Authentication Based on Attribute Encryption with Machine Learning

Weiran Tang; Ga Xiang; Yawei Ren

doi:doi:10.11648/j.sjedu.20231103.14

| Peer-Reviewed

Authentication Based on Attribute Encryption with Machine Learning

Weiran Tang, Ga Xiang, Yawei Ren

Published in Science Journal of Education (Volume 11, Issue 3)

Received: 12 May 2023 Accepted: 8 June 2023 Published: 14 June 2023

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

In recent years, even under the access control based on attribute encryption, the information resources in the network will inevitably be illegally obtained. There will still be the phenomenon of attackers posing as legitimate users to pass identity authentication. Therefore, it is necessary to take measures for behavior detection before identity authentication to establish trust between users and the network. After preprocessing the data set of user behavior information, the machine learning model is built to predict whether the user behavior is abnormal or not. Logical regression model, KNN model, and decision tree model are mainly built. After analyzing the prediction results, authentication is required. Therefore, an algorithm based on CP-ABE is proposed. First of all, establish a ciphertext access structure. Secondly, extract the user's valid identity element. Finally, verify the identity and decrypt. From the experimental results, the accuracy of the above three machine learning models is more than 75%. But the f1-score of the decision tree model is up to 93%, which is the highest, indicating that the decision tree model is largely suitable for dealing with the problem of behavior detection. In addition, the CP-ABE algorithm can determine whether the user has the right to access the information according to the user's identity effectively and quickly. The solution prevents and controls users with abnormal behavior and failed identity information verification effectively. It combines machine learning algorithm and algorithm based on attribute encryption successfully and makes certain contributions to the research of problems in this field.

Published in	Science Journal of Education (Volume 11, Issue 3)
DOI	10.11648/j.sjedu.20231103.14
Page(s)	110-116
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Machine Learning, CP-ABE, Behavior Detection, Authentication

References

[1]	Wang S J. (2022). Application of User Identity Authentication Technology in Network Information Security. Information and Computer (Theoretical Edition) (08), 221-223.
[2]	Liu Y, Guo S & Yang X Y. (2022). Threshold identity authentication scheme based on biometrics. Application Research of Computers (04), 1224-1227. doi: 10.19734/j.issn.1001-3695.2021.08.0388.
[3]	Wang S S, Ma Z F, Liu J W & Luo S S. (2022). Research and Implementation of Cross-Chain Security Access and Identity Authentication Scheme of Blockchain. Information Network Security (06), 61-72.
[4]	Sahai A, Waters B. Fuzzy Identity-Based Encryption [J]. International Conference on Theory & Applications of Cryptographic Techniques, 2005.
[5]	Goyal V, Pandey O, Sahai A, et al. Attribute-Based Encryption for Fine-Grained Access Control of Encrypted Data [J]. ACM, 2006.
[6]	Bethencourt J, Sahai A, Waters B. Ciphertext-Policy Attribute-Based Encryption [C] // IEEE Symposium on Security & Privacy. IEEE, 2007.
[7]	Huang G S. (2022). Application of Machine Learning Algorithm in Artificial Intelligence. Integrated Circuits Design and Application (09), 192-193. doi: 10.19339/j.issn.1674-2583.2022.09.085.
[8]	Guo G, Yang C, Chen M Z & Ma J F. App traffic identification under ShadowSocksR proxy with machine learning. Journal of Xidian University.
[9]	Chen Y J, Gao H R & Ding Z J. (2023). Credit Evaluation Model Based on Dynamic Machine Learning. Computer Science (01), 59-68.
[10]	Qin B D, Yu P H & Zheng D. (2022). Decision Tree Classification Model Based on Double Trapdoor Homomorphic Encryption. Information Network Security (07), 9-17.
[11]	Yin F F. (2021). Research on Revocable and Searchable Attribute-Based Encryption Algorithms (Master Dissertation, Xidian University). https://kns.cnki.net/KCMS/detail/detail.aspx?dbname=CMFD202201&filename=1022013684.nh
[12]	Kurniawan A, Kyas M. Securing Machine Learning Engines in IoT Applications with Attribute-Based Encryption [C] // 2019 IEEE International Conference on Intelligence and Security Informatics (ISI). 0.
[13]	Zhou X, Xu K, Wang N, et al. A Secure and Privacy-Preserving Machine Learning Model Sharing Scheme for Edge-Enabled IoT [J]. IEEE Access, 2021, 9: 17256-17265.
[14]	Wu X Y, Wang S H, Zhang Y D. Survey on theory and application of k-Nearest-Neighbors algorithm [J]. Computer Engineering and Applications, 2017.
[15]	Dong X. Research on logistic regression and its parallel implementation on GPU [D]. Harbin Institute of Technology, 2016.
[16]	Liu Y. Mathematical model of multiple linear regression [J]. Journal of Shenyang Institute of Engineering, 2005.
[17]	Zhang X, Huang X, Zhong W H, et al. Implementation of Sigmoid Function and Its Derivative on FPGA [J]. Journal of Fujian Normal University (Natural Science Edition), 2011.
[18]	Ruder S. An overview of gradient descent optimization algorithms [J]. 2016.
[19]	Chong L U, Hui X U, Yang Y C. The research and application of classification algorithm based on decision tree [J]. Electronic Design Engineering, 2016.
[20]	Chen L. (2013). Improvement and application of decision tree with Covariance information entropy information entropy (Master Dissertation, Yunnan University). https://kns.cnki.net/KCMS/detail/detail.aspx?dbname=CMFD201401&filename=1013306255.nh

