Defending Autonomous Agents Against Attacks in Multi-Agent Systems Using Norms

Jan Kantert, Sarah Edenhofer, Sven Tomforde, Jörg Hähner, Christian Müller-Schloer

2015

Abstract

The Trusted Desktop Grid (TDG) is a self-organised, agent-based organisation, where agents perform computational tasks for others to increase their performance. In order to establish a fair distribution and provide counter-measures against egoistic or malicious elements, technical trust is used. A fully self-organised approach can run into disturbed states such as a trust breakdown of the system that lead to unsatisfying system performance although the majority of participants is still behaving well. We previously introduced an additional system-wide control loop to detect and alleviate disturbed situations. Therefore, we describe an Observer/Controller loop at system level that monitors the system status and intervenes if necessary. This paper focuses on the controller part which instantiates norms as reaction to observed suspicious situations. We demonstrate the benefit of our approach within a Repast-based simulation of the TDG. Therein, the impact of disturbances on the system performance is decreased significantly and the time to recover is shortened.

Paper Citation

in Harvard Style

Kantert J., Edenhofer S., Tomforde S., Hähner J. and Müller-Schloer C. (2015). Defending Autonomous Agents Against Attacks in Multi-Agent Systems Using Norms . In Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-073-4, pages 149-156. DOI: 10.5220/0005202101490156

in Bibtex Style

@conference{icaart15,
author={Jan Kantert and Sarah Edenhofer and Sven Tomforde and Jörg Hähner and Christian Müller-Schloer},
title={Defending Autonomous Agents Against Attacks in Multi-Agent Systems Using Norms},
booktitle={Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2015},
pages={149-156},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005202101490156},
isbn={978-989-758-073-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Defending Autonomous Agents Against Attacks in Multi-Agent Systems Using Norms
SN - 978-989-758-073-4
AU - Kantert J.
AU - Edenhofer S.
AU - Tomforde S.
AU - Hähner J.
AU - Müller-Schloer C.
PY - 2015
SP - 149
EP - 156
DO - 10.5220/0005202101490156