Fake Node Attacks on Graph Convolutional Networks Article Swipe
Xiaoyun Wang
,
Minhao Cheng
,
Joe Eaton
,
Cho‐Jui Hsieh
,
S. Felix Wu
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.47852/bonviewjcce2202321
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.47852/bonviewjcce2202321
In this paper, we study the robustness of graph convolutional networks (GCNs). Previous works have shown that GCNs are vulnerable to adversarial perturbation on adjacency or feature matrices of existing nodes; however, such attacks are usually unrealistic in real applications. For instance, in social network applications, the attacker will need to hack into either the client or server to change existing links or features. In this paper, we propose a new type of “fake node attacks” to attack GCNs by adding malicious fake nodes. This is much more realistic than previous attacks; in social network applications, the attacker only needs to register a set of fake accounts and link to existing ones. To conduct fake node attacks, a greedy algorithm is proposed to generate edges of malicious nodes and their corresponding features aiming to minimize the classification accuracy on the target nodes. In addition, we introduce a discriminator to classify malicious nodes from real nodes and propose a Greedy-generative adversarial network attack to simultaneously update the discriminator and the attacker, to make malicious nodes indistinguishable from the real ones. Our non-targeted attack decreases the accuracy of GCN down to 0.03, and our targeted attack reaches a success rate of 78% on a group of 100 nodes and 90% on average for attacking a single target node. Received: 13 July 2022 | Revised: 18 July 2022 | Accepted: 24 August 2022 Conflicts of Interest The authors declare that they have no conflicts of interest to this work.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.47852/bonviewjcce2202321
- https://ojs.bonviewpress.com/index.php/JCCE/article/download/321/229
- OA Status
- diamond
- Cited By
- 71
- References
- 61
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4312759853
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4312759853Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.47852/bonviewjcce2202321Digital Object Identifier
- Title
-
Fake Node Attacks on Graph Convolutional NetworksWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-10-28Full publication date if available
- Authors
-
Xiaoyun Wang, Minhao Cheng, Joe Eaton, Cho‐Jui Hsieh, S. Felix WuList of authors in order
- Landing page
-
https://doi.org/10.47852/bonviewjcce2202321Publisher landing page
- PDF URL
-
https://ojs.bonviewpress.com/index.php/JCCE/article/download/321/229Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://ojs.bonviewpress.com/index.php/JCCE/article/download/321/229Direct OA link when available
- Concepts
-
Computer science, Discriminator, Computer security, Graph, Computer network, Node (physics), Attack model, Robustness (evolution), Greedy algorithm, Theoretical computer science, Algorithm, Engineering, Detector, Gene, Chemistry, Biochemistry, Structural engineering, TelecommunicationsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
71Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 7, 2024: 36, 2023: 28Per-year citation counts (last 5 years)
- References (count)
-
61Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4312759853 |
|---|---|
| doi | https://doi.org/10.47852/bonviewjcce2202321 |
| ids.doi | https://doi.org/10.47852/bonviewjcce2202321 |
| ids.openalex | https://openalex.org/W4312759853 |
| fwci | 13.90171624 |
| type | article |
| title | Fake Node Attacks on Graph Convolutional Networks |
| biblio.issue | 4 |
| biblio.volume | 1 |
| biblio.last_page | 173 |
| biblio.first_page | 165 |
| topics[0].id | https://openalex.org/T11273 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.996399998664856 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Advanced Graph Neural Networks |
| topics[1].id | https://openalex.org/T11689 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9937999844551086 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Adversarial Robustness in Machine Learning |
| topics[2].id | https://openalex.org/T10400 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9740999937057495 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1705 |
| topics[2].subfield.display_name | Computer Networks and Communications |
| topics[2].display_name | Network Security and Intrusion Detection |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7802311182022095 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2779803651 |
| concepts[1].level | 3 |
| concepts[1].score | 0.6745267510414124 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q5282088 |
| concepts[1].display_name | Discriminator |
| concepts[2].id | https://openalex.org/C38652104 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5122913122177124 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[2].display_name | Computer security |
