Research on Key Technology Algorithms of Communication Network Intrusion Detection and Data Encryption Based on Artificial Intelligence

被引:0
作者
Cai, Wei [1 ]
Ye, Yingze [2 ]
机构
[1] Jianghan Univ, Sch Intelligent Mfg, Wuhan 430056, Peoples R China
[2] Huazhong Agr Univ, Informat Technol Ctr, Wuhan 430070, Peoples R China
来源
TEHNICKI VJESNIK-TECHNICAL GAZETTE | 2025年 / 32卷 / 03期
关键词
artificial intelligence; communication; communication network; communication protocol; data encryption; intrusion detection;
D O I
10.17559/TV-20241009002044
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
In order to solve the problem of network intrusion detection and data encryption, artificial intelligence is introduced into communication network intrusion detection. Obtain the intrusion data of communication network and analyze the abnormal behavior of communication network: Firstly, the intrusion behavior data is processed based on artificial intelligence algorithm, and the number of network security vulnerabilities and network attacks is screened out. Secondly, an adaptive monitoring method is designed by using reinforcement learning agent to interact with the environment and constantly update the characteristics of the agent. The practical application shows that the method has higher detection stability than the traditional fixed detection method. Finally, on the basis of obtaining the data of communication network nodes by using artificial intelligence technology, the obtained data of communication network nodes is encrypted by using mixed-pool mapping method. The results of design comparison and test show that the proposed artificial intelligence-based network communication data encryption transmission method has higher efficiency, shorter response time and less abnormal node loss, which proves that the proposed method has better encryption transmission performance.
引用
收藏
页码:1000 / 1009
页数:10
相关论文
共 26 条
[1]   A Review of Research Works on Supervised Learning Algorithms for SCADA Intrusion Detection and Classification [J].
Alimi, Oyeniyi Akeem ;
Ouahada, Khmaies ;
Abu-Mahfouz, Adnan M. ;
Rimer, Suvendi ;
Alimi, Kuburat Oyeranti Adefemi .
SUSTAINABILITY, 2021, 13 (17)
[2]  
Chaowei W., 2020, International Journal for Engineering Modelling, V31, P184
[3]   Deep Learning Approach for Encryption Techniques in Vehicular Networks [J].
Choudhary, Deepak ;
Pahuja, Roop .
WIRELESS PERSONAL COMMUNICATIONS, 2022, 125 (01) :1-27
[4]  
Fu Ning, 2021, Journal of Physics: Conference Series, DOI 10.1088/1742-6596/1982/1/012132
[5]   RETRACTED: Forest management and resource monitoring based on AMI intrusion detection algorithm and artificial intelligence (Retracted Article) [J].
Huang, Chong .
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2021, 13 (Suppl 1) :49-49
[6]  
Jinling Yao, 2021, Journal of Physics: Conference Series, V1802, DOI 10.1088/1742-6596/1802/4/042028
[7]   Learning communication patterns for malware discovery in HTTPs data [J].
Kohout, Jan ;
Komarek, Tornag ;
Cchc, Premysl ;
Bodnar, Jan ;
Lokoc, Jakub .
EXPERT SYSTEMS WITH APPLICATIONS, 2018, 101 :129-142
[8]   RETRACTED: Information security model of block chain based on intrusion sensing in the IoT environment (Retracted article. See DEC, 2022) [J].
Li, Daming ;
Cai, Zhiming ;
Deng, Lianbing ;
Yao, Xiang ;
Wang, Harry Haoxiang .
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2019, 22 (Suppl 1) :451-468
[9]   Analysis and forecasting of the oil consumption in China based on combination models optimized by artificial intelligence algorithms [J].
Li, Jingrui ;
Wang, Rui ;
Wang, Jianzhou ;
Li, Yifan .
ENERGY, 2018, 144 :243-264
[10]  
Li Yonghong, 2021, Journal of Physics: Conference Series, DOI 10.1088/1742-6596/1982/1/012129