Research on the application of DT and K-NN-based data mining algorithms in network intrusion monitoring

• Main Author: Li, Shaoxi
• Format: Conference Proceeding
• Language: English
• Published: SPIE 26.10.2023
• ISBN: 9781510671423; 1510671420
• ISSN: 0277-786X
• DOI: 10.1117/12.3009151

With the rapid development of computer Internet technology, network communication has become an important way to obtain information. However, the open Internet is also vulnerable to all kinds of malicious damage and attacks. Intrusion monitoring technology can realize the monitoring, analysis and defense of intrusion behaviors, but the current intrusion monitoring technology cannot meet the development needs of current network security. The study adopts decision tree algorithm for information classification model design and combines k proximity algorithm to construct network intrusion classification model design. The experimental results show that the decision tree-k proximity algorithm has the highest correct detection rate, with a maximum accuracy of 94.36% and strong monitoring capability; the training time of the model is short, taking only 5 s when the training is completed; at the same time, the recall rate of the decision tree-k proximity algorithm is high, and the area enclosed by the subject's characteristic curve is large, with better comprehensive performance. The data mining network intrusion monitoring model based on decision tree and k proximity algorithm can accurately monitor malicious attacks and ensure system security, which is important for maintaining computer network security.