]   A Lightweight Model for DDoS Attack Detection Using Machine Learning Techniques [J].
Sadhwani, Sapna ;
Manibalan, Baranidharan ;
Muthalagu, Raja ;
Pawar, Pranav .
APPLIED SCIENCES-BASEL, 2023, 13 (17)