{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T04:15:17Z","timestamp":1778040917823,"version":"3.51.4"},"reference-count":29,"publisher":"International Association for Cryptologic Research","issue":"1","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IACR CiC"],"accepted":{"date-parts":[[2026,4,12]]},"abstract":"<jats:p>At CRYPTO 2019, Gohr pioneered neural cryptanalysis by introducing differential-based neural distinguishers to attack Speck32\/64, establishing a novel paradigm combining deep learning with differential cryptanalysis. Since then, constructing neural distinguishers has become a significant approach to achieving the deep learning-based cryptanalysis for block ciphers. This paper advances rotational-XOR (RX) attacks through neural networks, focusing on optimizing distinguishers and presenting key-recovery attacks for the lightweight block ciphers Simon32\/64 and Simeck32\/64. In particular, we first construct the fundamental data formats specially designed for training RX-neural distinguishers by refining the existing data formats for differential-neural distinguishers. Based on these data formats, we systematically identify optimal RX-differences with Hamming weights 1 and 2 that develop high-accuracy RX-neural distinguishers. Then, through innovative application of the bit sensitivity test, we achieve significant compression of data format without sacrificing the distinguisher accuracy. This optimization enables us to add more multi-ciphertext pairs into the data formats, further strengthening the performance of RX-neural distinguishers. As an application, we obtain 14- and 17-round RX-neural distinguishers for Simon32\/64 and Simeck32\/64, which improves the previous ones by 3 and 2 rounds, respectively. In addition, we propose two novel techniques, key bit sensitivity test and the joint wrong key response, to tackle the challenge of applying Bayesian's key-recovery strategy to the target cipher that adopts nonlinear key schedule in the related-key setting without considering of weak-key space. By this, we can straightforwardly mount a 17-round key-recovery attack on Simeck32\/64 based on the improved 16-round RX-neural distinguisher. To the best of our knowledge, the presented RX-neural distinguishers outperform the state-of-the-art neural-based distinguishers for both Simon32\/64 and Simeck32\/64, and this is the first successful neural-based key-recovery attack for Simeck32\/64 under the related-key setting.<\/jats:p>","DOI":"10.62056\/abksdkmol","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T18:09:08Z","timestamp":1777918148000},"update-policy":"https:\/\/doi.org\/10.62056\/adfjwm02dj","source":"Crossref","is-referenced-by-count":0,"title":["Improved Deep Learning-Based Rotational-XOR Attacks on Simon32\/64 and Simeck32\/64"],"prefix":"10.62056","volume":"3","author":[{"given":"Chengcai","family":"Liu","sequence":"first","affiliation":[{"name":"School of Cyber Science and Technology, Hubei University","place":["Wuhan, Hubei, 430062, China"]},{"name":"Key Laboratory of Intelligent Sensing System and Security, Ministry of Education, Hubei University","place":["Wuhan, Hubei, 430062, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3428-7647","authenticated-orcid":false,"given":"Siwei","family":"Chen*","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Hubei University","place":["Wuhan, Hubei, 430062, China"]},{"name":"Key Laboratory of Intelligent Sensing System and Security, Ministry of Education, Hubei University","place":["Wuhan, Hubei, 430062, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zejun","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Hubei University","place":["Wuhan, Hubei, 430062, China"]},{"name":"Key Laboratory of Intelligent Sensing System and Security, Ministry of Education, Hubei University","place":["Wuhan, Hubei, 430062, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyong","family":"Zeng","sequence":"additional","affiliation":[{"name":"Faculty of Mathematics and Statistics, Hubei Key Laboratory of Applied Mathematics, Hubei University","place":["Wuhan, Hubei, 430062, China"]},{"name":"Key Laboratory of Intelligent Sensing System and Security, Ministry of