Survey on Robustness Verification of Feedforward Neural Networks and Recurrent Neural Networks

Liu, Y; Yang, PF; Zhang, LJ; Wu, ZL; Feng, Y

Survey on Robustness Verification of Feedforward Neural Networks and Recurrent Neural Networks

Liu, Y Yang, PF Zhang, LJ Wu, ZL Feng, Y

Permalink

Publication Type:: Journal Article
Citation:: Ruan Jian Xue Bao/Journal of Software, 2023, 34, (7), pp. 1-33
Issue Date:: 2023-01-01

Closed Access

	Filename	Description	Size
	RNN.pdf	Accepted version	4.63 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	Liu, Y
dc.contributor.author	Yang, PF
dc.contributor.author	Zhang, LJ
dc.contributor.author	Wu, ZL
dc.contributor.author	Feng, Y https://orcid.org/0000-0002-3097-3896
dc.date.accessioned	2024-02-06T01:41:24Z
dc.date.available	2024-02-06T01:41:24Z
dc.date.issued	2023-01-01
dc.identifier.citation	Ruan Jian Xue Bao/Journal of Software, 2023, 34, (7), pp. 1-33
dc.identifier.issn	1000-9825
dc.identifier.uri	http://hdl.handle.net/10453/175347
dc.description.abstract	With the advent of the intelligent age, the applications of intelligent systems equipped with deep neural networks (DNNs) have penetrated into every aspect of our life. However, due to the black-box and large-scale characteristics, the predictions of the neural networks are difficult to be completely convincing. When neural networks are applied to security-critical fields such as autonomous driving, how to ensure their security is still a great challenge for the academia and industry. For this reason, the academia carried out much research on robustness—a kind of special security of neural networks, and proposed many algorithms for robustness analysis and verification. The verification algorithms for feedforward neural networks (FNNs) include precise algorithms and approximate algorithms, which have been developed relatively prosperously. The verification algorithms for other types of networks, such as recurrent neural networks (RNNs), are still in the primary stage. This study reviews the current development of DNNs and the challenges of deploying them into our life. It also exhaustively investigates the robustness verification algorithms of FNNs and RNNs, analyzes and compares the intrinsic connection among these algorithms. The security verification algorithms of RNNs in specific application scenarios are investigated, and the future research directions in the robustness verification field of neural networks are clarified.
dc.language	en
dc.relation	Beijing Baidu Netcom Science and Technology Co Ltd
dc.relation.ispartof	Ruan Jian Xue Bao/Journal of Software
dc.relation.isbasedon	10.13328/j.cnki.jos.006863
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0802 Computation Theory and Mathematics, 0803 Computer Software, 0805 Distributed Computing
dc.subject.classification	Software Engineering
dc.subject.classification	46 Information and computing sciences
dc.title	Survey on Robustness Verification of Feedforward Neural Networks and Recurrent Neural Networks
dc.type	Journal Article
utslib.citation.volume	34
utslib.for	0802 Computation Theory and Mathematics
utslib.for	0803 Computer Software
utslib.for	0805 Distributed Computing
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	2024-02-06T01:41:21Z
pubs.issue	7
pubs.publication-status	Published
pubs.volume	34
utslib.citation.issue	7

Abstract:

With the advent of the intelligent age, the applications of intelligent systems equipped with deep neural networks (DNNs) have penetrated into every aspect of our life. However, due to the black-box and large-scale characteristics, the predictions of the neural networks are difficult to be completely convincing. When neural networks are applied to security-critical fields such as autonomous driving, how to ensure their security is still a great challenge for the academia and industry. For this reason, the academia carried out much research on robustness—a kind of special security of neural networks, and proposed many algorithms for robustness analysis and verification. The verification algorithms for feedforward neural networks (FNNs) include precise algorithms and approximate algorithms, which have been developed relatively prosperously. The verification algorithms for other types of networks, such as recurrent neural networks (RNNs), are still in the primary stage. This study reviews the current development of DNNs and the challenges of deploying them into our life. It also exhaustively investigates the robustness verification algorithms of FNNs and RNNs, analyzes and compares the intrinsic connection among these algorithms. The security verification algorithms of RNNs in specific application scenarios are investigated, and the future research directions in the robustness verification field of neural networks are clarified.

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

http://hdl.handle.net/10453/175347