Differentially Private Malicious Agent Avoidance in Multiagent Advising Learning.

Ye, D; Zhu, T; Zhou, W; Yu, PS

Differentially Private Malicious Agent Avoidance in Multiagent Advising Learning.

Ye, D

Zhu, T Zhou, W

Yu, PS

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE transactions on cybernetics, 2020, 50, (10), pp. 4214-4227
Issue Date:: 2020-10

Closed Access

	Filename	Description	Size
	08685696.pdf	Published version	1.82 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Ye, D https://orcid.org/0000-0002-7561-0992
dc.contributor.author	Zhu, T
dc.contributor.author	Zhou, W https://orcid.org/0000-0002-1680-2521
dc.contributor.author	Yu, PS
dc.date.accessioned	2020-11-29T19:55:48Z
dc.date.available	2020-11-29T19:55:48Z
dc.date.issued	2020-10
dc.identifier.citation	IEEE transactions on cybernetics, 2020, 50, (10), pp. 4214-4227
dc.identifier.issn	2168-2267
dc.identifier.issn	2168-2275
dc.identifier.uri	http://hdl.handle.net/10453/144459
dc.description.abstract	Agent advising is one of the key approaches to improve agent learning performance by enabling agents to ask for advice between each other. Existing agent advising approaches have two limitations. The first limitation is that all the agents in a system are assumed to be friendly and cooperative. However, in the real world, malicious agents may exist and provide false advice to hinder the learning performance of other agents. The second limitation is that the analysis of communication overhead in these approaches is either overlooked or simplified. However, in communication-constrained environments, communication overhead has to be carefully considered. To overcome the two limitations, this paper proposes a novel differentially private agent advising approach. Our approach employs the Laplace mechanism to add noise on the rewards used by student agents to select teacher agents. By using the differential privacy technique, the proposed approach can reduce the impact of malicious agents without identifying them. Also, by adopting the privacy budget concept, the proposed approach can naturally control communication overhead. The experimental results demonstrate the effectiveness of the proposed approach.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation	http://purl.org/au-research/grants/arc/LP170100123
dc.relation.ispartof	IEEE transactions on cybernetics
dc.relation.isbasedon	10.1109/tcyb.2019.2906574
dc.rights	© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0102 Applied Mathematics, 0801 Artificial Intelligence and Image Processing, 0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Differentially Private Malicious Agent Avoidance in Multiagent Advising Learning.
dc.type	Journal Article
utslib.citation.volume	50
utslib.location.activity	United States
utslib.for	0102 Applied Mathematics
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
dc.date.updated	2020-11-29T19:55:45Z
pubs.issue	10
pubs.publication-status	Published
pubs.volume	50
utslib.citation.issue	10

Abstract:

Agent advising is one of the key approaches to improve agent learning performance by enabling agents to ask for advice between each other. Existing agent advising approaches have two limitations. The first limitation is that all the agents in a system are assumed to be friendly and cooperative. However, in the real world, malicious agents may exist and provide false advice to hinder the learning performance of other agents. The second limitation is that the analysis of communication overhead in these approaches is either overlooked or simplified. However, in communication-constrained environments, communication overhead has to be carefully considered. To overcome the two limitations, this paper proposes a novel differentially private agent advising approach. Our approach employs the Laplace mechanism to add noise on the rewards used by student agents to select teacher agents. By using the differential privacy technique, the proposed approach can reduce the impact of malicious agents without identifying them. Also, by adopting the privacy budget concept, the proposed approach can naturally control communication overhead. The experimental results demonstrate the effectiveness of the proposed approach.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/144459