计算机工程与应用 ›› 2006, Vol. 42 ›› Issue (7): 16-.

• 博士论坛 • 上一篇    下一篇

基于Kaufman算法提高D-WARD系统检测精度.

康健,鞠九滨   

  1. 吉林大学计算机科学与技术学院
  • 收稿日期:2005-11-30 修回日期:1900-01-01 出版日期:2006-03-01 发布日期:2006-03-01
  • 通讯作者: 康健 kj885788

An Improvement on Precision in D-WARD Detection System with Kaufman Algorithm

,   

  1. 吉林大学计算机科学与技术学院
  • Received:2005-11-30 Revised:1900-01-01 Online:2006-03-01 Published:2006-03-01

摘要: 深入分析了具有代表性的DDoS源端检测系统D-WARD的检测算法,在使用非参数化递归CUSUM算法改进D-WARD的基础上,借鉴负载平衡中Load-Shedding的思想,应用Kaufman算法动态调整和更新阈值Threshold,并对检测性能进行详细比较。经实验验证,改进的系统具有更低的误报率和漏报率,能够适应更复杂的网络检测环境。

Abstract: After analyzing the detection algorithm of D-WARD, a representative source-end DDoS detection system, improved D-WARD with nonparametric recursive CUSUM algorithm. Meanwhile, by drawing on the experience of Load-Shedding in the load balance , used Kaufman algorithm to adjust and upgrade threshold value dynamically and compared their respective performance. Experiments proved that the improved system is lower in false-positive rate and false-negative rate, which is more accurate and could adapt to more complex network environments.