Education, Hubei University","place":["Wuhan, Hubei, 430062, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"48349","published-online":{"date-parts":[[2026,5,4]]},"reference":[{"key":"ref1:timon2018non","doi-asserted-by":"publisher","first-page":"107","DOI":"10.13154\/TCHES.V2019.I2.107-131","article-title":"Non-Profiled Deep Learning-based Side-Channel attacks with\n  Sensitivity Analysis","volume":"2019","author":"Benjamin Timon","year":"2019","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref2:kim2019make","doi-asserted-by":"publisher","first-page":"148","DOI":"10.13154\/TCHES.V2019.I3.148-179","article-title":"Make Some Noise. Unleashing the Power of Convolutional\n  Neural Networks for Profiled Side-channel Analysis","volume":"2019","author":"Jaehun Kim","year":"2019","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref3:DBLP:journals\/tifs\/WuWKLPBP23","doi-asserted-by":"publisher","first-page":"3849","DOI":"10.1109\/TIFS.2023.3287728","article-title":"Label Correlation in Deep Learning-Based Side-Channel\n  Analysis","volume":"18","author":"Lichao Wu","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref4:DBLP:journals\/tifs\/KimHKSH24","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.1109\/TIFS.2023.3340088","article-title":"Deep Learning-Based Detection for Multiple Cache\n  Side-Channel Attacks","volume":"19","author":"Hodong Kim","year":"2024","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref5:rivest1991cryptography","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/3-540-57332-1_36","article-title":"Cryptography and Machine Learning","author":"Ronald L. Rivest","year":"1991"},{"key":"ref6:biham1991differential","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/BF00630563","article-title":"Differential Cryptanalysis of DES-like Cryptosystems","volume":"4","author":"Eli Biham","year":"1991","journal-title":"J. Cryptol."},{"key":"ref7:matsui1993linear","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1007\/3-540-48285-7_33","article-title":"Linear Cryptanalysis Method for DES Cipher","author":"Mitsuru Matsui","year":"1993"},{"key":"ref8:ashur2016rotational","doi-asserted-by":"publisher","first-page":"57","DOI":"10.13154\/TOSC.V2016.I1.57-70","article-title":"Rotational Cryptanalysis in the Presence of Constants","volume":"2016","author":"Tomer Ashur","year":"2016","journal-title":"IACR Trans. Symmetric Cryptol."},{"key":"ref9:gohr2019improving","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/978-3-030-26951-7_6","article-title":"Improving Attacks on Round-Reduced Speck32\/64 Using Deep\n  Learning","author":"Aron Gohr","year":"2019"},{"key":"ref10:DBLP:conf\/date\/BaksiBCD21","doi-asserted-by":"publisher","first-page":"176","DOI":"10.23919\/DATE51398.2021.9474092","article-title":"Machine Learning Assisted Differential Distinguishers For\n  Lightweight Ciphers","author":"Anubhab Baksi","year":"2021"},{"key":"ref11:hou2020linear","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/978-3-030-59013-0_7","article-title":"Linear Attack on Round-Reduced DES Using Deep Learning","author":"Botao Hou","year":"2020"},{"key":"ref12:zahednejad2022improved","doi-asserted-by":"publisher","first-page":"7584","DOI":"10.1002\/INT.22895","article-title":"An improved integral distinguisher scheme based on neural\n  networks","volume":"37","author":"Behnam Zahednejad","year":"2022","journal-title":"Int. J. Intell. Syst."},{"key":"ref13:palmierideep","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/978-3-031-53368-6_21","article-title":"Deep Learning-Based Rotational-XOR Distinguishers for\n  AND-RX Block Ciphers: Evaluations on Simeck and Simon","author":"Amirhossein Ebrahimi","year":"2023"},{"key":"ref14:chen2023new","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1093\/COMJNL\/BXAC019","article-title":"A New Neural Distinguisher Considering Features Derived From\n  Multiple Ciphertext Pairs","volume":"66","author":"Yi Chen","year":"2023","journal-title":"Comput. J."},{"key":"ref15:gohr2022assessment","first-page":"1521","article-title":"An Assessment of Differential-Neural Distinguishers","volume":"2022","author":"Aron Gohr","year":"2022","journal-title":"IACR Cryptol. ePrint Arch."