The P2P Traffic Identification Based On GA-SVM1

摘要：

This paper proposes a P2P traffic identification model based on GA-SVM aimed at solving network congestion problems and avoiding safety hazards caused by P2P traffic occupying scarce resources. The model uses genetic algorithms to optimize the support vector machine (SVM), and it has a higher accuracy and lower rate of false positives and false negatives compared to conventional behaviour detection systems. Additionally, we have also built in support for realtime online detection in a local area network (LAN), which current behaviour recognition systems do not support Through numerous experiments in real network environments we have concluded that this method is capable of accurately and effectively identifying the majority of P2P traffic

关键词： P2P traffic ldentification support vector machine genetic algorithm network Security

作者: Wan Chun Qin Hao Han Lansheng Zhang Yunhe

作者单位: Laboratory for Information Security, School of Computer Science and Technology Huazhong University of Science and Technology, Wuhan 430074, China

会议类型: 国际会议

会议名称: 2010 3rd International Conference on Environmental and Computer Science(2010年第三届环境与计算机科学国际会议 ICECS 2010)

会议地点: 昆明

会议语种:英文

页码: 67-72

在线出版日期: 2010-10-17（万方平台首次上网日期，不代表论文的发表时间）