{"id":"https://openalex.org/W4206299091","doi":"https://doi.org/10.1109/ase51524.2021.9678638","title":"Unsupervised Labeling and Extraction of Phrase-based Concepts in Vulnerability Descriptions","display_name":"Unsupervised Labeling and Extraction of Phrase-based Concepts in Vulnerability Descriptions","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4206299091","doi":"https://doi.org/10.1109/ase51524.2021.9678638"},"language":"en","primary_location":{"id":"doi:10.1109/ase51524.2021.9678638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase51524.2021.9678638","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009280810","display_name":"Sofonias Yitagesu","orcid":"https://orcid.org/0000-0002-9247-7521"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sofonias Yitagesu","raw_affiliation_strings":["College of Intelligence and Computing Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028641941","display_name":"Zhenchang Xing","orcid":"https://orcid.org/0000-0001-7663-1421"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhenchang Xing","raw_affiliation_strings":["Research School of Computer Science Australian National University, Data61 CSIRO, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science Australian National University, Data61 CSIRO, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679","https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030524599","display_name":"Xiaowang Zhang","orcid":"https://orcid.org/0000-0002-3931-3886"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowang Zhang","raw_affiliation_strings":["College of Intelligence and Computing Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736532","display_name":"Zhiyong Feng","orcid":"https://orcid.org/0000-0001-8158-7453"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Feng","raw_affiliation_strings":["College of Intelligence and Computing Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451509","display_name":"Xiaohong Li","orcid":"https://orcid.org/0000-0002-0752-6764"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohong Li","raw_affiliation_strings":["College of Intelligence and Computing Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041328957","display_name":"Linyi Han","orcid":"https://orcid.org/0000-0002-9747-4426"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linyi Han","raw_affiliation_strings":["College of Intelligence and Computing Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009280810"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":3.1346,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93136161,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"943","last_page":"954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9969000220298767,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.994700014591217,"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/T10028","display_name":"Topic Modeling","score":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.8296650052070618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6102985739707947},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5642663836479187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5376597046852112},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49342575669288635},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4930209815502167},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.48812755942344666},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4479118585586548},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.43913373351097107},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.41206106543540955},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25110965967178345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8296650052070618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6102985739707947},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5642663836479187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5376597046852112},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49342575669288635},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4930209815502167},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.48812755942344666},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4479118585586548},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.43913373351097107},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.41206106543540955},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25110965967178345},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":1,"locations":[{"id":"doi:10.1109/ase51524.2021.9678638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase51524.2021.9678638","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322701","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W10548402","https://openalex.org/W643044259","https://openalex.org/W1509924131","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1673310716","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W1976