{"id":"https://openalex.org/W4372260394","doi":"https://doi.org/10.1109/icassp49357.2023.10095719","title":"A Large-Scale Pretrained Deep Model for Phishing URL Detection","display_name":"A Large-Scale Pretrained Deep Model for Phishing URL Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260394","doi":"https://doi.org/10.1109/icassp49357.2023.10095719"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100716162","display_name":"Yanbin Wang","orcid":"https://orcid.org/0000-0001-8295-3638"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbin Wang","raw_affiliation_strings":["Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101106451","display_name":"Weifan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifan Zhu","raw_affiliation_strings":["Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055561370","display_name":"Haitao Xu","orcid":"https://orcid.org/0000-0002-0353-3879"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Xu","raw_affiliation_strings":["Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043524348","display_name":"Zhan Qin","orcid":"https://orcid.org/0000-0001-7872-6969"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Qin","raw_affiliation_strings":["Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000596496","display_name":"Kui Ren","orcid":"https://orcid.org/0000-0003-3441-6277"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kui Ren","raw_affiliation_strings":["Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101337304","display_name":"Wenrui Ma","orcid":"https://orcid.org/0009-0003-9649-1499"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Ma","raw_affiliation_strings":["Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,School of Cyber Security and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"School of Cyber Security and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and technological Innovation Center, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.3732,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.9873914,"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":"1","last_page":"5"},"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9965999722480774,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9940000176429749,"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":0.9644271731376648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8443223237991333},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6948492527008057},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.565237820148468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5227237343788147},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5109373927116394},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5101442933082581},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4993448257446289},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4114242196083069},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4101177453994751},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3394222855567932},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18615210056304932},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.15847784280776978},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07616099715232849}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.9644271731376648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8443223237991333},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6948492527008057},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.565237820148468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5227237343788147},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5109373927116394},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5101442933082581},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4993448257446289},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4114242196083069},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4101177453994751},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3394222855567932},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18615210056304932},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.15847784280776978},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07616099715232849},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2012481173","https://openalex.org/W2023973750","https://openalex.org/W2787538540","https://openalex.org/W2896457183","https://openalex.org/W2924514597","https://openalex.org/W2963250244","https://openalex.org/W2979476256","https://openalex.org/W3015534721","https://openalex.org/W3035204084","https://openalex.org/W3158143049","https://openalex.org/W3170863103","https://openalex.org/W3173978539","https://openalex.org/W3197388494","https://openalex.org/W3203910845","https://openalex.org/W4225454120","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6748384357","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6779411778","https://openalex.org/W6796761347"],"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],"attacks":[1],"have":[2],"always":[3],"been":[4],"a":[5,59,71,77,87],"security":[6,16],"issue":[7],"that":[8,123],"has":[9],"attracted":[10],"great":[11],"attention":[12],"in":[13,133],"the":[14,19,102,129,141],"cyber":[15],"community.":[17],"Recently,":[18],"famous":[20],"pre-trained":[21,37],"models":[22,36,46],"is":[23,98,125],"being":[24,84],"used":[25],"as":[26],"an":[27],"anti-phishing":[28],"solution.":[29],"However,":[30],"existing":[31],"studies":[32,121],"either":[33],"simply":[34],"transfer":[35],"on":[38,86,140],"text":[39],"to":[40,101,128],"phishing":[41,51,67,144],"detection":[42,103],"task,":[43],"or":[44],"pre-train":[45],"using":[47,114],"only":[48],"extremely":[49],"small":[50],"samples.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"propose":[57],"PhishBERT,":[58],"veritable":[60],"pretrained":[61,85],"deep":[62],"transformer":[63],"network":[64],"model":[65],"for":[66],"URL":[68,95,109],"detection.":[69,146],"Using":[70],"tailor":[72],"pre-training":[73],"objective,":[74],"PhishBERT":[75,124],"obtained":[76],"general":[78],"understanding":[79],"of":[80,89,105,135,143],"various":[81],"URLs":[82],"by":[83],"corpus":[88],"more":[90],"than":[91],"3":[92],"billion":[93],"unlabeled":[94],"data.":[96],"It":[97],"then":[99],"transferred":[100],"task":[104,142],"benign":[106],"and":[107,118,138],"malicious":[108],"data,":[110],"with":[111],"supervised":[112],"fine-tuning":[113],"adversarial":[115],"methods.":[116],"Extensive":[117],"rigorous":[119],"benchmark":[120],"verify":[122],"significantly":[126],"superior":[127],"current":[130],"state-of-the-art":[131],"methods":[132],"terms":[134],"efficiency,":[136],"robustness":[137],"accuracy":[139],"website":[145]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}