An autonomous trust construction system based on Bayesian method

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

Though research on multi-agent systems have progressed at a steady pace, its promise has yet to be realized. One major difficulty is that, by its very nature, the multi-agent system is a large, uncensored system. This raises the question of how much dependability to give each information source. We cannot expect each user to know the trustworthiness of each source. Trust mechanism is regarded as a key for solving the problem of security in multi-agent systems. To achieve the trust management autonomy, this paper presents an autonomous trust construction model based on Bayesian method. The presented model adopts the Bayesian method to evaluate the trust value of each agent, and uses the graph theory to combination and path searching to construct the trust relation. The simulation experiment results prove that the autonomous trust construction is effective.

Original languageEnglish
Title of host publicationProceedings - 2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT 2006 Main Conference Proceedings), IAT'06
Pages357-362
Number of pages6
DOIs
StatePublished - 2007
Externally publishedYes
Event2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT'06 - Hong Kong, China
Duration: 18 Dec 200622 Dec 2006

Publication series

NameProceedings - 2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT 2006 Main Conference Proceedings), IAT'06

Conference

Conference2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT'06
Country/TerritoryChina
CityHong Kong
Period18/12/0622/12/06

Keywords

  • Autonomous
  • Bayesian method
  • Cooperation
  • Multi-agent systems
  • Trust model

Fingerprint

Dive into the research topics of 'An autonomous trust construction system based on Bayesian method'. Together they form a unique fingerprint.

Cite this