Applying differential privacy mechanism in artificial intelligence

Zhu, T; Yu, PS

Applying differential privacy mechanism in artificial intelligence

Zhu, T

Yu, PS

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: Proceedings - International Conference on Distributed Computing Systems, 2019, 2019-July, pp. 1601-1609
Issue Date:: 2019-07-01

Closed Access

	Filename	Description	Size
	08885331.pdf	Published version	248.19 kB	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	Zhu, T https://orcid.org/0000-0003-3411-7947
dc.contributor.author	Yu, PS
dc.date	2019-07-07
dc.date.accessioned	2020-06-21T00:07:48Z
dc.date.available	2020-06-21T00:07:48Z
dc.date.issued	2019-07-01
dc.identifier.citation	Proceedings - International Conference on Distributed Computing Systems, 2019, 2019-July, pp. 1601-1609
dc.identifier.isbn	9781728125190
dc.identifier.issn	1063-6927
dc.identifier.issn	2575-8411
dc.identifier.uri	http://hdl.handle.net/10453/141593
dc.description.abstract	© 2019 IEEE. Artificial Intelligence (AI) has attracted a large amount of attention in recent years. However, several new problems, such as privacy violations, security issues, or effectiveness, have been emerging. Differential privacy has several attractive properties that make it quite valuable for AI, such as privacy preservation, security, randomization, composition, and stability. Therefore, this paper presents differential privacy mechanisms for multi-agent systems, reinforcement learning, and knowledge transfer based on those properties, which proves that current AI can benefit from differential privacy mechanisms. In addition, the previous usage of differential privacy mechanisms in private machine learning, distributed machine learning, and fairness in models is discussed, bringing several possible avenues to use differential privacy mechanisms in AI. The purpose of this paper is to deliver the initial idea of how to integrate AI with differential privacy mechanisms and to explore more possibilities to improve AIs performance.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	Proceedings - International Conference on Distributed Computing Systems
dc.relation.ispartof	International Conference on Distributed Computing Systems
dc.relation.isbasedon	10.1109/ICDCS.2019.00159
dc.rights	© 2019 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/restrictedAccess
dc.title	Applying differential privacy mechanism in artificial intelligence
dc.type	Conference Proceeding
utslib.citation.volume	2019-July
utslib.location.activity	Dallas, TX, USA
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2020-06-21T00:07:43Z
pubs.finish-date	2019-07-10
pubs.place-of-publication	Piscataway. USA
pubs.publication-status	Published
pubs.start-date	2019-07-07
pubs.volume	2019-July
dc.location	Piscataway. USA

Abstract:

© 2019 IEEE. Artificial Intelligence (AI) has attracted a large amount of attention in recent years. However, several new problems, such as privacy violations, security issues, or effectiveness, have been emerging. Differential privacy has several attractive properties that make it quite valuable for AI, such as privacy preservation, security, randomization, composition, and stability. Therefore, this paper presents differential privacy mechanisms for multi-agent systems, reinforcement learning, and knowledge transfer based on those properties, which proves that current AI can benefit from differential privacy mechanisms. In addition, the previous usage of differential privacy mechanisms in private machine learning, distributed machine learning, and fairness in models is discussed, bringing several possible avenues to use differential privacy mechanisms in AI. The purpose of this paper is to deliver the initial idea of how to integrate AI with differential privacy mechanisms and to explore more possibilities to improve AIs performance.

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

http://hdl.handle.net/10453/141593