Earticle

초록

영어

On the basis of analyzing the existing intrusion detection system (IDS) based on agent, this paper proposed a multi-agent distributed IDS(DIDS) model based on BP neural network. This model adopted the modes of distributed detection and distributed response. Each Agent was independence relatively. And this model analyzed the functional design of each agent and central console. Meanwhile, to improve the performance of the system, an improved error back-propagation algorithm was designed, which could improve the detection accuracy of the system by using its good learning ability. In addition, the dynamic election algorithm and collaborative algorithm were analyzed preliminarily. Experiments proved that the system could complete the intrusion detection tasks by making full use of various resources collaboratively, and thus the detection speed and accuracy of the system could be improved.

목차

Abstract
 1. Introduction
 2. System Design
  2.1. Main Framework
  2.2. Central Console
  2.3. Basic Agent
  2.4. Track Agent and Management Agent
 3. Key Algorithm
  3.1. Dynamic Election Algorithm
  3.2. Collaborative Algorithm
  3.3. Inference Algorithm based on BP Neural Network
 4. Experimental Analysis
 5. Conclusion
 References

키워드

저자

• ZhaiShuang-can [ Nanjing University of Chinese Medicine ]
• Hu Chen-jun [ Nanjing University of Chinese Medicine ]
• Zhang Wei-ming [ Nanjing University of Chinese Medicine ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Security and Its Applications

• 간기

  격월간

• pISSN

  1738-9976

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605