| concepts[3].id | https://openalex.org/C132525143 |
| concepts[3].level | 2 |
| concepts[3].score | 0.4734984040260315 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[3].display_name | Graph |
| concepts[4].id | https://openalex.org/C31258907 |
| concepts[4].level | 1 |
| concepts[4].score | 0.451097697019577 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[4].display_name | Computer network |
| concepts[5].id | https://openalex.org/C62611344 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4460177421569824 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1062658 |
| concepts[5].display_name | Node (physics) |
| concepts[6].id | https://openalex.org/C65856478 |
| concepts[6].level | 2 |
| concepts[6].score | 0.44030874967575073 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q3991682 |
| concepts[6].display_name | Attack model |
| concepts[7].id | https://openalex.org/C63479239 |
| concepts[7].level | 3 |
| concepts[7].score | 0.431018590927124 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[7].display_name | Robustness (evolution) |
| concepts[8].id | https://openalex.org/C51823790 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4228935241699219 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q504353 |
| concepts[8].display_name | Greedy algorithm |
| concepts[9].id | https://openalex.org/C80444323 |
| concepts[9].level | 1 |
| concepts[9].score | 0.32928135991096497 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[9].display_name | Theoretical computer science |
| concepts[10].id | https://openalex.org/C11413529 |
| concepts[10].level | 1 |
| concepts[10].score | 0.20498549938201904 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[10].display_name | Algorithm |
| concepts[11].id | https://openalex.org/C127413603 |
| concepts[11].level | 0 |
| concepts[11].score | 0.08424979448318481 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[11].display_name | Engineering |
| concepts[12].id | https://openalex.org/C94915269 |
| concepts[12].level | 2 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1834857 |
| concepts[12].display_name | Detector |
| concepts[13].id | https://openalex.org/C104317684 |
| concepts[13].level | 2 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[13].display_name | Gene |
| concepts[14].id | https://openalex.org/C185592680 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[14].display_name | Chemistry |
| concepts[15].id | https://openalex.org/C55493867 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[15].display_name | Biochemistry |
| concepts[16].id | https://openalex.org/C66938386 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q633538 |
| concepts[16].display_name | Structural engineering |
| concepts[17].id | https://openalex.org/C76155785 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[17].display_name | Telecommunications |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7802311182022095 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/discriminator |
| keywords[1].score | 0.6745267510414124 |
| keywords[1].display_name | Discriminator |
| keywords[2].id | https://openalex.org/keywords/computer-security |
| keywords[2].score | 0.5122913122177124 |
| keywords[2].display_name | Computer security |
| keywords[3].id | https://openalex.org/keywords/graph |
| keywords[3].score | 0.4734984040260315 |
| keywords[3].display_name | Graph |
| keywords[4].id | https://openalex.org/keywords/computer-network |
| keywords[4].score | 0.451097697019577 |
| keywords[4].display_name | Computer network |
| keywords[5].id | https://openalex.org/keywords/node |
| keywords[5].score | 0.4460177421569824 |
| keywords[5].display_name | Node (physics) |
| keywords[6].id | https://openalex.org/keywords/attack-model |
| keywords[6].score | 0.44030874967575073 |
| keywords[6].display_name | Attack model |
| keywords[7].id | https://openalex.org/keywords/robustness |
| keywords[7].score | 0.431018590927124 |
| keywords[7].display_name | Robustness (evolution) |
| keywords[8].id | https://openalex.org/keywords/greedy-algorithm |
| keywords[8].score | 0.4228935241699219 |
| keywords[8].display_name | Greedy algorithm |
| keywords[9].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[9].score | 0.32928135991096497 |
| keywords[9].display_name | Theoretical computer science |
| keywords[10].id | https://openalex.org/keywords/algorithm |
| keywords[10].score | 0.20498549938201904 |
| keywords[10].display_name | Algorithm |
| keywords[11].id | https://openalex.org/keywords/engineering |
| keywords[11].score | 0.08424979448318481 |
| keywords[11].display_name | Engineering |
| language | en |
| locations[0].id | doi:10.47852/bonviewjcce2202321 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4387278861 |
