New Results on Machine Learning-Based Distinguishers
Machine Learning (ML) is almost ubiquitously used in multiple disciplines nowadays. Recently, we have seen its usage in the realm of differential distinguishers for symmetric key ciphers. It has been shown that ML-based differential distinguishers can be easily extended to break round-reduced versio...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10108966/ |
| _version_ | 1797808485461655552 |
|---|---|
| author | Anubhab Baksi Jakub Breier Vishnu Asutosh Dasu Xiaolu Hou Hyunji Kim Hwajeong Seo |
| author_facet | Anubhab Baksi Jakub Breier Vishnu Asutosh Dasu Xiaolu Hou Hyunji Kim Hwajeong Seo |
| author_sort | Anubhab Baksi |
| collection | DOAJ |
| description | Machine Learning (ML) is almost ubiquitously used in multiple disciplines nowadays. Recently, we have seen its usage in the realm of differential distinguishers for symmetric key ciphers. It has been shown that ML-based differential distinguishers can be easily extended to break round-reduced versions of ciphers. In this paper, we show new distinguishers on the unkeyed and round-reduced versions of SPECK-32, SPECK-128, ASCON, SIMECK-32, SIMECK-64, and SKINNY-128. We explore multiple avenues in the process. In summary, we use neural networks and support vector machines in various settings (such as varying the activation function), apart from experimenting with a number of input difference tuples. Among other results, we show a distinguisher of 8-round SPECK-32 that works with low data complexity. |
| first_indexed | 2024-03-13T06:38:13Z |
| format | Article |
| id | doaj.art-8835f2ecc6d1456c9188a6a9cc8e996a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T06:38:13Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8835f2ecc6d1456c9188a6a9cc8e996a2023-06-08T23:01:26ZengIEEEIEEE Access2169-35362023-01-0111541755418710.1109/ACCESS.2023.327039610108966New Results on Machine Learning-Based DistinguishersAnubhab Baksi0https://orcid.org/0000-0002-5639-7372Jakub Breier1https://orcid.org/0000-0002-7844-5267Vishnu Asutosh Dasu2https://orcid.org/0000-0002-1849-1288Xiaolu Hou3https://orcid.org/0000-0002-4512-6921Hyunji Kim4https://orcid.org/0000-0001-9828-3894Hwajeong Seo5https://orcid.org/0000-0003-0069-9061Nanyang Technological University, Jurong West, SingaporeSilicon Austria Labs, TU-Graz SAL DES Lab, Graz, AustriaSchool of Electrical Engineering and Computer Science, The Pennsylvania State University, State College, PA, USAFaculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, SlovakiaDivision of IT Convergence Engineering, Hansung University, Seoul, South KoreaDivision of IT Convergence Engineering, Hansung University, Seoul, South KoreaMachine Learning (ML) is almost ubiquitously used in multiple disciplines nowadays. Recently, we have seen its usage in the realm of differential distinguishers for symmetric key ciphers. It has been shown that ML-based differential distinguishers can be easily extended to break round-reduced versions of ciphers. In this paper, we show new distinguishers on the unkeyed and round-reduced versions of SPECK-32, SPECK-128, ASCON, SIMECK-32, SIMECK-64, and SKINNY-128. We explore multiple avenues in the process. In summary, we use neural networks and support vector machines in various settings (such as varying the activation function), apart from experimenting with a number of input difference tuples. Among other results, we show a distinguisher of 8-round SPECK-32 that works with low data complexity.https://ieeexplore.ieee.org/document/10108966/Speckasconsimeckskinnydistinguishermachine learning |
| spellingShingle | Anubhab Baksi Jakub Breier Vishnu Asutosh Dasu Xiaolu Hou Hyunji Kim Hwajeong Seo New Results on Machine Learning-Based Distinguishers IEEE Access Speck ascon simeck skinny distinguisher machine learning |
| title | New Results on Machine Learning-Based Distinguishers |
| title_full | New Results on Machine Learning-Based Distinguishers |
| title_fullStr | New Results on Machine Learning-Based Distinguishers |
| title_full_unstemmed | New Results on Machine Learning-Based Distinguishers |
| title_short | New Results on Machine Learning-Based Distinguishers |
| title_sort | new results on machine learning based distinguishers |
| topic | Speck ascon simeck skinny distinguisher machine learning |
| url | https://ieeexplore.ieee.org/document/10108966/ |
| work_keys_str_mv | AT anubhabbaksi newresultsonmachinelearningbaseddistinguishers AT jakubbreier newresultsonmachinelearningbaseddistinguishers AT vishnuasutoshdasu newresultsonmachinelearningbaseddistinguishers AT xiaoluhou newresultsonmachinelearningbaseddistinguishers AT hyunjikim newresultsonmachinelearningbaseddistinguishers AT hwajeongseo newresultsonmachinelearningbaseddistinguishers |