{"id":"https://openalex.org/W4224086099","doi":"https://doi.org/10.1145/3508398.3511524","title":"Leveraging Synthetic Data and PU Learning For Phishing Email Detection","display_name":"Leveraging Synthetic Data and PU Learning For Phishing Email Detection","publication_year":2022,"publication_date":"2022-04-14","ids":{"openalex":"https://openalex.org/W4224086099","doi":"https://doi.org/10.1145/3508398.3511524"},"language":"en","primary_location":{"id":"doi:10.1145/3508398.3511524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508398.3511524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth ACM Conference on Data and Application Security and Privacy","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/A5073964491","display_name":"Fatima Zahra Qachfar","orcid":"https://orcid.org/0000-0002-6254-3364"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fatima Zahra Qachfar","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050592031","display_name":"Rakesh Verma","orcid":"https://orcid.org/0000-0002-7466-7823"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakesh M. Verma","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078060919","display_name":"Arjun Mukherjee","orcid":"https://orcid.org/0000-0002-8896-604X"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arjun Mukherjee","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073964491"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":3.6361,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93685972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991000294685364,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9988999962806702,"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/phishing","display_name":"Phishing","score":0.8560845851898193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7527920007705688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6106271743774414},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5904651284217834},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47821590304374695},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4691426157951355},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.45690077543258667},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.451806902885437},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32269710302352905},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11511784791946411},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.09247192740440369}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.8560845851898193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527920007705688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6106271743774414},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5904651284217834},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47821590304374695},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4691426157951355},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.45690077543258667},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.451806902885437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32269710302352905},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11511784791946411},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.09247192740440369},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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":1,"locations":[{"id":"doi:10.1145/3508398.3511524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508398.3511524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth ACM Conference on Data and Application Security and Privacy","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2057110230","display_name":null,"funder_award_id":"N00014-19-S-F009","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2334921733","display_name":null,"funder_award_id":"1433817,1838147","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6523399184","display_name":null,"funder_award_id":"W911NF-20-1-0254","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1991181258","https://openalex.org/W1992914835","https://openalex.org/W2016692778","https://openalex.org/W2050871273","https://openalex.org/W2107138773","https://openalex.org/W2121879602","https://openalex.org/W2123958887","https://openalex.org/W2148143831","https://openalex.org/W2187089797","https://openalex.org/W2330681997","https://openalex.org/W2794598542","https://openalex.org/W2914620184","https://openalex.org/W2962784628","https://openalex.org/W2963940534","https://openalex.org/W2979826702","https://openalex.org/W2994155906","https://openalex.org/W2998993395","https://openalex.org/W3003583062","https://openalex.org/W3006834142","https://openalex.org/W3090717071","https://openalex.org/W3094502939","https://openalex.org/W3134075462","https://openalex.org/W3170052928","https://openalex.org/W3193944778","https://openalex.org/W3204305681","https://openalex.org/W4240367438","https://openalex.org/W4381304672","https://openalex.org/W6635474240"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W4285706568"],"abstract_inverted_index":{"Imbalanced":[0],"data":[1,13],"classification":[2],"has":[3],"always":[4],"been":[5],"one":[6],"of":[7,45,51,154,165],"the":[8,17,48,60,88,108,119,136,148,157],"most":[9,44,158],"challenging":[10],"problems":[11],"in":[12,16,31,42],"science":[14],"especially":[15],"cybersecurity":[18],"field,":[19],"where":[20],"we":[21,58],"observe":[22],"an":[23,152,163],"out-of-balance":[24],"proportion":[25],"between":[26],"benign":[27],"and":[28,91,105,162],"phishing":[29,39,52,67],"examples":[30],"security":[32],"datasets.":[33,54],"Even":[34],"though":[35],"there":[36],"are":[37,100],"many":[38],"detection":[40],"methods":[41,134],"literature,":[43],"them":[46],"neglect":[47],"imbalanced":[49,61,110,149,160],"nature":[50],"email":[53],"In":[55],"this":[56],"paper,":[57],"examine":[59],"property":[62],"by":[63,102],"varying":[64],"legitimate":[65],"to":[66,85,107,118],"class":[68],"ratios.":[69],"We":[70,130],"generate":[71],"new":[72],"synthetic":[73,98],"instances":[74,99],"using":[75],"a":[76,143],"generative":[77],"adversarial":[78],"network":[79],"model":[80,126],"for":[81,127,156,167],"long":[82],"sentences":[83],"(LeakGAN)":[84],"balance":[86],"out":[87],"training":[89,111],"process":[90],"ameliorate":[92],"its":[93],"impact":[94],"on":[95],"classification.":[96,129],"These":[97],"labeled":[101],"positive-unlabeled":[103],"learning":[104],"added":[106],"initial":[109],"set.":[112],"The":[113],"resulting":[114],"dataset":[115],"is":[116],"given":[117],"Bidirectional":[120],"Encoder":[121],"Representations":[122],"from":[123,135],"Transformers":[124],"(BERT)":[125],"sequence":[128],"compare":[131],"several":[132],"state-of-the-art":[133],"literature":[137],"against":[138],"our":[139],"approach,":[140],"which":[141],"achieves":[142],"high":[144],"performance":[145],"throughout":[146],"all":[147],"ratios":[150],"reaching":[151],"F1-score":[153,164],"99.6%":[155],"extreme":[159],"ratio":[161],"99.8%":[166],"balanced":[168],"cases.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}