A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning

Zhang, G; Sun, J; Xu, F; Sui, Y; Bandara, HMND; Chen, S; Menzies, T

A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning

Zhang, G Sun, J Xu, F Sui, Y

Bandara, HMND Chen, S Menzies, T

Permalink

Publisher:: IEEE COMPUTER SOC
Publication Type:: Journal Article
Citation:: IEEE Internet Computing, 2023, 27, (6), pp. 13-20
Issue Date:: 2023-11-01

Embargoed

	Filename	Description	Size
	A Tale of Two Cities Data and Configuration Variances in Robust Deep Learning.pdf	Accepted version	610 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Embargoed
Open Access

This item is currently unavailable due to the publisher's embargo.

The embargo period expires on 1 Nov 2025

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, G
dc.contributor.author	Sun, J
dc.contributor.author	Xu, F
dc.contributor.author	Sui, Y https://orcid.org/0000-0002-9510-6574
dc.contributor.author	Bandara, HMND
dc.contributor.author	Chen, S
dc.contributor.author	Menzies, T
dc.date.accessioned	2024-02-21T23:57:16Z
dc.date.available	2024-02-21T23:57:16Z
dc.date.issued	2023-11-01
dc.identifier.citation	IEEE Internet Computing, 2023, 27, (6), pp. 13-20
dc.identifier.issn	1089-7801
dc.identifier.issn	1941-0131
dc.identifier.uri	http://hdl.handle.net/10453/175816
dc.description.abstract	Deep neural networks (DNNs) have widespread applications in industries such as image recognition, supply chain, medical diagnosis, and autonomous driving. However, previous work has shown that the high accuracy of a DNN model does not imply high robustness (i.e., consistent performances on new and future datasets) because the input data and external environment (e.g., software and model configurations) for a deployed model are constantly changing. Therefore, ensuring robustness is crucial to enhance business and consumer confidence. Previous research focuses mostly on the data aspect of model variance. This article takes a holistic view of DNN robustness by summarizing the issues related to both data and software configuration variances. We also present a predictive framework using search-based optimization to generate representative variances for robust learning, considering data and configurations.
dc.language	English
dc.publisher	IEEE COMPUTER SOC
dc.relation.ispartof	IEEE Internet Computing
dc.relation.isbasedon	10.1109/MIC.2023.3322283
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject	0805 Distributed Computing, 0906 Electrical and Electronic Engineering, 1005 Communications Technologies
dc.subject.classification	Networking & Telecommunications
dc.subject.classification	4009 Electronics, sensors and digital hardware
dc.subject.classification	4606 Distributed computing and systems software
dc.title	A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning
dc.type	Journal Article
utslib.citation.volume	27
utslib.for	0805 Distributed Computing
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1005 Communications Technologies
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 - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	embargoed	*
utslib.copyright.embargo	2025-11-01T00:00:00+1000Z
dc.date.updated	2024-02-21T23:57:15Z
pubs.issue	6
pubs.publication-status	Published
pubs.volume	27
utslib.citation.issue	6

Abstract:

Deep neural networks (DNNs) have widespread applications in industries such as image recognition, supply chain, medical diagnosis, and autonomous driving. However, previous work has shown that the high accuracy of a DNN model does not imply high robustness (i.e., consistent performances on new and future datasets) because the input data and external environment (e.g., software and model configurations) for a deployed model are constantly changing. Therefore, ensuring robustness is crucial to enhance business and consumer confidence. Previous research focuses mostly on the data aspect of model variance. This article takes a holistic view of DNN robustness by summarizing the issues related to both data and software configuration variances. We also present a predictive framework using search-based optimization to generate representative variances for robust learning, considering data and configurations.

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

http://hdl.handle.net/10453/175816