RSA modulus length regression prediction based on the Run Test and machine learning in the ciphertext-only scenarios

Abstract RSA is a classical public key cryptographic algorithm, over 40 years of widespread use has proven that its security is reliable when the key parameters are properly configured. Attacks against RSA mainly rely on its internal mathematical constructs, such as modulus factorization, co-modulus...

Full description

Saved in:
Bibliographic Details
Main Authors: Ke Yuan, Chenmeng Zhao, Longwei Yang, Hanlin Sun, Sufang Zhou, Chunfu Jia
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-025-02014-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331547182727168
author Ke Yuan
Chenmeng Zhao
Longwei Yang
Hanlin Sun
Sufang Zhou
Chunfu Jia
author_facet Ke Yuan
Chenmeng Zhao
Longwei Yang
Hanlin Sun
Sufang Zhou
Chunfu Jia
author_sort Ke Yuan
collection DOAJ
description Abstract RSA is a classical public key cryptographic algorithm, over 40 years of widespread use has proven that its security is reliable when the key parameters are properly configured. Attacks against RSA mainly rely on its internal mathematical constructs, such as modulus factorization, co-modulus attack, small exponent Attack, etc. Modulus length is one of the most important security metrics for RSA, considering that in some scenarios, the public key of RSA is not always public in order to improve the security strength of communication, and there is no ciphertext-only attack on modulus length in the existing attack methods, this paper designs a Modulus Length Regression Scheme (MLRS) using the Run Test and machine learning for RSA algorithm, aiming to identify the length of modulus used in RSA ciphertexts in the ciphertext-only scenario, and provide a reference for further attacks. In the proposed MLRS, we use National Institute of Standards and Technology (NIST) Run Test and Machine Learning models as ciphertext feature extraction method and modulus length regression tools, respectively, along with a hyperparameter tuple in MLRS to find a balance between resource overhead and regression effects, so as to achieve better results at a smaller cost. The experimental results show that this scheme using DTR-based AdaBoost can achieve a modulus length regression prediction of RMSE  $$=$$ =  34.16, $$R^{2}$$ R 2 Score  $$=$$ =  0.9738 for RSA ciphertexts without filling. In addition, we analyzed the effect of variation in modulus length on the Run Test and find that the longer the modulus, the more indistinguishable the corresponding ciphertext features are, which laterally verifies that the longer the RSA modulus length is, the more secure it is from the perspective of artificial intelligence cryptanalysis.
format Article
id doaj-art-ce354c7ea0cd4e8788949c1c7a5d2364
institution Kabale University
issn 2199-4536
2198-6053
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-ce354c7ea0cd4e8788949c1c7a5d23642025-08-20T03:46:32ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-07-0111911510.1007/s40747-025-02014-4RSA modulus length regression prediction based on the Run Test and machine learning in the ciphertext-only scenariosKe Yuan0Chenmeng Zhao1Longwei Yang2Hanlin Sun3Sufang Zhou4Chunfu Jia5School of Computer and Information Engineering, Henan UniversitySchool of Computer and Information Engineering, Henan UniversityCollege of Cybersecurity, Nankai UniversitySchool of Computer and Information Engineering, Henan UniversitySchool of Computer and Information Engineering, Henan UniversityCollege of Cybersecurity, Nankai UniversityAbstract RSA is a classical public key cryptographic algorithm, over 40 years of widespread use has proven that its security is reliable when the key parameters are properly configured. Attacks against RSA mainly rely on its internal mathematical constructs, such as modulus factorization, co-modulus attack, small exponent Attack, etc. Modulus length is one of the most important security metrics for RSA, considering that in some scenarios, the public key of RSA is not always public in order to improve the security strength of communication, and there is no ciphertext-only attack on modulus length in the existing attack methods, this paper designs a Modulus Length Regression Scheme (MLRS) using the Run Test and machine learning for RSA algorithm, aiming to identify the length of modulus used in RSA ciphertexts in the ciphertext-only scenario, and provide a reference for further attacks. In the proposed MLRS, we use National Institute of Standards and Technology (NIST) Run Test and Machine Learning models as ciphertext feature extraction method and modulus length regression tools, respectively, along with a hyperparameter tuple in MLRS to find a balance between resource overhead and regression effects, so as to achieve better results at a smaller cost. The experimental results show that this scheme using DTR-based AdaBoost can achieve a modulus length regression prediction of RMSE  $$=$$ =  34.16, $$R^{2}$$ R 2 Score  $$=$$ =  0.9738 for RSA ciphertexts without filling. In addition, we analyzed the effect of variation in modulus length on the Run Test and find that the longer the modulus, the more indistinguishable the corresponding ciphertext features are, which laterally verifies that the longer the RSA modulus length is, the more secure it is from the perspective of artificial intelligence cryptanalysis.https://doi.org/10.1007/s40747-025-02014-4RSA algorithmCiphertext-only scenarioDistinguishing attackRun testMachine learning
spellingShingle Ke Yuan
Chenmeng Zhao
Longwei Yang
Hanlin Sun
Sufang Zhou
Chunfu Jia
RSA modulus length regression prediction based on the Run Test and machine learning in the ciphertext-only scenarios
Complex & Intelligent Systems
RSA algorithm
Ciphertext-only scenario
Distinguishing attack
Run test
Machine learning
title RSA modulus length regression prediction based on the Run Test and machine learning in the ciphertext-only scenarios
title_full RSA modulus length regression prediction based on the Run Test and machine learning in the ciphertext-only scenarios
title_fullStr RSA modulus length regression prediction based on the Run Test and machine learning in the ciphertext-only scenarios
title_full_unstemmed RSA modulus length regression prediction based on the Run Test and machine learning in the ciphertext-only scenarios
title_short RSA modulus length regression prediction based on the Run Test and machine learning in the ciphertext-only scenarios
title_sort rsa modulus length regression prediction based on the run test and machine learning in the ciphertext only scenarios
topic RSA algorithm
Ciphertext-only scenario
Distinguishing attack
Run test
Machine learning
url https://doi.org/10.1007/s40747-025-02014-4
work_keys_str_mv AT keyuan rsamoduluslengthregressionpredictionbasedontheruntestandmachinelearningintheciphertextonlyscenarios
AT chenmengzhao rsamoduluslengthregressionpredictionbasedontheruntestandmachinelearningintheciphertextonlyscenarios
AT longweiyang rsamoduluslengthregressionpredictionbasedontheruntestandmachinelearningintheciphertextonlyscenarios
AT hanlinsun rsamoduluslengthregressionpredictionbasedontheruntestandmachinelearningintheciphertextonlyscenarios
AT sufangzhou rsamoduluslengthregressionpredictionbasedontheruntestandmachinelearningintheciphertextonlyscenarios
AT chunfujia rsamoduluslengthregressionpredictionbasedontheruntestandmachinelearningintheciphertextonlyscenarios