{"id":"https://openalex.org/W3167402552","doi":"https://doi.org/10.1109/milcom52596.2021.9653028","title":"URLTran: Improving Phishing URL Detection Using Transformers","display_name":"URLTran: Improving Phishing URL Detection Using Transformers","publication_year":2021,"publication_date":"2021-11-29","ids":{"openalex":"https://openalex.org/W3167402552","doi":"https://doi.org/10.1109/milcom52596.2021.9653028","mag":"3167402552"},"language":"en","primary_location":{"id":"doi:10.1109/milcom52596.2021.9653028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom52596.2021.9653028","pdf_url":null,"source":{"id":"https://openalex.org/S4363608138","display_name":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","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":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.05256","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005531495","display_name":"Pranav Maneriker","orcid":"https://orcid.org/0000-0003-1333-4424"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranav Maneriker","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859993","display_name":"Jack W. Stokes","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack W. Stokes","raw_affiliation_strings":["Microsoft, Redmond, WA, USA","(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007099906","display_name":"Edir Garcia Lazo","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Edir Garcia Lazo","raw_affiliation_strings":["Microsoft, Redmond, WA, USA","(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083935555","display_name":"Diana Carutasu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Diana Carutasu","raw_affiliation_strings":["Microsoft, Redmond, WA, USA","(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061108898","display_name":"Farid Tajaddodianfar","orcid":"https://orcid.org/0000-0002-6135-1993"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farid Tajaddodianfar","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088331085","display_name":"Arun Gururajan","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Arun Gururajan","raw_affiliation_strings":["Amazon, Seattle, WA, USA","(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.534,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83322044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9997000098228455,"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":0.9997000098228455,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9869999885559082,"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":0.9178156852722168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7502701282501221},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5815407633781433},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5405517816543579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5377166271209717},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4599986970424652},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3078213334083557},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.209648996591568},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10292074084281921}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.9178156852722168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7502701282501221},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5815407633781433},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5405517816543579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5377166271209717},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4599986970424652},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3078213334083557},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.209648996591568},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10292074084281921},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/milcom52596.2021.9653028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom52596.2021.9653028","pdf_url":null,"source":{"id":"https://openalex.org/S4363608138","display_name":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","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":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.05256","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.05256","pdf_url":"https://arxiv.org/pdf/2106.05256","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},{"id":"mag:3167402552","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2106.05256","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.05256","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.05256","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.05256","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.05256","pdf_url":"https://arxiv.org/pdf/2106.05256","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3167402552.pdf","grobid_xml":"https://content.openalex.org/works/W3167402552.