Adversarial attack and defense on graph neural networks: a survey

For the numerous existing adversarial attack and defense methods on GNN, the main adversarial attack and defense algorithms of GNN were reviewed comprehensively, as well as robustness analysis techniques.Besides, the commonly used benchmark datasets and evaluation metrics in the security research of...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinyin CHEN, Dunjie ZHANG, Guohan HUANG, Xiang LIN, Liang BAO
Format: Article
Language:English
Published: POSTS&TELECOM PRESS Co., LTD 2021-06-01
Series:网络与信息安全学报
Subjects:
Online Access:http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021051
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850092367757967360
author Jinyin CHEN
Dunjie ZHANG
Guohan HUANG
Xiang LIN
Liang BAO
author_facet Jinyin CHEN
Dunjie ZHANG
Guohan HUANG
Xiang LIN
Liang BAO
author_sort Jinyin CHEN
collection DOAJ
description For the numerous existing adversarial attack and defense methods on GNN, the main adversarial attack and defense algorithms of GNN were reviewed comprehensively, as well as robustness analysis techniques.Besides, the commonly used benchmark datasets and evaluation metrics in the security research of GNN were introduced.In conclusion, some insights on the future research direction of adversarial attacks and the trend of development were put forward.
format Article
id doaj-art-e52ca536de0b487cbd12df43d3e17cc0
institution DOAJ
issn 2096-109X
language English
publishDate 2021-06-01
publisher POSTS&TELECOM PRESS Co., LTD
record_format Article
series 网络与信息安全学报
spelling doaj-art-e52ca536de0b487cbd12df43d3e17cc02025-08-20T02:42:08ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2021-06-01712859563329Adversarial attack and defense on graph neural networks: a surveyJinyin CHENDunjie ZHANGGuohan HUANGXiang LINLiang BAOFor the numerous existing adversarial attack and defense methods on GNN, the main adversarial attack and defense algorithms of GNN were reviewed comprehensively, as well as robustness analysis techniques.Besides, the commonly used benchmark datasets and evaluation metrics in the security research of GNN were introduced.In conclusion, some insights on the future research direction of adversarial attacks and the trend of development were put forward.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021051graph neural networksadversarial attackdefense algorithmsrobustness analysis
spellingShingle Jinyin CHEN
Dunjie ZHANG
Guohan HUANG
Xiang LIN
Liang BAO
Adversarial attack and defense on graph neural networks: a survey
网络与信息安全学报
graph neural networks
adversarial attack
defense algorithms
robustness analysis
title Adversarial attack and defense on graph neural networks: a survey
title_full Adversarial attack and defense on graph neural networks: a survey
title_fullStr Adversarial attack and defense on graph neural networks: a survey
title_full_unstemmed Adversarial attack and defense on graph neural networks: a survey
title_short Adversarial attack and defense on graph neural networks: a survey
title_sort adversarial attack and defense on graph neural networks a survey
topic graph neural networks
adversarial attack
defense algorithms
robustness analysis
url http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021051
work_keys_str_mv AT jinyinchen adversarialattackanddefenseongraphneuralnetworksasurvey
AT dunjiezhang adversarialattackanddefenseongraphneuralnetworksasurvey
AT guohanhuang adversarialattackanddefenseongraphneuralnetworksasurvey
AT xianglin adversarialattackanddefenseongraphneuralnetworksasurvey
AT liangbao adversarialattackanddefenseongraphneuralnetworksasurvey