{"id":"https://openalex.org/W4412605393","doi":"https://doi.org/10.1109/access.2025.3591843","title":"Enhancing Generalization in Phishing URL Detection via a Fine-Tuned BERT-Based Multimodal Approach","display_name":"Enhancing Generalization in Phishing URL Detection via a Fine-Tuned BERT-Based Multimodal Approach","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412605393","doi":"https://doi.org/10.1109/access.2025.3591843"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3591843","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591843","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3591843","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026288065","display_name":"Yi Wei","orcid":"https://orcid.org/0000-0002-3016-6816"},"institutions":[{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Wei","raw_affiliation_strings":["Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3016-6816","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103816766","display_name":"Masaya Nakayama","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaya Nakayama","raw_affiliation_strings":["Information Technology Center, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011635598","display_name":"Yuji Sekiya","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuji Sekiya","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":7.9717,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97172401,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"131197","last_page":"131216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9830999970436096,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9775999784469604,"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/phishing","display_name":"Phishing","score":0.8482328653335571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8262662291526794},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6631371974945068},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.4228464961051941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3610624074935913},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32781749963760376},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3212634325027466},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.30831652879714966},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2626868784427643},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.20151659846305847},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06547397375106812}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.8482328653335571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8262662291526794},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6631371974945068},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.4228464961051941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3610624074935913},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32781749963760376},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3212634325027466},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.30831652879714966},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2626868784427643},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.20151659846305847},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06547397375106812},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3591843","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591843","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:371c11d948674a67a2ec22b38bc14772","is_oa":true,"landing_page_url":"https://doaj.org/article/371c11d948674a67a2ec22b38bc14772","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 131197-131216 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3591843","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591843","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2801182074","https://openalex.org/W2806379428","https://openalex.org/W2884001105","https://openalex.org/W2963026768","https://openalex.org/W2971561269","https://openalex.org/W3014091144","https://openalex.org/W3022651159","https://openalex.org/W3041247367","https://openalex.org/W3093641884","https://openalex.org/W3094291258","https://openalex.org/W3138009395","https://openalex.org/W3158143049","https://openalex.org/W3179968378","https://openalex.org/W3189081616","https://openalex.org/W4206660322","https://openalex.org/W4210417849","https://openalex.org/W4213081600","https://openalex.org/W4213287278","https://openalex.org/W4280614404","https://openalex.org/W4285247275","https://openalex.org/W4294486857","https://openalex.org/W4296617364","https://openalex.org/W4306953359","https://openalex.org/W4308531811","https://openalex.org/W4312887856","https://openalex.org/W4313588323","https://openalex.org/W4322706916","https://openalex.org/W4322736749","https://openalex.org/W4385245566","https://openalex.org/W4387826905","https://openalex.org/W4388864562","https://openalex.org/W4391113002","https://openalex.org/W4391925589","https://openalex.org/W4392515583","https://openalex.org/W4396216346","https://openalex.org/W4399730868","https://openalex.org/W4402639496","https://openalex.org/W4406461453","https://openalex.org/W4407785486","https://openalex.org/W4411337475","https://openalex.org/W6640284647","https://openalex.org/W6748384357","https://openalex.org/W6798553033","https://openalex.org/W7048367968"],"related_works":["https://openalex.org/W2149202530","https://openalex.org/W2807822918","https://openalex.org/W2921723332","https://openalex.org/W4391093354","https://openalex.org/W2482950156","https://openalex.org/W4396966040","https://openalex.org/W2305322260","https://openalex.org/W3139248031","https://openalex.org/W3042334625","https://openalex.org/W4200017362"],"abstract_inverted_index":{"Phishing":[0],"has":[1],"emerged":[2],"as":[3,18,150],"a":[4,91,106,126,151,166],"prevalent":[5],"cyber":[6],"threat":[7],"aimed":[8],"at":[9],"stealing":[10],"confidential":[11],"information":[12],"through":[13,165],"diverse":[14,78],"delivery":[15],"media":[16,24],"such":[17],"emails,":[19],"instant":[20],"messages,":[21],"and":[22,32,73,171,187],"social":[23],"posts,":[25],"often":[26],"resulting":[27],"in":[28,62,184],"severe":[29],"identity":[30],"theft":[31],"financial":[33],"loss.":[34],"Traditional":[35],"approaches":[36],"typically":[37],"rely":[38],"on":[39],"machine":[40],"learning":[41,61],"models":[42],"combined":[43],"with":[44,113,175],"handcrafted,":[45],"specialized":[46],"feature":[47],"engineering.":[48],"More":[49],"recent":[50],"efforts":[51],"have":[52],"shifted":[53],"toward":[54],"fully":[55],"automated,":[56],"featureless":[57],"strategies":[58],"using":[59],"deep":[60],"an":[63,139],"end-to-end":[64],"manner.":[65],"However,":[66],"many":[67],"existing":[68],"studies":[69],"are":[70],"highly":[71],"data-dependent":[72],"lack":[74],"practical":[75],"validation":[76],"across":[77,177],"scenarios,":[79],"thus":[80],"leaving":[81],"their":[82],"real-world":[83],"applicability":[84],"uncertain.":[85],"In":[86,122],"this":[87],"study,":[88],"we":[89,124],"propose":[90],"multimodal":[92],"approach":[93],"that":[94],"enhances":[95],"the":[96],"generalization":[97,188],"capability":[98],"of":[99,168],"phishing":[100,135],"URL":[101,111],"detection":[102,158,185],"systems":[103],"by":[104],"combining":[105],"fine-tuned":[107],"BERT":[108],"model":[109],"for":[110,155],"processing":[112],"auxiliary":[114],"external":[115],"features":[116],"derived":[117],"from":[118,142],"public":[119],"Internet":[120],"resources.":[121],"addition,":[123],"share":[125],"publicly":[127],"available":[128],"dataset":[129,148],"named":[130],"PhishMail,":[131],"which":[132],"contains":[133],"8,937":[134],"samples":[136],"collected":[137],"over":[138],"extended":[140],"period":[141],"daily":[143],"incoming":[144],"malicious":[145],"emails.":[146],"This":[147],"serves":[149],"valuable":[152],"testing":[153],"resource":[154],"simulating":[156],"zero-day":[157],"scenarios.":[159],"The":[160],"proposed":[161],"framework":[162],"is":[163,172],"evaluated":[164],"series":[167],"extensive":[169],"experiments":[170],"thoroughly":[173],"validated,":[174],"results":[176],"multiple":[178],"cross-dataset":[179],"evaluations":[180],"demonstrating":[181],"significant":[182],"improvements":[183],"effectiveness":[186],"capability.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}