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1945616565","https://openalex.org/W2012481173","https://openalex.org/W2046166587","https://openalex.org/W2121879602","https://openalex.org/W2270070752","https://openalex.org/W2493916176","https://openalex.org/W2525778437","https://openalex.org/W2580641941","https://openalex.org/W2787538540","https://openalex.org/W2799194071","https://openalex.org/W2803751389","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2957266847","https://openalex.org/W2962784628","https://openalex.org/W2962818281","https://openalex.org/W2963403868","https://openalex.org/W2963545917","https://openalex.org/W2963635116","https://openalex.org/W2964046515","https://openalex.org/W2964047576","https://openalex.org/W2964054038","https://openalex.org/W2964121744","https://openalex.org/W2965373594","https://openalex.org/W2971252690","https://openalex.org/W2996599509","https://openalex.org/W3005725208","https://openalex.org/W3015534721","https://openalex.org/W3027172182","https://openalex.org/W3030163527","https://openalex.org/W3034549508","https://openalex.org/W3034835156","https://openalex.org/W3035231859","https://openalex.org/W3105604018","https://openalex.org/W3118485687","https://openalex.org/W6631190155","https://openalex.org/W6640425456","https://openalex.org/W6685053522","https://openalex.org/W6727690538","https://openalex.org/W6732691979","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6778883912","https://openalex.org/W6779580516"],"related_works":["https://openalex.org/W3085804088","https://openalex.org/W3197388494","https://openalex.org/W3173117104","https://openalex.org/W3031672437","https://openalex.org/W3081881044","https://openalex.org/W2806379428","https://openalex.org/W3201593480","https://openalex.org/W2909737018","https://openalex.org/W184264206","https://openalex.org/W3212616499","https://openalex.org/W2779627157","https://openalex.org/W2046603953","https://openalex.org/W3097602862","https://openalex.org/W3130735219","https://openalex.org/W3158143049","https://openalex.org/W3173978539","https://openalex.org/W3022651159","https://openalex.org/W2771035496","https://openalex.org/W3130013025","https://openalex.org/W2801552647"],"abstract_inverted_index":{"Browsers":[0],"often":[1],"include":[2,48],"security":[3,59],"features":[4],"to":[5,39,47,63,87,127,168,186,207,224,263],"detect":[6,89],"phishing":[7,26,36,91,94,115,149,192,251],"web":[8],"pages.":[9,27,92],"In":[10,136],"the":[11,30,107,114,148,175,189,227,265],"past,":[12],"some":[13,83,247],"browsers":[14,45,76],"evaluated":[15],"an":[16,232],"unknown":[17,80],"URL":[18,81,116,150,193],"for":[19,113,226],"inclusion":[20],"in":[21,85,130,237],"a":[22,42,141,196,216,238],"list":[23],"of":[24,32,57,109,144,191,199,221,234,241,267],"known":[25,35],"However,":[28],"as":[29,55,254],"number":[31],"URLs":[33],"and":[34,159,164,171,259,277],"pages":[37],"continued":[38],"increase":[40],"at":[41,231],"rapid":[43],"pace,":[44],"started":[46],"one":[49],"or":[50],"more":[51],"machine":[52,98],"learning":[53,99,111],"classifiers":[54],"part":[56],"their":[58],"services":[60],"that":[61,279],"aim":[62],"better":[64],"protect":[65],"end":[66],"users":[67],"from":[68,177],"harm.":[69],"While":[70],"additional":[71,160,271],"information":[72],"could":[73],"be":[74],"used,":[75],"typically":[77],"evaluate":[78],"every":[79],"using":[82,123],"classifier":[84],"order":[86],"quickly":[88],"these":[90,166,178,274,286],"Early":[93],"detection":[95,117,151,194],"used":[96],"standard":[97,155],"classifiers,":[100],"but":[101],"recent":[102],"research":[103,122],"has":[104,125],"instead":[105],"proposed":[106],"use":[108],"deep":[110,209],"models":[112,146,167],"task.":[118,152],"Concurrently,":[119],"text":[120],"embedding":[121],"transformers":[124,185],"led":[126],"state-of-the-art":[128],"results":[129],"many":[131],"natural":[132],"language":[133,157],"processing":[134],"tasks.":[135],"this":[137],"work,":[138],"we":[139,180,245],"perform":[140],"comprehensive":[142],"analysis":[143],"transformer":[145],"on":[147,257],"We":[153,269],"consider":[154,246,270],"masked":[156],"modeling":[158],"domain-specific":[161],"pre-training":[162],"tasks,":[163],"compare":[165],"fine-tuned":[169],"BERT":[170],"RoBERTa":[172],"models.":[173],"Combining":[174],"insights":[176],"experiments,":[179],"propose":[181],"URLTran":[182,214,280],"which":[183],"uses":[184],"significantly":[187],"improve":[188,264],"performance":[190],"over":[195,242],"wide":[197],"range":[198],"very":[200],"low":[201,283],"false":[202],"positive":[203,218],"rates":[204],"(FPRs)":[205],"compared":[206,223],"other":[208],"learning-based":[210],"methods.":[211],"For":[212],"example,":[213],"yields":[215],"true":[217],"rate":[219],"(TPR)":[220],"86.80%":[222],"71.20%":[225],"next":[228],"best":[229],"baseline":[230],"FPR":[233],"0.01%,":[235],"resulting":[236],"relative":[239],"improvement":[240],"21.9%.":[243],"Further,":[244],"classical":[248],"adversarial":[249,275],"black-box":[250],"attacks":[252],"such":[253],"those":[255],"based":[256],"homoglyphs":[258],"compound":[260],"word":[261],"splits":[262],"robustness":[266],"URLTran.":[268],"fine-tuning":[272],"with":[273],"samples":[276],"demonstrate":[278],"can":[281],"maintain":[282],"FPRs":[284],"under":[285],"scenarios.":[287]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}