Structack: Structure-based Adversarial Attacks on Graph Neural Networks

Structack: Structure-based Adversarial Attacks on Graph Neural NetworksStructure-based, uninformed adversarial attacks on graph neural networks

doi: 10.1145/3465336.3475110
name: Structack: Structure-based Adversarial Attacks on Graph Neural Networks
pages: 11
venue: Proceedings of the 32nd ACM Conference on Hypertext and Social Media (HT ’21)
acm_url: https://dl.acm.org/doi/10.1145/3465336.3475110
authors: 1.Hussain Hussain
2.Tomislav Duricic
3.Elisabeth Lex
4.Denis Helic
5.Markus Strohmaier
6.Roman Kern
doi_url: https://doi.org/10.1145/3465336.3475110
license: This work is licensed under a Creative Commons Attribution International 4.0 License.
summary: Structure-based, uninformed adversarial attacks on graph neural networks
keywords: Graph neural networks; adversarial attacks; network centrality;
source_pdf: 3465336.3475110.pdf
import_kind: full_text
open_access: false
ccs_concepts: · Computing methodologies →Machine learning; Adversar-
displayAuthor: Hussain Hussain, Tomislav Duricic, Elisabeth Lex, Denis Helic, Markus Strohmaier, Roman Kern
source_sha256: 5592ac8ab49764ae32bd6bd8515339a72ea723eb10d03f0851149f38f820d689
publication_year: 2021