},{"key":"ref16:bao2023more","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-981-99-8727-6_15","article-title":"More Insight on Deep Learning-Aided Cryptanalysis","author":"Zhenzhen Bao","year":"2023"},{"key":"ref17:chen2020neural","doi-asserted-by":"publisher","first-page":"2480","DOI":"10.1093\/COMJNL\/BXAC099","article-title":"Neural-Aided Statistical Attack for Cryptanalysis","volume":"66","author":"Yi Chen","year":"2023","journal-title":"Comput. J."},{"key":"ref18:lu2022improved","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1093\/COMJNL\/BXAC195","article-title":"Improved (Related-Key) Differential-Based Neural\n  Distinguishers for SIMON and SIMECK Block Ciphers","volume":"67","author":"Jinyu Lu","year":"2024","journal-title":"Comput. J."},{"key":"ref19:zhang2022improving","doi-asserted-by":"publisher","first-page":"13","DOI":"10.62056\/AY11WA3Y6","article-title":"Improving Differential-Neural Cryptanalysis","volume":"1","author":"Liu Zhang","year":"2024","journal-title":"IACR Commun. Cryptol."},{"key":"ref20:DBLP:journals\/tosc\/HouBLC25","doi-asserted-by":"publisher","first-page":"755","DOI":"10.46586\/TOSC.V2025.I3.755-799","article-title":"Observations on the BayesianKeySearch with Applications to\n  Simon and Simeck","volume":"2025","author":"Zezhou Hou","year":"2025","journal-title":"IACR Trans. Symmetric Cryptol."},{"key":"ref21:yuan2025multi","first-page":"697","volume-title":"A Multi-Differential Approach to Enhance Related-Key Neural\n  Distinguishers","volume":"2025","author":"Xue Yuan","year":"2025","journal-title":"IACR Cryptol. ePrint Arch."},{"key":"ref22:zhang2023improved","doi-asserted-by":"publisher","first-page":"176817","DOI":"10.1007\/S11704-023-3261-Z","article-title":"Improved differential-neural cryptanalysis for round-reduced\n  SIMECK32\/64","volume":"17","author":"Liu Zhang","year":"2023","journal-title":"Frontiers Comput. Sci."},{"key":"ref23:DBLP:conf\/isw\/LyuTZ22","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/978-3-031-22390-7_26","article-title":"Deep Learning Assisted Key Recovery Attack for Round-Reduced\n  Simeck32\/64","author":"Lijun Lyu","year":"2022"},{"key":"ref24:beaulieu2013simon","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2747946","article-title":"The SIMON and SPECK lightweight block ciphers","author":"Ray Beaulieu","year":"2015"},{"key":"ref25:yang2015simeck","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/978-3-662-48324-4_16","article-title":"The Simeck Family of Lightweight Block Ciphers","author":"Gangqiang Yang","year":"2015"},{"key":"ref26:lu2022improvedsimon_like","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1049\/ISE2.12061","article-title":"Improved rotational-XOR cryptanalysis of Simon-like block\n  ciphers","volume":"16","author":"Jinyu Lu","year":"2022","journal-title":"IET Inf. Secur."},{"key":"ref27:hou2021improve","first-page":"1017","article-title":"Improve Neural Distinguisher for Cryptanalysis","volume":"2021","author":"Zezhou Hou","year":"2021","journal-title":"IACR Cryptol. ePrint Arch."},{"key":"ref28:benamira2021deeper","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1007\/978-3-030-77870-5_28","article-title":"A Deeper Look at Machine Learning-Based Cryptanalysis","author":"Adrien Benamira","year":"2021"},{"key":"ref29:bao2022enhancing","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-031-22963-3_11","article-title":"Enhancing Differential-Neural Cryptanalysis","author":"Zhenzhen Bao","year":"2022"}],"container-title":["IACR Communications in Cryptology"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T04:02:17Z","timestamp":1778040137000},"score":1,"resource":{"primary":{"URL":"https:\/\/cic.iacr.org\/p\/3\/1\/12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,4]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,5,4]]}},"URL":"https:\/\/doi.org\/10.62056\/abksdkmol","archive":["Internet Archive","Internet Archive"],"relation":{},"ISSN":["3006-5496"],"issn-type":[{"value":"3006-5496","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,4]]},"assertion":[{"value":"2026-01-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-12","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"cc3-1-19"}}