| locations[0].source.issn | 2810-9503, 2810-9570 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2810-9503 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Journal of Computational and Cognitive Engineering |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://ojs.bonviewpress.com/index.php/JCCE/article/download/321/229 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Journal of Computational and Cognitive Engineering |
| locations[0].landing_page_url | https://doi.org/10.47852/bonviewjcce2202321 |
| locations[1].id | pmh:oai:doaj.org/article:301560d014fc42a3996687c0186230c7 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306401280 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | DOAJ (DOAJ: Directory of Open Access Journals) |
| locations[1].source.host_organization | |
| locations[1].source.host_organization_name | |
| locations[1].license | cc-by-sa |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by-sa |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | Journal of Computational and Cognitive Engineering, Vol 1, Iss 4, Pp 165-173 (2022) |
| locations[1].landing_page_url | https://doaj.org/article/301560d014fc42a3996687c0186230c7 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5046791174 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-8148-9060 |
| authorships[0].author.display_name | Xiaoyun Wang |
| authorships[0].affiliations[0].raw_affiliation_string | University of California, USA |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xiaoyun Wang |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | University of California, USA |
| authorships[1].author.id | https://openalex.org/A5000534132 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3965-4215 |
| authorships[1].author.display_name | Minhao Cheng |
| authorships[1].affiliations[0].raw_affiliation_string | University of California, USA |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Minhao Cheng |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | University of California, USA |
| authorships[2].author.id | https://openalex.org/A5073670556 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7540-995X |
| authorships[2].author.display_name | Joe Eaton |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I4210127875 |
| authorships[2].affiliations[0].raw_affiliation_string | NVIDIA, California, USA |
| authorships[2].institutions[0].id | https://openalex.org/I4210127875 |
| authorships[2].institutions[0].ror | https://ror.org/03jdj4y14 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I4210127875 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | Nvidia (United States) |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Joe Eaton |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | NVIDIA, California, USA |
| authorships[3].author.id | https://openalex.org/A5010841999 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3520-9627 |
| authorships[3].author.display_name | Cho‐Jui Hsieh |
| authorships[3].affiliations[0].raw_affiliation_string | University of California, USA |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Cho-Jui Hsieh |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | University of California, USA |
| authorships[4].author.id | https://openalex.org/A5088633029 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-4644-569X |
| authorships[4].author.display_name | S. Felix Wu |
| authorships[4].affiliations[0].raw_affiliation_string | University of California, USA |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | S. Felix Wu |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | University of California, USA |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ojs.bonviewpress.com/index.php/JCCE/article/download/321/229 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-01-05T00:00:00 |
| display_name | Fake Node Attacks on Graph Convolutional Networks |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11273 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.996399998664856 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Advanced Graph Neural Networks |
| related_works | https://openalex.org/W4387497383, https://openalex.org/W3183948672, https://openalex.org/W3173606202, https://openalex.org/W3110381201, https://openalex.org/W2948807893, https://openalex.org/W2935909890, https://openalex.org/W2778153218, https://openalex.org/W2758277628, https://openalex.org/W1531601525, https://openalex.org/W4293202849 |
| cited_by_count | 71 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 7 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 36 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 28 |
| locations_count | 2 |
| best_oa_location.id | doi:10.47852/bonviewjcce2202321 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4387278861 |
| best_oa_location.source.issn | 2810-9503, 2810-9570 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2810-9503 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Journal of Computational and Cognitive Engineering |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://ojs.bonviewpress.com/index.php/JCCE/article/download/321/229 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Journal of Computational and Cognitive Engineering |