339648","https://openalex.org/W1986203139","https://openalex.org/W2008652694","https://openalex.org/W2042251811","https://openalex.org/W2072729271","https://openalex.org/W2097606805","https://openalex.org/W2128180557","https://openalex.org/W2158427745","https://openalex.org/W2187089797","https://openalex.org/W2269892441","https://openalex.org/W2527802371","https://openalex.org/W2538865281","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2741608233","https://openalex.org/W2784152338","https://openalex.org/W2792145631","https://openalex.org/W2810348307","https://openalex.org/W2886325293","https://openalex.org/W2896457183","https://openalex.org/W2911964244","https://openalex.org/W2940125701","https://openalex.org/W2944104031","https://openalex.org/W2944593082","https://openalex.org/W2950821630","https://openalex.org/W2953384591","https://openalex.org/W2958246628","https://openalex.org/W2959224760","https://openalex.org/W2964738734","https://openalex.org/W2965876165","https://openalex.org/W2974159469","https://openalex.org/W3023882301","https://openalex.org/W3093190191","https://openalex.org/W3105146463","https://openalex.org/W3176717822","https://openalex.org/W4239319433","https://openalex.org/W4294170691","https://openalex.org/W4294214797","https://openalex.org/W6621097521","https://openalex.org/W6631190155","https://openalex.org/W6637131181","https://openalex.org/W6637242042","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6682691769","https://openalex.org/W6683083456","https://openalex.org/W6713134421","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6755207826","https://openalex.org/W6762351946","https://openalex.org/W6766458556","https://openalex.org/W6775650844"],"related_works":["https://openalex.org/W2773208253","https://openalex.org/W2039546652","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W65104662","https://openalex.org/W1871748041","https://openalex.org/W2362286668","https://openalex.org/W2133382151","https://openalex.org/W2153339597","https://openalex.org/W1528412344"],"abstract_inverted_index":{"People":[0],"usually":[1,130],"describe":[2],"the":[3,26,115,136,162,189,208,215,225,231,245],"key":[4,34,112],"characteristics":[5],"of":[6,29,33,76,117,165,192,207,210,217,227],"software":[7],"vulnerabilities":[8],"in":[9,66,124,135,230],"natural":[10],"language":[11],"mixed":[12],"with":[13,174],"domain-specific":[14],"names":[15],"and":[16,61,84,94,104,127,148,151,181,194,201,224],"concepts.":[17,211],"This":[18],"textual":[19],"nature":[20,164],"poses":[21],"a":[22,111,184,235],"significant":[23,42],"challenge":[24],"for":[25,48,177,220],"automatic":[27],"analysis":[28],"vulnerabilities.":[30],"Automatic":[31],"extraction":[32],"vulnerability":[35,64,68,78,228,242],"aspects":[36],"is":[37,108],"highly":[38],"desirable":[39],"but":[40],"demands":[41],"effort":[43],"to":[44,59,92,155,204],"manually":[45,247],"label":[46,60,93],"data":[47,179],"model":[49],"training.":[50],"In":[51,188,234],"this":[52],"paper,":[53],"we":[54,141,168,197],"propose":[55,142],"an":[56,153],"unsupervised":[57],"approach":[58,107],"extract":[62,95],"important":[63],"concepts":[65,79,229,243],"textural":[67],"descriptions":[69],"(TVDs).":[70],"We":[71],"focus":[72],"on":[73,110],"three":[74],"types":[75],"phrase-based":[77],"(root":[80],"cause,":[81],"attack":[82],"vector,":[83],"impact)":[85],"as":[86],"they":[87,122],"are":[88],"much":[89],"more":[90],"difficult":[91],"than":[96],"name-":[97],"or":[98],"number-based":[99],"entities":[100],"(i.e.,":[101],"vendor,":[102],"product,":[103],"version).":[105],"Our":[106,212],"based":[109],"observation":[113],"that":[114],"same-type":[116,209],"phrases,":[118],"no":[119],"matter":[120],"how":[121],"differ":[123],"sentence":[125,137],"structures":[126],"phrase":[128],"expressions,":[129],"share":[131],"syntactically":[132],"similar":[133],"paths":[134,147],"parsing":[138],"trees.":[139],"Therefore,":[140],"two":[143,246],"path":[144,222],"representations":[145,223],"(absolute":[146],"relative":[149,195],"paths)":[150],"use":[152,199],"auto-encoder":[154],"encode":[156],"such":[157],"syntactic":[158],"similarities.":[159],"To":[160],"address":[161],"discrete":[163],"our":[166,218,239],"paths,":[167,196],"enhance":[169],"traditional":[170],"Variational":[171],"Auto-encoder":[172],"(VAE)":[173],"Gumble-Max":[175],"trick":[176],"categorical":[178],"distribution,":[180],"thus":[182],"creates":[183],"Categorical":[185],"VAE":[186],"(CaVAE).":[187],"latent":[190],"space":[191],"absolute":[193],"further":[198],"FIt-TSNE":[200],"clustering":[202],"techniques":[203],"generate":[205],"clusters":[206],"evaluation":[213],"confirms":[214],"effectiveness":[216],"CaVAE":[219],"encoding":[221],"accuracy":[226],"resulting":[232],"clusters.":[233],"concept":[236],"classification":[237],"task,":[238],"unsupervisedly":[240],"labeled":[241,248],"outperform":[244],"datasets":[249],"from":[250],"previous":[251],"work.":[252]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}