{"id":"https://openalex.org/W3170068709","doi":"https://doi.org/10.1145/3447548.3467314","title":"TDGIA: Effective Injection Attacks on Graph Neural Networks","display_name":"TDGIA: Effective Injection Attacks on Graph Neural Networks","publication_year":2021,"publication_date":"2021-08-13","ids":{"openalex":"https://openalex.org/W3170068709","doi":"https://doi.org/10.1145/3447548.3467314","mag":"3170068709"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467314","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.06663","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xu Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Zou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qinkai Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinkai Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuxiao Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxiao Dong","raw_affiliation_strings":["Facebook AI, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, Seattle, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyu Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Guan","raw_affiliation_strings":["Biendata, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Biendata, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Evgeny Kharlamov","orcid":null},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Evgeny Kharlamov","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Renningen, Germany"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Renningen, Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jialiang Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialiang Lu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jie Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Tang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":7.558,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.97697026,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2461","last_page":"2471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6829000115394592},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.5252000093460083},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4571000039577484},{"id":"https://openalex.org/keywords/vulnerability-assessment","display_name":"Vulnerability assessment","score":0.45500001311302185},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44369998574256897},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.3763999938964844}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6420000195503235},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5252000093460083},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C167063184","wikidata":"https://www.wikidata.org/wiki/Q1400839","display_name":"Vulnerability assessment","level":3,"score":0.45500001311302185},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.36660000681877136},{"id":"https://openalex.org/C65856478","wikidata":"https://www.wikidata.org/wiki/Q3991682","display_name":"Attack model","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3447548.3467314","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.06663","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.06663","pdf_url":"https://arxiv.org/pdf/2106.06663","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.06663","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.06663","pdf_url":"https://arxiv.org/pdf/2106.06663","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1040948671","display_name":null,"funder_award_id":"61836013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2803831897","https://openalex.org/W2807021761","https://openalex.org/W2949208225","https://openalex.org/W2963857521","https://openalex.org/W2964301649","https://openalex.org/W3012846134","https://openalex.org/W3032123378","https://openalex.org/W3124962940"],"related_works":[],"abstract_inverted_index":{"Graph":[0,93],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4,15],"achieved":[5],"promising":[6],"performance":[7,162],"in":[8,153],"various":[9,150],"real-world":[10],"applications.":[11],"However,":[12],"recent":[13],"studies":[14],"shown":[16],"that":[17,143],"GNNs":[18,81,166],"are":[19],"vulnerable":[20],"to":[21,48,110,129],"adversarial":[22,68],"attacks.":[23,100],"In":[24,39],"this":[25],"paper,":[26],"we":[27,88],"study":[28],"a":[29],"recently-introduced":[30],"realistic":[31],"attack":[32,37,63,151,180],"scenario":[33],"on":[34,76,86,139,164,186],"graphs---graph":[35],"injection":[36,99],"(GIA).":[38],"the":[40,43,50,58,62,77,90,104,112,118,124,131,134,161,174,178],"GIA":[41,83],"scenario,":[42],"adversary":[44],"is":[45,64,170],"not":[46],"able":[47],"modify":[49],"existing":[51],"link":[52],"structure":[53],"and":[54,147],"node":[55],"attributes":[56],"of":[57,80,156,184],"input":[59],"graph,":[60],"instead":[61],"performed":[65],"by":[66,177],"injecting":[67],"nodes":[69,114],"into":[70],"it.":[71],"We":[72],"present":[73],"an":[74],"analysis":[75],"topological":[78,105],"vulnerability":[79],"under":[82],"setting,":[84],"based":[85],"which":[87],"propose":[89],"Topological":[91],"Defective":[92],"Injection":[94],"Attack":[95],"(TDGIA)":[96],"for":[97,115,133],"effective":[98],"TDGIA":[101,144,169],"first":[102],"introduces":[103],"defective":[106],"edge":[107],"selection":[108],"strategy":[109],"choose":[111],"original":[113],"connecting":[116],"with":[117],"injected":[119,135],"ones.":[120],"It":[121],"then":[122],"designs":[123],"smooth":[125],"feature":[126],"optimization":[127],"objective":[128],"generate":[130],"features":[132],"nodes.":[136],"Extensive":[137],"experiments":[138],"large-scale":[140],"datasets":[141],"show":[142],"can":[145],"consistently":[146],"significantly":[148],"outperform":[149],"baselines":[152],"attacking":[154],"dozens":[155],"defense":[157],"GNN":[158],"models.":[159],"Notably,":[160],"drop":[163],"target":[165],"resultant":[167],"from":[168],"more":[171],"than":[172],"double":[173],"damage":[175],"brought":[176],"best":[179],"solution":[181],"among":[182],"hundreds":[183],"submissions":[185],"KDD-CUP":[187],"2020.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":8}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2021-06-22T00:00:00"}