DIGNN-A:Real-Time Network Intrusion Detection with Integrated Neural Networks Based on Dynamic Graph

作     者：Jizhao Liu Minghao Guo 

作者机构：College of ComputerZhongyuan University of TechnologyZhengzhou450007China 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2025年第82卷第1期

页      面：817-842页

核心收录：

学科分类：07[理学] 0701[理学-数学] 070101[理学-基础数学] 

主　　题：Intrusion detection graph neural networks attention mechanisms line graphs dynamic graph neural networks 

摘      要：The increasing popularity of the Internet and the widespread use of information technology have led to a rise in the number and sophistication of network attacks and security *** detection systems are crucial to network security,playing a pivotal role in safeguarding networks from potential ***,in the context of an evolving landscape of sophisticated and elusive attacks,existing intrusion detection methodologies often overlook critical aspects such as changes in network topology over time and interactions between *** address these issues,this paper proposes a real-time network intrusion detection method based on graph neural *** proposedmethod leverages the advantages of graph neural networks and employs a straightforward graph construction method to represent network traffic as dynamic graph-structured ***,a graph convolution operation with a multi-head attention mechanism is utilized to enhance the model’s ability to capture the intricate relationships within the graph structure ***,it uses an integrated graph neural network to address dynamic graphs’structural and topological changes at different time points and the challenges of edge embedding in intrusion detection *** edge classification problem is effectively transformed into node classification by employing a line graph data representation,which facilitates fine-grained intrusion detection tasks on dynamic graph node feature *** efficacy of the proposed method is evaluated using two commonly used intrusion detection datasets,UNSW-NB15 and NF-ToN-IoT-v2,and results are compared with previous studies in this *** experimental results demonstrate that our proposed method achieves 99.3%and 99.96%accuracy on the two datasets,respectively,and outperforms the benchmark model in several evaluation metrics.