Anomaly detection algorithm based on fractal characteristics of large-scale network traffic

XU Xiao-dong1; ZHU Shi-rui2; SUN Ya-min1

您当前的位置：

首页 >

文章列表页 >

Anomaly detection algorithm based on fractal characteristics of large-scale network traffic

更新时间：2024-10-14

- Anomaly detection algorithm based on fractal characteristics of large-scale network traffic
- Vol. 30, Issue 9, Pages: 43-53(2009)
- 作者机构：
  
  1. 南京理工大学计算机科学与技术学院
  2. 江苏大学现代教育技术中心
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP393.08
- Published：2009
- 稿件说明：
移动端阅览
XU Xiao-dong1, ZHU Shi-rui2, SUN Ya-min1. Anomaly detection algorithm based on fractal characteristics of large-scale network traffic[J]. 2009, 30(9): 43-53.
DOI：

XU Xiao-dong1, ZHU Shi-rui2, SUN Ya-min1. Anomaly detection algorithm based on fractal characteristics of large-scale network traffic[J]. 2009, 30(9): 43-53. DOI：

摘要

基于宏观网络流量汇聚的分形结构

从流量的全局标度指数和局部标度指数出发

对流量异常进行定性和定量分析。利用多分形奇异谱和Lipschitz正则性分布分析流量异常的分形参数

试图找出这些参数的变化轨迹与异常出现的对应关系。实验结果表明异常的发生在奇异谱和Lipschitz正则性分布中确实有明显的体现。基于此特性构建了新的多分形异常检测算法并设计了新的检测框架

对DARPA1999年数据的实验表明

算法在低误报率的前提下

达到了较高的检测率

优于EMERALD算法。

Abstract

Based on the fractal structure of the large-scale network traffic aggregation

anomalies were analyzed qualitatively and quantitatively from perspective of the global and local scaling exponents.Multi-fractal singular spectrum and Lipschitz regularity distribution were used to analyze the fractal parameters of abnormal flow

trying to identify the relationship between the changes of these parameters and the emergence of anomalies.Experimental results show that the emergence of anomalies has obvious signs on the singular spectrum and Lipschitz regularity distribution.Using this feature

a new multi-fractal-based anomaly detection algorithm and a new detection framework were constructed.On the DARPA/Lincoln laboratory intrusion detection evaluation data set 1999

this algorithm’s detection rate is high at low false alarm rate

which is better than EMERALD.

关键词

Keywords

references

Views

877

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Anomaly detection method for intelligent UAV networks based on collaborative adversarial enhanced generative model

Deep learning architecture for anomaly detection, classification, and localization in free-space optical communication

Anomaly detection method for spatio-temporal correlation of WSN nodes based on graph prompt fine-tuning

Protocol field mutation method for 5G core network based on adaptive meta-learning

Research on traffic representation in network anomaly detection

Related Author

SUI He

MA Chunyan

LONG Lingchun

GU Zhaojun

LIU Jiajia

DING Lei

SONG Song

WU Tingwei

Related Institution

College of Aeronautical Engineering, Civil Aviation University of China

Information Security Evaluation Center, Civil Aviation University of China

School of Mechanical Engineering, North University of China

School of Cyber Science and Technology, Guangzhou University

School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications

AI问答

⁰