A trust-based detecting mechanism against profile injection attacks in recommender systems

Qiang Zhang*, Yuan Luo, Chuliang Weng, Minglu Li

*Corresponding author for this work

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

6 Scopus citations

Abstract

Recommender systems could be applied in grid environment to help grid users select more suitable services by making high quality personalized recommendations. Also, recommendation could be employed in the virtual machines managing platform to measure the performance and creditability of each virtual machine. However, such systems have been shown to be vulnerable to profile injection attacks (shilling attacks), attacks that involve the insertion of malicious profiles into the ratings database for the purpose of altering the system's recommendation behavior. In this paper we introduce and evaluate a new trust-based detecting algorithm for protecting recommender systems against profile injection attacks. Moreover, we discuss the combination of our trust-based metrics with previous metrics such as RDMA in profile-level and item-level respectively. In the end, we show these metrics can lead to improved detecting accuracy experimentally.

Original languageEnglish
Title of host publicationSSIRI 2009 - 3rd IEEE International Conference on Secure Software Integration Reliability Improvement
Pages59-64
Number of pages6
DOIs
StatePublished - 2009
Externally publishedYes
Event3rd IEEE International Conference on Secure Software Integration Reliability Improvement, SSIRI 2009 - Shanghai, China
Duration: 8 Jul 200910 Jul 2009

Publication series

NameSSIRI 2009 - 3rd IEEE International Conference on Secure Software Integration Reliability Improvement

Conference

Conference3rd IEEE International Conference on Secure Software Integration Reliability Improvement, SSIRI 2009
Country/TerritoryChina
CityShanghai
Period8/07/0910/07/09

Fingerprint

Dive into the research topics of 'A trust-based detecting mechanism against profile injection attacks in recommender systems'. Together they form a unique fingerprint.

Cite this