A Comparative Study of Several Different Neural Network Approaches for Information Security Modeling

Jiahui Xie, Junpeng Li, Ping Qiu
Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, PMLR 278:527-533, 2025.

Abstract

In the rapid development of the Internet, people’s lives have been deeply bound to the Internet, and the network information data is explosive growth. However, along with it, there is an increasingly serious problem of network information security. In order to achieve more accurate network information security classification judgment, we use BP neural network, RBF neural network, based on genetic algorithm optimization of RBF neural network three models to compare the information security model respectively, used to assess their ability to assess the information security risk (threatening, vulnerability, asset identification). The experimental results show that the RBF neural network optimized based on genetic algorithm has higher accuracy and lower error in information security risk assessment, which has significant advantages over the traditional neural network and provides a strong basis for improving the level of information security protection and selecting the best neural network model.

Cite this Paper

BibTeX
@InProceedings{pmlr-v278-xie25a, title = {A Comparative Study of Several Different Neural Network Approaches for Information Security Modeling}, author = {Xie, Jiahui and Li, Junpeng and Qiu, Ping}, booktitle = {Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing}, pages = {527--533}, year = {2025}, editor = {Zeng, Nianyin and Pachori, Ram Bilas and Wang, Dongshu}, volume = {278}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v278/main/assets/xie25a/xie25a.pdf}, url = {https://proceedings.mlr.press/v278/xie25a.html}, abstract = {In the rapid development of the Internet, people’s lives have been deeply bound to the Internet, and the network information data is explosive growth. However, along with it, there is an increasingly serious problem of network information security. In order to achieve more accurate network information security classification judgment, we use BP neural network, RBF neural network, based on genetic algorithm optimization of RBF neural network three models to compare the information security model respectively, used to assess their ability to assess the information security risk (threatening, vulnerability, asset identification). The experimental results show that the RBF neural network optimized based on genetic algorithm has higher accuracy and lower error in information security risk assessment, which has significant advantages over the traditional neural network and provides a strong basis for improving the level of information security protection and selecting the best neural network model.} }
Endnote
%0 Conference Paper %T A Comparative Study of Several Different Neural Network Approaches for Information Security Modeling %A Jiahui Xie %A Junpeng Li %A Ping Qiu %B Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing %C Proceedings of Machine Learning Research %D 2025 %E Nianyin Zeng %E Ram Bilas Pachori %E Dongshu Wang %F pmlr-v278-xie25a %I PMLR %P 527--533 %U https://proceedings.mlr.press/v278/xie25a.html %V 278 %X In the rapid development of the Internet, people’s lives have been deeply bound to the Internet, and the network information data is explosive growth. However, along with it, there is an increasingly serious problem of network information security. In order to achieve more accurate network information security classification judgment, we use BP neural network, RBF neural network, based on genetic algorithm optimization of RBF neural network three models to compare the information security model respectively, used to assess their ability to assess the information security risk (threatening, vulnerability, asset identification). The experimental results show that the RBF neural network optimized based on genetic algorithm has higher accuracy and lower error in information security risk assessment, which has significant advantages over the traditional neural network and provides a strong basis for improving the level of information security protection and selecting the best neural network model.
APA
Xie, J., Li, J. & Qiu, P.. (2025). A Comparative Study of Several Different Neural Network Approaches for Information Security Modeling. Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, in Proceedings of Machine Learning Research 278:527-533 Available from https://proceedings.mlr.press/v278/xie25a.html.

Related Material