Boosting-based distributed and adaptive security-monitoring through agent collaboration

Evens Jean, Yu Jiao, Ali R. Hurson, Thomas E. Potok

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

4 Scopus citations

Abstract

The use of mobile agents to support the development of practical applications is limited primarily by the risks to which hosts in the system are subject to. This article introduces a distributed and adaptive security-monitoring framework to decrease such potential threats. The proposed framework is based on a modified version of the popular Boosting algorithm to classify malicious agents based on their execution patterns on current and prior hosts. Having implemented the framework for the Aglet platform, we herein present the results of our experiments showcasing the detection of agent entities in the system with intention deviating from that of their well-behaved counterparts.

Original languageEnglish
Title of host publicationProceedings - 2007 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2007
Pages516-520
Number of pages5
DOIs
StatePublished - 2007
Event2007 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2007 - Silicon Valley, CA, United States
Duration: Nov 2 2007Nov 5 2007

Publication series

NameProceedings - 2007 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2007

Conference

Conference2007 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2007
Country/TerritoryUnited States
CitySilicon Valley, CA
Period11/2/0711/5/07

Fingerprint

Dive into the research topics of 'Boosting-based distributed and adaptive security-monitoring through agent collaboration'. Together they form a unique fingerprint.

Cite this