Identifying vulnerabilities in trust and reputation systems
Identifying vulnerabilities in trust and reputation systems
Online communities use trust and reputation systems to assist their users in evaluating other parties. Due to the preponderance of these systems, malicious entities have a strong incentive to attempt to influence them, and strategies employed are increasingly sophisticated. Current practice is to evaluate trust and reputation systems against known attacks, and hence are heavily reliant on expert analysts. We present a novel method for automatically identifying vulnerabilities in such systems by formulating the problem as a derivative-free optimisation problem and applying efficient sampling methods. We illustrate the application of this method for attacks that involve the injection of false evidence, and identify vulnerabilities in existing trust models. In this way, we provide reliable and objective means to assess how robust trust and reputation systems are to different kinds of attacks.
trust and reputation, security and privacy
308-314
International Joint Conferences on Artificial Intelligence
Gunes, Taha
19edfddb-8c8e-49f1-83eb-f7fca56e737a
Tran-Thanh, Long
e0666669-d34b-460e-950d-e8b139fab16c
Norman, Timothy
663e522f-807c-4569-9201-dc141c8eb50d
Gunes, Taha
19edfddb-8c8e-49f1-83eb-f7fca56e737a
Tran-Thanh, Long
e0666669-d34b-460e-950d-e8b139fab16c
Norman, Timothy
663e522f-807c-4569-9201-dc141c8eb50d
Gunes, Taha, Tran-Thanh, Long and Norman, Timothy
(2019)
Identifying vulnerabilities in trust and reputation systems.
In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, Macao, China, August 10-16, 2019.
International Joint Conferences on Artificial Intelligence.
.
(doi:10.24963/ijcai.2019/44).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Online communities use trust and reputation systems to assist their users in evaluating other parties. Due to the preponderance of these systems, malicious entities have a strong incentive to attempt to influence them, and strategies employed are increasingly sophisticated. Current practice is to evaluate trust and reputation systems against known attacks, and hence are heavily reliant on expert analysts. We present a novel method for automatically identifying vulnerabilities in such systems by formulating the problem as a derivative-free optimisation problem and applying efficient sampling methods. We illustrate the application of this method for attacks that involve the injection of false evidence, and identify vulnerabilities in existing trust models. In this way, we provide reliable and objective means to assess how robust trust and reputation systems are to different kinds of attacks.
Text
Full text version
- Accepted Manuscript
More information
Accepted/In Press date: 2019
e-pub ahead of print date: August 2019
Venue - Dates:
International Joint Conference on Artificial Intelligence, Venetian Macao Hotel Resort, Cotai Strip, Macao, China, 2019-08-10 - 2019-08-16
Keywords:
trust and reputation, security and privacy
Identifiers
Local EPrints ID: 431278
URI: http://eprints.soton.ac.uk/id/eprint/431278
PURE UUID: d6bcc289-b7aa-4328-aaca-312d41017da3
Catalogue record
Date deposited: 29 May 2019 16:30
Last modified: 16 Mar 2024 04:24
Export record
Altmetrics
Contributors
Author:
Taha Gunes
Author:
Long Tran-Thanh
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics