Two Views of Constrained Differential Privacy: Belief Revision and Update

Liu, L; Sun, K; Zhou, C; Feng, Y

Two Views of Constrained Differential Privacy: Belief Revision and Update

Liu, L Sun, K Zhou, C Feng, Y

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, 2023, 37, pp. 6450-6457
Issue Date:: 2023-06-27

Closed Access

	Filename	Description	Size
	4382.LiuL.pdf	Accepted version	369.81 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	Liu, L
dc.contributor.author	Sun, K
dc.contributor.author	Zhou, C
dc.contributor.author	Feng, Y https://orcid.org/0000-0002-3097-3896
dc.date.accessioned	2024-02-06T01:36:59Z
dc.date.available	2024-02-06T01:36:59Z
dc.date.issued	2023-06-27
dc.identifier.citation	Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, 2023, 37, pp. 6450-6457
dc.identifier.isbn	9781577358800
dc.identifier.uri	http://hdl.handle.net/10453/175345
dc.description.abstract	In this paper, we provide two views of constrained differential private (DP) mechanisms. The first one is as belief revision. A constrained DP mechanism is obtained by standard probabilistic conditioning, and hence can be naturally implemented by Monte Carlo algorithms. The other is as belief update. A constrained DP is defined according to l2-distance minimization postprocessing or projection and hence can be naturally implemented by optimization algorithms. The main advantage of these two perspectives is that we can make full use of the machinery of belief revision and update to show basic properties for constrained differential privacy especially some important new composition properties. Within the framework established in this paper, constrained DP algorithms in the literature can be classified either as belief revision or belief update. At the end of the paper, we demonstrate their differences especially in utility in a couple of scenarios.
dc.language	en
dc.relation	http://purl.org/au-research/grants/arc/DP220102059
dc.relation.ispartof	Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Two Views of Constrained Differential Privacy: Belief Revision and Update
dc.type	Conference Proceeding
utslib.citation.volume	37
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - QSI - Centre for Quantum Software and Information
utslib.copyright.status	closed_access	*
dc.date.updated	2024-02-06T01:36:58Z
pubs.publication-status	Published
pubs.volume	37

Abstract:

In this paper, we provide two views of constrained differential private (DP) mechanisms. The first one is as belief revision. A constrained DP mechanism is obtained by standard probabilistic conditioning, and hence can be naturally implemented by Monte Carlo algorithms. The other is as belief update. A constrained DP is defined according to l2-distance minimization postprocessing or projection and hence can be naturally implemented by optimization algorithms. The main advantage of these two perspectives is that we can make full use of the machinery of belief revision and update to show basic properties for constrained differential privacy especially some important new composition properties. Within the framework established in this paper, constrained DP algorithms in the literature can be classified either as belief revision or belief update. At the end of the paper, we demonstrate their differences especially in utility in a couple of scenarios.

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

http://hdl.handle.net/10453/175345