{"id":"https://openalex.org/W3200455702","doi":"https://doi.org/10.1145/3474369.3486867","title":"A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labels","display_name":"A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labels","publication_year":2021,"publication_date":"2021-10-28","ids":{"openalex":"https://openalex.org/W3200455702","doi":"https://doi.org/10.1145/3474369.3486867","mag":"3200455702"},"language":"en","primary_location":{"id":"doi:10.1145/3474369.3486867","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474369.3486867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.11126","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008388322","display_name":"Robert J. Joyce","orcid":"https://orcid.org/0009-0003-7168-1237"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]},{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert J. Joyce","raw_affiliation_strings":["Booz Allen Hamilton & University of Maryland, Baltimore County, McLean, VA, USA"],"affiliations":[{"raw_affiliation_string":"Booz Allen Hamilton & University of Maryland, Baltimore County, McLean, VA, USA","institution_ids":["https://openalex.org/I1322124587","https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068036546","display_name":"Edward Raff","orcid":"https://orcid.org/0000-0002-9900-1972"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]},{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Raff","raw_affiliation_strings":["Booz Allen Hamilton & University of Maryland, Baltimore County, McLean, VA, USA"],"affiliations":[{"raw_affiliation_string":"Booz Allen Hamilton & University of Maryland, Baltimore County, McLean, VA, USA","institution_ids":["https://openalex.org/I1322124587","https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025012064","display_name":"Charles Nicholas","orcid":"https://orcid.org/0000-0001-9494-7139"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Nicholas","raw_affiliation_strings":["University of Maryland, Baltimore County, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008388322"],"corresponding_institution_ids":["https://openalex.org/I1322124587","https://openalex.org/I79272384"],"apc_list":null,"apc_paid":null,"fwci":1.539,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.83497752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8319715261459351},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6949888467788696},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6464115977287292},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6450419425964355},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5999425649642944},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.5773331522941589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5590274333953857},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5571931600570679},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5150713324546814},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46164435148239136},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4303407073020935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08515390753746033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319715261459351},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6949888467788696},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6464115977287292},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6450419425964355},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5999425649642944},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.5773331522941589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5590274333953857},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5571931600570679},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5150713324546814},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46164435148239136},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4303407073020935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08515390753746033},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474369.3486867","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474369.3486867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.11126","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.11126","pdf_url":"https://arxiv.org/pdf/2109.11126","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:2109.11126","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.11126","pdf_url":"https://arxiv.org/pdf/2109.11126","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":[{"id":"https://metadata.un.org/sdg/16","score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W152854583","https://openalex.org/W1237542396","https://openalex.org/W1587106557","https://openalex.org/W1591082683","https://openalex.org/W1851403712","https://openalex.org/W1910686388","https://openalex.org/W1969414390","https://openalex.org/W1981221397","https://openalex.org/W2000159976","https://openalex.org/W2037109870","https://openalex.org/W2057079516","https://openalex.org/W2068361557","https://openalex.org/W2122672392","https://openalex.org/W2125011234","https://openalex.org/W2169203263","https://openalex.org/W2170707709","https://openalex.org/W2476429474","https://openalex.org/W2514847810","https://openalex.org/W2586493909","https://openalex.org/W2620844046","https://openalex.org/W2749928722","https://openalex.org/W2788864200","https://openalex.org/W2789983203","https://openalex.org/W2794523151","https://openalex.org/W2798159728","https://openalex.org/W2912218663","https://openalex.org/W2942735926","https://openalex.org/W2946506331","https://openalex.org/W2963956526","https://openalex.org/W2970043916","https://openalex.org/W2970382805","https://openalex.org/W3023980642","https://openalex.org/W3026767020","https://openalex.org/W3029868457","https://openalex.org/W3035578002","https://openalex.org/W3088444111","https://openalex.org/W3100191342","https://openalex.org/W3109684201","https://openalex.org/W3115698556","https://openalex.org/W3135261467","https://openalex.org/W3136455557","https://openalex.org/W3174292387","https://openalex.org/W3175955584","https://openalex.org/W3176783553","https://openalex.org/W3180332766","https://openalex.org/W3191250776","https://openalex.org/W4287727290","https://openalex.org/W4300687693","https://openalex.org/W6635503409","https://openalex.org/W6639864006","https://openalex.org/W6738945431","https://openalex.org/W6748641434","https://openalex.org/W6763420789","https://openalex.org/W6797881406"],"related_works":["https://openalex.org/W2097492617","https://openalex.org/W2753240997","https://openalex.org/W2378211422","https://openalex.org/W1764168690","https://openalex.org/W2537959205","https://openalex.org/W2740895074","https://openalex.org/W2772446090","https://openalex.org/W4284893819","https://openalex.org/W4323323165","https://openalex.org/W2745033168"],"abstract_inverted_index":{"In":[0],"some":[1],"problem":[2],"spaces,":[3],"the":[4,116],"high":[5],"cost":[6],"of":[7,14,93,118],"obtaining":[8],"ground":[9,48],"truth":[10,49],"labels":[11],"necessitates":[12],"use":[13],"lower":[15],"quality":[16],"reference":[17,41,74],"datasets.":[18],"It":[19],"is":[20,106],"difficult":[21],"to":[22,39,63,85,130,136],"benchmark":[23],"model":[24],"performance":[25],"using":[26,40],"these":[27],"datasets,":[28],"as":[29],"evaluation":[30,88,125],"results":[31,89],"may":[32],"be":[33,71,149],"biased.":[34],"We":[35,76,121],"propose":[36],"a":[37,79,107,131],"supplement":[38],"labels,":[42],"which":[43],"we":[44,55],"call":[45],"an":[46,53,83,97,119],"approximate":[47],"refinement":[50],"(AGTR).":[51],"Using":[52],"AGTR,":[54],"prove":[56],"that":[57,81,114],"bounds":[58],"on":[59],"specific":[60],"metrics":[61],"used":[62],"evaluate":[64,143],"clustering":[65],"algorithms":[66],"and":[67,102,142],"multi-class":[68],"classifiers":[69],"can":[70],"computed":[72],"without":[73],"labels.":[75],"also":[77],"introduce":[78],"procedure":[80],"uses":[82],"AGTR":[84,98,124],"identify":[86],"inaccurate":[87],"produced":[90],"from":[91],"datasets":[92],"dubious":[94],"quality.":[95],"Creating":[96],"requires":[99],"domain":[100,111],"knowledge,":[101],"malware":[103,133],"family":[104],"classification":[105],"task":[108],"with":[109],"robust":[110],"knowledge":[112],"approaches":[113],"support":[115],"construction":[117],"AGTR.":[120],"demonstrate":[122],"our":[123],"framework":[126],"by":[127],"applying":[128],"it":[129],"popular":[132],"labeling":[134],"tool":[135],"diagnose":[137],"over-fitting":[138],"in":[139],"prior":[140],"testing":[141],"changes":[144],"whose":[145],"impact":[146],"could":[147],"not":[148],"meaningfully":[150],"quantified":[151],"under":[152],"previous":[153],"data.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}