Author Login Editor-in-Chief Peer Review Editor Work Office Work

Computer Engineering ›› 2010, Vol. 36 ›› Issue (3): 174-176. doi: 10.3969/j.issn.1000-3428.2010.03.058

• Security Technology • Previous Articles     Next Articles

Network Anomaly Detection Based on High-order AR Model

HUANG Qiang-sheng, CHENG Jiu-jun, KANG Qin-ma   

  1. (Department of Computer Science and Technology, College of Electronics and Information Engineering, Tongji University, Shanghai 201804)
  • Received:1900-01-01 Revised:1900-01-01 Online:2010-02-05 Published:2010-02-05

基于高阶AR模型的网络异常检测

黄强盛,程久军,康钦马   

  1. (同济大学电子与信息工程学院计算机科学与技术系,上海 201804)

Abstract: This paper presents detection method based on 1-order AR model. Because of the low precision 1-order AR model owns, it proposes a method by substituting high-order AR model for 1-order one to make it more precise. Because setting the best parameters of the high-order AR model is an NP-complete problem, it applies genetic algorithm to search the better ones. Experiment shows that the high-order AR model is more efficient and precise for network anomaly detection.

Key words: network anomaly detection, AR model, genetic algorithm

摘要: 介绍基于1阶AR模型的检测方法,用高阶AR模型代替1阶AR模型以增加其精度。鉴于高阶AR模型最优参数的确定是个NP完全问题,利用遗传算法搜索其参数的近似最优解,通过实验验证高阶AR模型对网络异常检测的有效性和精确性。

关键词: 网络异常检测, AR模型, 遗传算法

CLC Number: