{"id":"https://openalex.org/W4416553123","doi":"https://doi.org/10.1609/aaaiss.v7i1.36895","title":"Query-Based Model Extraction Attack on GCN: A SurrogateModel Technique for Non-Euclidean Data","display_name":"Query-Based Model Extraction Attack on GCN: A SurrogateModel Technique for Non-Euclidean Data","publication_year":2025,"publication_date":"2025-11-23","ids":{"openalex":"https://openalex.org/W4416553123","doi":"https://doi.org/10.1609/aaaiss.v7i1.36895"},"language":null,"primary_location":{"id":"doi:10.1609/aaaiss.v7i1.36895","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaaiss.v7i1.36895","pdf_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/36895/39033","source":{"id":"https://openalex.org/S4389157828","display_name":"Proceedings of the AAAI Symposium Series","issn_l":"2994-4317","issn":["2994-4317"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Symposium Series","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/36895/39033","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050909830","display_name":"Sibtain Syed","orcid":"https://orcid.org/0009-0009-9937-2536"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Sibtain Syed","raw_affiliation_strings":["COMSATS University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"COMSATS University","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019784196","display_name":"Alvi Ataur Khalil","orcid":"https://orcid.org/0000-0002-4186-111X"},"institutions":[{"id":"https://openalex.org/I110378019","display_name":"Southern Illinois University Carbondale","ror":"https://ror.org/049kefs16","country_code":"US","type":"education","lineage":["https://openalex.org/I110378019","https://openalex.org/I2801502357"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alvi Ataur Khalil","raw_affiliation_strings":["Southern Illinois University Carbondale"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern Illinois University Carbondale","institution_ids":["https://openalex.org/I110378019"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068262430","display_name":"Kishor Datta Gupta","orcid":"https://orcid.org/0000-0001-6867-2653"},"institutions":[{"id":"https://openalex.org/I52064589","display_name":"Clark Atlanta University","ror":"https://ror.org/0397tsa92","country_code":"US","type":"education","lineage":["https://openalex.org/I52064589"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kishor Datta Gupta","raw_affiliation_strings":["Clark Atlanta University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clark Atlanta University","institution_ids":["https://openalex.org/I52064589"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101738054","display_name":"Saima Jabeen","orcid":"https://orcid.org/0000-0002-6542-9436"},"institutions":[{"id":"https://openalex.org/I4210096041","display_name":"Riyadh Elm University","ror":"https://ror.org/00rz3mr26","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210096041"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Saima Jabeen","raw_affiliation_strings":["Riyadh Elm University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Riyadh Elm University","institution_ids":["https://openalex.org/I4210096041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100648380","display_name":"Mohammad Ashiqur Rahman","orcid":"https://orcid.org/0000-0002-2963-7430"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Ashiqur Rahman","raw_affiliation_strings":["Florida international University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida international University","institution_ids":["https://openalex.org/I19700959"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33720726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"1","first_page":"265","last_page":"272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.829200029373169,"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":0.829200029373169,"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":0.08550000190734863,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.019999999552965164,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5353999733924866},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5317000150680542},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5264000296592712},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4729999899864197},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4239000082015991},{"id":"https://openalex.org/keywords/network-model","display_name":"Network model","score":0.40959998965263367},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.39399999380111694},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38100001215934753},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.37940001487731934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610999941825867},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5600000023841858},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131999850273132},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.387800008058548},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.37940001487731934},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C2779179475","wikidata":"https://www.wikidata.org/wiki/Q3545649","display_name":"Decoy","level":3,"score":0.33410000801086426},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C32946077","wikidata":"https://www.wikidata.org/wiki/Q618079","display_name":"Network analysis","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaaiss.v7i1.36895","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaaiss.v7i1.36895","pdf_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/36895/39033","source":{"id":"https://openalex.org/S4389157828","display_name":"Proceedings of the AAAI Symposium Series","issn_l":"2994-4317","issn":["2994-4317"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Symposium Series","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaaiss.v7i1.36895","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaaiss.v7i1.36895","pdf_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/36895/39033","source":{"id":"https://openalex.org/S4389157828","display_name":"Proceedings of the AAAI Symposium Series","issn_l":"2994-4317","issn":["2994-4317"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Symposium Series","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416553123.pdf","grobid_xml":"https://content.openalex.org/works/W4416553123.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"models":[3,72],"are":[4,54],"facing":[5],"serious":[6],"threats":[7,125],"from":[8],"Model":[9],"Extraction":[10],"Attacks,":[11],"in":[12,126,159,201],"which":[13,53],"a":[14,19,27,36,91,97,149,154],"black-box":[15],"model":[16,29,64,92,102],"owned":[17],"by":[18,30,103,114],"private":[20],"service":[21],"provider":[22],"can":[23],"be":[24,35,81],"cloned":[25],"to":[26,34,80,135,161,177,208],"surrogate":[28],"an":[31],"attacker":[32],"pretending":[33],"client":[37],"solely":[38],"through":[39],"query-based":[40],"access.":[41],"Unfortunately,":[42],"most":[43],"of":[44,131,165,199],"the":[45,109,129,136,146,182,197,202,209],"past":[46],"studies":[47],"only":[48],"focus":[49],"on":[50,56,67,87,119],"ML":[51],"models,":[52],"trained":[55],"Euclidean":[57],"spaces":[58],"like":[59],"images":[60],"and":[61,76,89,142,174],"texts,":[62],"while":[63],"extraction":[65,93,121],"attacks":[66],"Graph":[68,98],"Neural":[69],"Network":[70,100],"(GNN)":[71],"containing":[73],"node":[74,140],"features":[75],"graph":[77],"structure":[78],"need":[79],"explored.":[82],"The":[83,111],"respective":[84],"study":[85,112,147],"focuses":[86],"investigating":[88],"developing":[90],"attack":[94],"strategy":[95],"against":[96],"Convolutional":[99],"(GCN)":[101],"simulating":[104],"more":[105],"realistic":[106],"conditions":[107],"for":[108],"attacker.":[110],"begins":[113],"formalizing":[115],"threat":[116],"modeling":[117],"based":[118],"GCN":[120],"attacks,":[122],"categorizing":[123],"potential":[124],"accordance":[127],"with":[128,181,194],"levels":[130],"background":[132],"knowledge":[133],"accessible":[134],"attacker,":[137],"such":[138],"as":[139],"attributes":[141,164],"neighbor":[143,167],"connections.":[144],"Subsequently,":[145],"presents":[148],"novel":[150],"method":[151],"that":[152,192],"leverages":[153],"learnable":[155],"feature":[156],"synthesis":[157],"module":[158],"order":[160],"infer":[162],"missing":[163],"unknown":[166],"nodes,":[168],"evaluated":[169],"using":[170],"fidelity":[171],"(85-90":[172],"percentage)":[173],"KL-divergence":[175],"(0.28-0.10)":[176],"assess":[178],"behavioral":[179],"similarity":[180],"victim":[183],"model,":[184],"rather":[185],"than":[186],"exact":[187],"parameter":[188],"recovery.":[189],"Results":[190],"demonstrate":[191],"even":[193],"partial":[195],"knowledge,":[196],"majority":[198],"inputs":[200],"target":[203],"domain":[204],"yield":[205],"predictions":[206],"identical":[207],"original":[210],"model.":[211]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-23T00:00:00"}