| best_oa_location.landing_page_url | https://doi.org/10.47852/bonviewjcce2202321 |
| primary_location.id | doi:10.47852/bonviewjcce2202321 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4387278861 |
| primary_location.source.issn | 2810-9503, 2810-9570 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2810-9503 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Journal of Computational and Cognitive Engineering |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://ojs.bonviewpress.com/index.php/JCCE/article/download/321/229 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Journal of Computational and Cognitive Engineering |
| primary_location.landing_page_url | https://doi.org/10.47852/bonviewjcce2202321 |
| publication_date | 2022-10-28 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W2769999273, https://openalex.org/W2516574342, https://openalex.org/W2772114856, https://openalex.org/W2786915849, https://openalex.org/W6966866225, https://openalex.org/W2791941932, https://openalex.org/W6751569023, https://openalex.org/W2468907370, https://openalex.org/W6746678344, https://openalex.org/W2778115935, https://openalex.org/W2783097478, https://openalex.org/W1945616565, https://openalex.org/W2624431344, https://openalex.org/W2798801120, https://openalex.org/W2738015883, https://openalex.org/W2519887557, https://openalex.org/W6729756640, https://openalex.org/W2562979205, https://openalex.org/W6737220129, https://openalex.org/W6746449270, https://openalex.org/W2640329709, https://openalex.org/W2609920186, https://openalex.org/W2408141691, https://openalex.org/W2344365922, https://openalex.org/W6726923012, https://openalex.org/W2770671706, https://openalex.org/W6741419198, https://openalex.org/W6747184836, https://openalex.org/W2620038827, https://openalex.org/W2604505099, https://openalex.org/W3100848837, https://openalex.org/W6745847742, https://openalex.org/W2803831897, https://openalex.org/W2963062382, https://openalex.org/W2735135478, https://openalex.org/W4294558607, https://openalex.org/W2766108848, https://openalex.org/W2964346747, https://openalex.org/W2776936219, https://openalex.org/W2964236544, https://openalex.org/W2963118571, https://openalex.org/W2964097310, https://openalex.org/W2963920355, https://openalex.org/W3106412272, https://openalex.org/W4297571622, https://openalex.org/W2963695795, https://openalex.org/W2609368435, https://openalex.org/W2966149470, https://openalex.org/W2963857521, https://openalex.org/W2963744840, https://openalex.org/W2962818281, https://openalex.org/W2759063673, https://openalex.org/W2964283260, https://openalex.org/W2963834268, https://openalex.org/W2963969878, https://openalex.org/W4293846201, https://openalex.org/W2775467454, https://openalex.org/W2964321699, https://openalex.org/W2777353073, https://openalex.org/W2964015378, https://openalex.org/W2963389226 |
| referenced_works_count | 61 |
| abstract_inverted_index.a | 69, 102, 117, 146, 157, 195, 201, 212 |
| abstract_inverted_index.| | 220, 225 |
| abstract_inverted_index.13 | 217 |
| abstract_inverted_index.18 | 222 |
| abstract_inverted_index.24 | 227 |
| abstract_inverted_index.In | 0, 64, 142 |
| abstract_inverted_index.To | 112 |
| abstract_inverted_index.by | 79 |
| abstract_inverted_index.in | 37, 42, 92 |
| abstract_inverted_index.is | 85, 120 |
| abstract_inverted_index.no | 239 |
| abstract_inverted_index.of | 7, 28, 72, 104, 125, 185, 198, 203, 231, 241 |
| abstract_inverted_index.on | 23, 138, 200, 208 |
| abstract_inverted_index.or | 25, 56, 62 |
| abstract_inverted_index.to | 20, 50, 58, 76, 100, 109, 122, 133, 148, 162, 170, 188, 243 |
| abstract_inverted_index.we | 3, 67, 144 |
| abstract_inverted_index.100 | 204 |
| abstract_inverted_index.78% | 199 |
| abstract_inverted_index.90% | 207 |
| abstract_inverted_index.For | 40 |
| abstract_inverted_index.GCN | 186 |
| abstract_inverted_index.Our | 179 |
| abstract_inverted_index.The | 233 |
| abstract_inverted_index.and | 107, 128, 155, 167, 190, 206 |
| abstract_inverted_index.are | 18, 34 |
| abstract_inverted_index.for | 210 |
| abstract_inverted_index.new | 70 |
| abstract_inverted_index.our | 191 |
| abstract_inverted_index.set | 103 |
| abstract_inverted_index.the | 5, 46, 54, 96, 135, 139, 165, 168, 176, 183 |
| abstract_inverted_index.2022 | 219, 224, 229 |
| abstract_inverted_index.GCNs | 17, 78 |
| abstract_inverted_index.July | 218, 223 |
| abstract_inverted_index.This | 84 |
| abstract_inverted_index.down | 187 |
| abstract_inverted_index.fake | 82, 105, 114 |
| abstract_inverted_index.from | 152, 175 |
| abstract_inverted_index.hack | 51 |
| abstract_inverted_index.have | 14, 238 |
| abstract_inverted_index.into | 52 |
| abstract_inverted_index.link | 108 |
| abstract_inverted_index.make | 171 |
| abstract_inverted_index.more | 87 |
| abstract_inverted_index.much | 86 |
| abstract_inverted_index.need | 49 |
