{"id":"https://openalex.org/W4391094165","doi":"https://doi.org/10.1109/bigdata59044.2023.10386782","title":"Detecting Phishing URLs using the BERT Transformer Model","display_name":"Detecting Phishing URLs using the BERT Transformer Model","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391094165","doi":"https://doi.org/10.1109/bigdata59044.2023.10386782"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","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/A5081577106","display_name":"Denish Omondi Otieno","orcid":null},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Denish Omondi Otieno","raw_affiliation_strings":["Texas Tech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Tech University","institution_ids":["https://openalex.org/I12315562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083906665","display_name":"Faranak Abri","orcid":"https://orcid.org/0000-0003-3028-094X"},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Faranak Abri","raw_affiliation_strings":["San Jose State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"San Jose State University","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026464816","display_name":"Akbar Siami Namin","orcid":"https://orcid.org/0000-0002-1646-7495"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akbar Siami Namin","raw_affiliation_strings":["Texas Tech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Tech University","institution_ids":["https://openalex.org/I12315562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102751548","display_name":"Keith S. Jones","orcid":"https://orcid.org/0000-0002-3463-0401"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keith S. Jones","raw_affiliation_strings":["Texas Tech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Tech University","institution_ids":["https://openalex.org/I12315562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.333,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.97216683,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2483","last_page":"2492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9957000017166138,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9926000237464905,"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":0.9593634605407715},{"id":"https://openalex.org/keywords/blacklisting","display_name":"Blacklisting","score":0.7506920099258423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7094171643257141},{"id":"https://openalex.org/keywords/blacklist","display_name":"Blacklist","score":0.6354146599769592},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6180514693260193},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4570900797843933},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.43368563055992126},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.41656994819641113},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2710440158843994}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.9593634605407715},{"id":"https://openalex.org/C2779797433","wikidata":"https://www.wikidata.org/wiki/Q632959","display_name":"Blacklisting","level":2,"score":0.7506920099258423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7094171643257141},{"id":"https://openalex.org/C2781345505","wikidata":"https://www.wikidata.org/wiki/Q2535979","display_name":"Blacklist","level":2,"score":0.6354146599769592},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6180514693260193},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4570900797843933},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.43368563055992126},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.41656994819641113},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2710440158843994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1498672433","https://openalex.org/W1582830784","https://openalex.org/W1985920648","https://openalex.org/W2136136174","https://openalex.org/W2146729596","https://openalex.org/W2163803148","https://openalex.org/W2347140731","https://openalex.org/W2521519773","https://openalex.org/W2588813228","https://openalex.org/W2791923027","https://openalex.org/W2958447199","https://openalex.org/W2960612889","https://openalex.org/W3146533344","https://openalex.org/W4225454120","https://openalex.org/W4385245566","https://openalex.org/W4385485171","https://openalex.org/W6739901393","https://openalex.org/W6842152837"],"related_works":["https://openalex.org/W2933056782","https://openalex.org/W4281884841","https://openalex.org/W1593211785","https://openalex.org/W3207470445","https://openalex.org/W2183312460","https://openalex.org/W4313492216","https://openalex.org/W3215769141","https://openalex.org/W2794575345","https://openalex.org/W4375830807","https://openalex.org/W2730643147"],"abstract_inverted_index":{"Phishing":[0],"websites":[1,8,48,130,158],"many":[2],"a":[3,71,88,126,176,207],"times":[4,23],"look-alike":[5],"to":[6,13,17,64,151],"benign":[7],"with":[9],"the":[10,43,51,56,82,163,166,188,204],"objective":[11],"being":[12],"lure":[14],"unsuspecting":[15,59],"users":[16,60],"visit":[18],"them.":[19],"The":[20,103,183],"visits":[21],"at":[22],"may":[24,49],"be":[25],"driven":[26],"through":[27],"links":[28,32],"in":[29,55],"phishing":[30,47,80,129,157,181],"emails,":[31],"from":[33,170],"web":[34,39],"pages":[35],"as":[36,38,96,98,175],"well":[37,97],"search":[40],"results.":[41],"Although":[42],"precise":[44],"motivations":[45],"behind":[46],"differ":[50],"common":[52],"denominator":[53],"lies":[54],"fact":[57],"that":[58,154,187],"are":[61,106,137,140],"mostly":[62],"required":[63],"take":[65],"some":[66],"action":[67],"e.g.,":[68],"clicking":[69],"on":[70,87],"desired":[72],"Uniform":[73],"Resource":[74],"Locator":[75],"(URL).":[76],"To":[77],"accurately":[78],"identify":[79],"websites,":[81],"cybersecurity":[83],"community":[84],"has":[85],"relied":[86],"variety":[89],"of":[90,114,128,165,206],"approaches":[91,100],"including":[92],"blacklisting,":[93],"heuristic":[94],"techniques":[95,105,202],"content-based":[99],"among":[101,123],"others.":[102,124],"identification":[104],"every":[107],"so":[108],"often":[109],"enhanced":[110],"using":[111],"an":[112],"array":[113],"methods":[115],"i.e.,":[116],"honeypots,":[117],"features":[118],"recognitions,":[119],"manual":[120],"reporting,":[121],"web-crawlers":[122],"Nevertheless,":[125],"number":[127],"still":[131],"escape":[132],"detection":[133],"either":[134],"because":[135],"they":[136],"not":[138],"blacklisted,":[139],"too":[141],"recent":[142],"or":[143,203],"were":[144],"incorrectly":[145],"evaluated.":[146],"It":[147],"is":[148,173],"therefore":[149],"imperative":[150],"enhance":[152],"solutions":[153],"could":[155],"mitigate":[156],"threats.":[159],"In":[160],"this":[161],"study,":[162],"effectiveness":[164],"Bidirectional":[167],"Encoder":[168],"Representations":[169],"Transformers":[171],"(BERT)":[172],"investigated":[174],"possible":[177],"tool":[178],"for":[179],"detecting":[180],"URLs.":[182],"experimental":[184],"results":[185,195],"detail":[186],"BERT":[189],"transformer":[190],"model":[191],"achieves":[192],"acceptable":[193],"prediction":[194],"without":[196],"requiring":[197],"advanced":[198],"URLs":[199],"feature":[200],"selection":[201],"involvement":[205],"domain":[208],"specialist.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