Cite This Article

Plain Text BibTeX RIS

APA Style

Weiran Tang, Ga Xiang, Yawei Ren. (2023). Authentication Based on Attribute Encryption with Machine Learning. Science Journal of Education, 11(3), 110-116. https://doi.org/10.11648/j.sjedu.20231103.14

Copy | Download

ACS Style

Weiran Tang; Ga Xiang; Yawei Ren. Authentication Based on Attribute Encryption with Machine Learning. Sci. J. Educ. 2023, 11(3), 110-116. doi: 10.11648/j.sjedu.20231103.14

Copy | Download

AMA Style

Weiran Tang, Ga Xiang, Yawei Ren. Authentication Based on Attribute Encryption with Machine Learning. Sci J Educ. 2023;11(3):110-116. doi: 10.11648/j.sjedu.20231103.14

Copy | Download

@article{10.11648/j.sjedu.20231103.14,
  author = {Weiran Tang and Ga Xiang and Yawei Ren},
  title = {Authentication Based on Attribute Encryption with Machine Learning},
  journal = {Science Journal of Education},
  volume = {11},
  number = {3},
  pages = {110-116},
  doi = {10.11648/j.sjedu.20231103.14},
  url = {https://doi.org/10.11648/j.sjedu.20231103.14},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sjedu.20231103.14},
  abstract = {In recent years, even under the access control based on attribute encryption, the information resources in the network will inevitably be illegally obtained. There will still be the phenomenon of attackers posing as legitimate users to pass identity authentication. Therefore, it is necessary to take measures for behavior detection before identity authentication to establish trust between users and the network. After preprocessing the data set of user behavior information, the machine learning model is built to predict whether the user behavior is abnormal or not. Logical regression model, KNN model, and decision tree model are mainly built. After analyzing the prediction results, authentication is required. Therefore, an algorithm based on CP-ABE is proposed. First of all, establish a ciphertext access structure. Secondly, extract the user's valid identity element. Finally, verify the identity and decrypt. From the experimental results, the accuracy of the above three machine learning models is more than 75%. But the f1-score of the decision tree model is up to 93%, which is the highest, indicating that the decision tree model is largely suitable for dealing with the problem of behavior detection. In addition, the CP-ABE algorithm can determine whether the user has the right to access the information according to the user's identity effectively and quickly. The solution prevents and controls users with abnormal behavior and failed identity information verification effectively. It combines machine learning algorithm and algorithm based on attribute encryption successfully and makes certain contributions to the research of problems in this field.},
 year = {2023}
}