| abstract_inverted_index.node | 74, 115 |
| abstract_inverted_index.only | 98 |
| abstract_inverted_index.rate | 197 |
| abstract_inverted_index.real | 38, 153, 177 |
| abstract_inverted_index.such | 32 |
| abstract_inverted_index.than | 89 |
| abstract_inverted_index.that | 16, 236 |
| abstract_inverted_index.they | 237 |
| abstract_inverted_index.this | 1, 65, 244 |
| abstract_inverted_index.type | 71 |
| abstract_inverted_index.will | 48 |
| abstract_inverted_index.0.03, | 189 |
| abstract_inverted_index.edges | 124 |
| abstract_inverted_index.graph | 8 |
| abstract_inverted_index.group | 202 |
| abstract_inverted_index.links | 61 |
| abstract_inverted_index.needs | 99 |
| abstract_inverted_index.node. | 215 |
| abstract_inverted_index.nodes | 127, 151, 154, 173, 205 |
| abstract_inverted_index.ones. | 111, 178 |
| abstract_inverted_index.shown | 15 |
| abstract_inverted_index.study | 4 |
| abstract_inverted_index.their | 129 |
| abstract_inverted_index.work. | 245 |
| abstract_inverted_index.works | 13 |
| abstract_inverted_index.August | 228 |
| abstract_inverted_index.adding | 80 |
| abstract_inverted_index.aiming | 132 |
| abstract_inverted_index.attack | 77, 161, 181, 193 |
| abstract_inverted_index.change | 59 |
| abstract_inverted_index.client | 55 |
| abstract_inverted_index.either | 53 |
| abstract_inverted_index.greedy | 118 |
| abstract_inverted_index.nodes. | 83, 141 |
| abstract_inverted_index.nodes; | 30 |
| abstract_inverted_index.paper, | 2, 66 |
| abstract_inverted_index.server | 57 |
| abstract_inverted_index.single | 213 |
| abstract_inverted_index.social | 43, 93 |
| abstract_inverted_index.target | 140, 214 |
| abstract_inverted_index.update | 164 |
| abstract_inverted_index.(GCNs). | 11 |
| abstract_inverted_index.attacks | 33 |
| abstract_inverted_index.authors | 234 |
| abstract_inverted_index.average | 209 |
| abstract_inverted_index.conduct | 113 |
| abstract_inverted_index.declare | 235 |
| abstract_inverted_index.feature | 26 |
| abstract_inverted_index.network | 44, 94, 160 |
| abstract_inverted_index.propose | 68, 156 |
| abstract_inverted_index.reaches | 194 |
| abstract_inverted_index.success | 196 |
| abstract_inverted_index.usually | 35 |
| abstract_inverted_index.“fake | 73 |
| abstract_inverted_index.Interest | 232 |
| abstract_inverted_index.Previous | 12 |
| abstract_inverted_index.Revised: | 221 |
| abstract_inverted_index.accounts | 106 |
| abstract_inverted_index.accuracy | 137, 184 |
| abstract_inverted_index.attacker | 47, 97 |
| abstract_inverted_index.attacks, | 116 |
| abstract_inverted_index.attacks; | 91 |
| abstract_inverted_index.classify | 149 |
| abstract_inverted_index.existing | 29, 60, 110 |
| abstract_inverted_index.features | 131 |
| abstract_inverted_index.generate | 123 |
| abstract_inverted_index.however, | 31 |
| abstract_inverted_index.interest | 242 |
| abstract_inverted_index.matrices | 27 |
| abstract_inverted_index.minimize | 134 |
| abstract_inverted_index.networks | 10 |
| abstract_inverted_index.previous | 90 |
| abstract_inverted_index.proposed | 121 |
| abstract_inverted_index.register | 101 |
| abstract_inverted_index.targeted | 192 |
| abstract_inverted_index.Accepted: | 226 |
| abstract_inverted_index.Conflicts | 230 |
| abstract_inverted_index.Received: | 216 |
| abstract_inverted_index.addition, | 143 |
| abstract_inverted_index.adjacency | 24 |
| abstract_inverted_index.algorithm | 119 |
| abstract_inverted_index.attacker, | 169 |
| abstract_inverted_index.attacking | 211 |
| abstract_inverted_index.conflicts | 240 |
| abstract_inverted_index.decreases | 182 |
| abstract_inverted_index.features. | 63 |
| abstract_inverted_index.instance, | 41 |
| abstract_inverted_index.introduce | 145 |
| abstract_inverted_index.malicious | 81, 126, 150, 172 |
| abstract_inverted_index.realistic | 88 |
| abstract_inverted_index.attacks” | 75 |
| abstract_inverted_index.robustness | 6 |
| abstract_inverted_index.vulnerable | 19 |
| abstract_inverted_index.adversarial | 21, 159 |
| abstract_inverted_index.unrealistic | 36 |
| abstract_inverted_index.non-targeted | 180 |
| abstract_inverted_index.perturbation | 22 |
| abstract_inverted_index.applications, | 45, 95 |
| abstract_inverted_index.applications. | 39 |
| abstract_inverted_index.convolutional | 9 |
| abstract_inverted_index.corresponding | 130 |
| abstract_inverted_index.discriminator | 147, 166 |
| abstract_inverted_index.classification | 136 |
| abstract_inverted_index.simultaneously | 163 |
| abstract_inverted_index.Greedy-generative | 158 |
| abstract_inverted_index.indistinguishable | 174 |
| cited_by_percentile_year.max | 100 |
| cited_by_percentile_year.min | 99 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/10 |
| sustainable_development_goals[0].score | 0.7599999904632568 |
| sustainable_development_goals[0].display_name | Reduced inequalities |
| citation_normalized_percentile.value | 0.98555229 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |