{"id":"https://openalex.org/W2810683959","doi":"https://doi.org/10.3390/info9080189","title":"First Steps towards Data-Driven Adversarial Deduplication","display_name":"First Steps towards Data-Driven Adversarial Deduplication","publication_year":2018,"publication_date":"2018-07-27","ids":{"openalex":"https://openalex.org/W2810683959","doi":"https://doi.org/10.3390/info9080189","mag":"2810683959"},"language":"en","primary_location":{"id":"doi:10.3390/info9080189","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info9080189","pdf_url":"https://www.mdpi.com/2078-2489/9/8/189/pdf?version=1532669325","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/9/8/189/pdf?version=1532669325","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067367312","display_name":"Jose N. Paredes","orcid":"https://orcid.org/0000-0002-4319-6344"},"institutions":[{"id":"https://openalex.org/I4210125789","display_name":"Centro Cient\u00edfico Tecnol\u00f3gico - Bah\u00eda Blanca","ror":"https://ror.org/03efzvv60","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4210125789","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I56858762","display_name":"Universidad Nacional del Sur","ror":"https://ror.org/028crwz56","country_code":"AR","type":"education","lineage":["https://openalex.org/I56858762"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Jose N. Paredes","raw_affiliation_strings":["Department of Computer Science and Engineering, Universidad Nacional del Sur (UNS), 8000 Bahia Blanca, Argentina","Institute for Computer Science and Engineering (CONICET\u2013UNS), 8000 Bahia Blanca, Argentina"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Universidad Nacional del Sur (UNS), 8000 Bahia Blanca, Argentina","institution_ids":["https://openalex.org/I56858762"]},{"raw_affiliation_string":"Institute for Computer Science and Engineering (CONICET\u2013UNS), 8000 Bahia Blanca, Argentina","institution_ids":["https://openalex.org/I4210125789"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079109547","display_name":"Gerardo I. Simari","orcid":"https://orcid.org/0000-0003-3185-4992"},"institutions":[{"id":"https://openalex.org/I4210125789","display_name":"Centro Cient\u00edfico Tecnol\u00f3gico - Bah\u00eda Blanca","ror":"https://ror.org/03efzvv60","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4210125789","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]},{"id":"https://openalex.org/I56858762","display_name":"Universidad Nacional del Sur","ror":"https://ror.org/028crwz56","country_code":"AR","type":"education","lineage":["https://openalex.org/I56858762"]}],"countries":["AR","US"],"is_corresponding":true,"raw_author_name":"Gerardo I. Simari","raw_affiliation_strings":["Department of Computer Science and Engineering, Universidad Nacional del Sur (UNS), 8000 Bahia Blanca, Argentina","Institute for Computer Science and Engineering (CONICET\u2013UNS), 8000 Bahia Blanca, Argentina","School of Computing, Informatics, and Decision Systems Engineering (CIDSE), Arizona State University, Tempe, AZ 85281, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Universidad Nacional del Sur (UNS), 8000 Bahia Blanca, Argentina","institution_ids":["https://openalex.org/I56858762"]},{"raw_affiliation_string":"Institute for Computer Science and Engineering (CONICET\u2013UNS), 8000 Bahia Blanca, Argentina","institution_ids":["https://openalex.org/I4210125789"]},{"raw_affiliation_string":"School of Computing, Informatics, and Decision Systems Engineering (CIDSE), Arizona State University, Tempe, AZ 85281, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087504296","display_name":"Mar\u00eda Vanina Mart\u00ednez","orcid":"https://orcid.org/0000-0003-2819-4735"},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]},{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Maria Vanina Martinez","raw_affiliation_strings":["Department of Computer Science, Universidad de Buenos Aires (UBA), C1428EGA Ciudad Autonoma de Buenos Aires, Argentina","Institute for Computer Science Research (CONICET\u2013UBA), C1428EGA Ciudad Autonoma de Buenos Aires, Argentina"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universidad de Buenos Aires (UBA), C1428EGA Ciudad Autonoma de Buenos Aires, Argentina","institution_ids":["https://openalex.org/I24354313"]},{"raw_affiliation_string":"Institute for Computer Science Research (CONICET\u2013UBA), C1428EGA Ciudad Autonoma de Buenos Aires, Argentina","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I4210144290"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028916487","display_name":"Marcelo Alejandro Falappa","orcid":"https://orcid.org/0000-0002-3863-2893"},"institutions":[{"id":"https://openalex.org/I4210125789","display_name":"Centro Cient\u00edfico Tecnol\u00f3gico - Bah\u00eda Blanca","ror":"https://ror.org/03efzvv60","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4210125789","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I56858762","display_name":"Universidad Nacional del Sur","ror":"https://ror.org/028crwz56","country_code":"AR","type":"education","lineage":["https://openalex.org/I56858762"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Marcelo A. Falappa","raw_affiliation_strings":["Department of Computer Science and Engineering, Universidad Nacional del Sur (UNS), 8000 Bahia Blanca, Argentina","Institute for Computer Science and Engineering (CONICET\u2013UNS), 8000 Bahia Blanca, Argentina"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Universidad Nacional del Sur (UNS), 8000 Bahia Blanca, Argentina","institution_ids":["https://openalex.org/I56858762"]},{"raw_affiliation_string":"Institute for Computer Science and Engineering (CONICET\u2013UNS), 8000 Bahia Blanca, Argentina","institution_ids":["https://openalex.org/I4210125789"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079109547"],"corresponding_institution_ids":["https://openalex.org/I4210125789","https://openalex.org/I55732556","https://openalex.org/I56858762"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.6619,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74110582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"9","issue":"8","first_page":"189","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computer-science","display_name":"Computer science","score":0.8004302382469177},{"id":"https://openalex.org/keywords/hacker","display_name":"Hacker","score":0.7608304619789124},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6683454513549805},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6563963294029236},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6402381658554077},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5743719339370728},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5215975046157837},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.49197790026664734},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4634992778301239},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4242934286594391},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3747156262397766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31037360429763794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004302382469177},{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.7608304619789124},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6683454513549805},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6563963294029236},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6402381658554077},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5743719339370728},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5215975046157837},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.49197790026664734},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4634992778301239},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4242934286594391},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3747156262397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31037360429763794},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/info9080189","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info9080189","pdf_url":"https://www.mdpi.com/2078-2489/9/8/189/pdf?version=1532669325","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:americanae.aecid.es:3928148","is_oa":true,"landing_page_url":"http://hdl.handle.net/11336/89020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400786","display_name":"Americanae (AECID Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"reponame:CONICET Digital (CONICET)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:68a91f75c62d4fb78dc8efaa5ff4c7dd","is_oa":true,"landing_page_url":"https://doaj.org/article/68a91f75c62d4fb78dc8efaa5ff4c7dd","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 9, Iss 8, p 189 (2018)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/9/8/189/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/info9080189","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info9080189","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info9080189","pdf_url":"https://www.mdpi.com/2078-2489/9/8/189/pdf?version=1532669325","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G3533541525","display_name":null,"funder_award_id":"690974","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G4433789615","display_name":null,"funder_award_id":"Marie Sklodowska-Curie grant","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7331901853","display_name":null,"funder_award_id":"EU H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7533379976","display_name":null,"funder_award_id":"690974","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7931865478","display_name":null,"funder_award_id":"4-15-1-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8104872798","display_name":null,"funder_award_id":"PGI 24/ZN34","funder_id":"https://openalex.org/F4320323402","funder_display_name":"Universidad Nacional del Sur"},{"id":"https://openalex.org/G8320706195","display_name":null,"funder_award_id":"N00014-15-1-2742","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320321594","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59"},{"id":"https://openalex.org/F4320323402","display_name":"Universidad Nacional del Sur","ror":"https://ror.org/028crwz56"},{"id":"https://openalex.org/F4320332923","display_name":"U.S. Navy","ror":"https://ror.org/03ar0mv07"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2810683959.pdf","grobid_xml":"https://content.openalex.org/works/W2810683959.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1782779125","https://openalex.org/W1964786778","https://openalex.org/W1971772795","https://openalex.org/W2004661748","https://openalex.org/W2041439319","https://openalex.org/W2057228200","https://openalex.org/W2059009730","https://openalex.org/W2077414053","https://openalex.org/W2092475127","https://openalex.org/W2117974736","https://openalex.org/W2118425947","https://openalex.org/W2119804197","https://openalex.org/W2148019918","https://openalex.org/W2244440518","https://openalex.org/W2295240344","https://openalex.org/W2325921650","https://openalex.org/W2484789065","https://openalex.org/W2508310662","https://openalex.org/W2554218322","https://openalex.org/W2569536984","https://openalex.org/W2604283646","https://openalex.org/W2771482031","https://openalex.org/W2793551582","https://openalex.org/W2807143630","https://openalex.org/W2808174359","https://openalex.org/W2963980822","https://openalex.org/W2964051216","https://openalex.org/W2964226158","https://openalex.org/W3146259567","https://openalex.org/W6605292376"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2921504876","https://openalex.org/W2587188779","https://openalex.org/W4320018150","https://openalex.org/W4239582170","https://openalex.org/W2918664383","https://openalex.org/W106056076","https://openalex.org/W4320855730","https://openalex.org/W2135200719"],"abstract_inverted_index":{"In":[0,64,151],"traditional":[1],"databases,":[2],"the":[3,15,50,72,102,134],"entity":[4],"resolution":[5],"problem":[6,70,143,157],"(which":[7],"is":[8,39,77,191],"also":[9],"known":[10],"as":[11,49,95,148,236],"deduplication)":[12],"refers":[13],"to":[14,24,91,106,112,124,147,202,205,225,248],"task":[16],"of":[17,21,45,52,136,185,212,229],"mapping":[18],"multiple":[19],"manifestations":[20],"virtual":[22,46],"objects":[23,47],"their":[25,114,126,250],"corresponding":[26],"real-world":[27,163],"entities.":[28,231],"When":[29],"addressing":[30],"this":[31,65,69,75,152,156,183,206],"problem,":[32,207],"in":[33,83,85,100,133],"both":[34],"theory":[35],"and":[36,61,98,128,139,169,208],"practice,":[37],"it":[38,120,190],"widely":[40],"assumed":[41],"that":[42,74,144,160,189,221,243],"such":[43,94],"sets":[44],"appear":[48],"result":[51],"clerical":[53],"errors,":[54],"transliterations,":[55],"missing":[56],"or":[57],"updated":[58],"attributes,":[59],"abbreviations,":[60],"so":[62],"forth.":[63],"paper,":[66,153],"we":[67,145,154],"address":[68],"under":[71],"assumption":[73],"situation":[76],"caused":[78],"by":[79],"malicious":[80,166],"actors":[81],"operating":[82],"domains":[84],"which":[86,101,201],"they":[87,110,118],"do":[88],"not":[89,194],"wish":[90,111],"be":[92],"identified,":[93],"hacker":[96,167],"forums":[97,168],"markets":[99,170],"participants":[103],"are":[104,131,234],"motivated":[105],"remain":[107],"semi-anonymous":[108],"(though":[109],"keep":[113],"true":[115],"identities":[116],"secret,":[117],"find":[119,196],"useful":[121],"for":[122],"customers":[123],"identify":[125],"products":[127],"services).":[129],"We":[130,187],"therefore":[132],"presence":[135],"a":[137,175,210,237],"different,":[138],"even":[140],"more":[141],"challenging,":[142],"refer":[146],"adversarial":[149],"deduplication.":[150],"study":[155],"via":[158],"examples":[159],"arise":[161],"from":[162,172],"data":[164,199],"on":[165,181,200,216],"arising":[171],"collaborations":[173],"with":[174],"cyber":[176,254],"threat":[177],"intelligence":[178],"company":[179],"focusing":[180],"understanding":[182],"kind":[184],"behavior.":[186],"argue":[188],"very":[192],"difficult\u2014if":[193],"impossible\u2014to":[195],"ground":[197],"truth":[198],"build":[203],"solutions":[204],"develop":[209],"set":[211],"preliminary":[213],"experiments":[214],"based":[215],"training":[217],"machine":[218],"learning":[219],"classifiers":[220],"leverage":[222],"text":[223],"analysis":[224],"detect":[226],"potential":[227],"cases":[228],"duplicate":[230],"Our":[232],"results":[233],"encouraging":[235],"first":[238],"step":[239],"towards":[240,252],"building":[241],"tools":[242],"human":[244],"analysts":[245],"can":[246],"use":[247],"enhance":[249],"capabilities":[251],"fighting":[253],"threats.":[255]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