Copy | Download

TY - JOUR
T1 - Authentication Based on Attribute Encryption with Machine Learning
AU - Weiran Tang
AU - Ga Xiang
AU - Yawei Ren
Y1 - 2023/06/14
PY - 2023
N1 - https://doi.org/10.11648/j.sjedu.20231103.14
DO - 10.11648/j.sjedu.20231103.14
T2 - Science Journal of Education
JF - Science Journal of Education
JO - Science Journal of Education
SP - 110
EP - 116
PB - Science Publishing Group
SN - 2329-0897
UR - https://doi.org/10.11648/j.sjedu.20231103.14
AB - In recent years, even under the access control based on attribute encryption, the information resources in the network will inevitably be illegally obtained. There will still be the phenomenon of attackers posing as legitimate users to pass identity authentication. Therefore, it is necessary to take measures for behavior detection before identity authentication to establish trust between users and the network. After preprocessing the data set of user behavior information, the machine learning model is built to predict whether the user behavior is abnormal or not. Logical regression model, KNN model, and decision tree model are mainly built. After analyzing the prediction results, authentication is required. Therefore, an algorithm based on CP-ABE is proposed. First of all, establish a ciphertext access structure. Secondly, extract the user's valid identity element. Finally, verify the identity and decrypt. From the experimental results, the accuracy of the above three machine learning models is more than 75%. But the f1-score of the decision tree model is up to 93%, which is the highest, indicating that the decision tree model is largely suitable for dealing with the problem of behavior detection. In addition, the CP-ABE algorithm can determine whether the user has the right to access the information according to the user's identity effectively and quickly. The solution prevents and controls users with abnormal behavior and failed identity information verification effectively. It combines machine learning algorithm and algorithm based on attribute encryption successfully and makes certain contributions to the research of problems in this field.
VL - 11
IS - 3
ER -

Copy | Download

Author Information

Weiran Tang

School of Information Management, Beijing Information Science and Technology University, Beijing, China
Ga Xiang

School of Information Management, Beijing Information Science and Technology University, Beijing, China
Yawei Ren

School of Information Management, Beijing Information Science and Technology University, Beijing, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Weiran Tang, Ga Xiang, Yawei Ren. (2023). Authentication Based on Attribute Encryption with Machine Learning. Science Journal of Education, 11(3), 110-116. https://doi.org/10.11648/j.sjedu.20231103.14

Copy | Download

ACS Style

Weiran Tang; Ga Xiang; Yawei Ren. Authentication Based on Attribute Encryption with Machine Learning. Sci. J. Educ. 2023, 11(3), 110-116. doi: 10.11648/j.sjedu.20231103.14

Copy | Download

AMA Style

Weiran Tang, Ga Xiang, Yawei Ren. Authentication Based on Attribute Encryption with Machine Learning. Sci J Educ. 2023;11(3):110-116. doi: 10.11648/j.sjedu.20231103.14

Copy | Download

@article{10.11648/j.sjedu.20231103.14,
  author = {Weiran Tang and Ga Xiang and Yawei Ren},
  title = {Authentication Based on Attribute Encryption with Machine Learning},
  journal = {Science Journal of Education},
  volume = {11},
  number = {3},
  pages = {110-116},
  doi = {10.11648/j.sjedu.20231103.14},
  url = {https://doi.org/10.11648/j.sjedu.20231103.14},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sjedu.20231103.14},
  abstract = {In recent years, even under the access control based on attribute encryption, the information resources in the network will inevitably be illegally obtained. There will still be the phenomenon of attackers posing as legitimate users to pass identity authentication. Therefore, it is necessary to take measures for behavior detection before identity authentication to establish trust between users and the network. After preprocessing the data set of user behavior information, the machine learning model is built to predict whether the user behavior is abnormal or not. Logical regression model, KNN model, and decision tree model are mainly built. After analyzing the prediction results, authentication is required. Therefore, an algorithm based on CP-ABE is proposed. First of all, establish a ciphertext access structure. Secondly, extract the user's valid identity element. Finally, verify the identity and decrypt. From the experimental results, the accuracy of the above three machine learning models is more than 75%. But the f1-score of the decision tree model is up to 93%, which is the highest, indicating that the decision tree model is largely suitable for dealing with the problem of behavior detection. In addition, the CP-ABE algorithm can determine whether the user has the right to access the information according to the user's identity effectively and quickly. The solution prevents and controls users with abnormal behavior and failed identity information verification effectively. It combines machine learning algorithm and algorithm based on attribute encryption successfully and makes certain contributions to the research of problems in this field.},
 year = {2023}
}

Copy | Download