{"id":"https://openalex.org/W4391828056","doi":"https://doi.org/10.1109/soli60636.2023.10425260","title":"Bridging the Gap in Phishing Detection: A Comprehensive Phishing Dataset Collector","display_name":"Bridging the Gap in Phishing Detection: A Comprehensive Phishing Dataset Collector","publication_year":2023,"publication_date":"2023-12-11","ids":{"openalex":"https://openalex.org/W4391828056","doi":"https://doi.org/10.1109/soli60636.2023.10425260"},"language":"en","primary_location":{"id":"doi:10.1109/soli60636.2023.10425260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/soli60636.2023.10425260","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 Service Operations and Logistics, and Informatics (SOLI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Bridging_the_Gap_in_Phishing_Detection_A_Comprehensive_Phishing_Dataset_Collector/27018694","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009137011","display_name":"Aditya Kulkarni","orcid":"https://orcid.org/0000-0002-7084-428X"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Kulkarni","raw_affiliation_strings":["Indian Institute of Technology,Dharwad,India","Indian Institute of Technology, Dharwad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]},{"raw_affiliation_string":"Indian Institute of Technology, Dharwad, India","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102617499","display_name":"Shahil Manishbhai Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shahil Manishbhai Patel","raw_affiliation_strings":["Indian Institute of Technology,Dharwad,India","Indian Institute of Technology, Dharwad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]},{"raw_affiliation_string":"Indian Institute of Technology, Dharwad, India","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093930947","display_name":"Shivam Pradip Tirrnare","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shivam Pradip Tirrnare","raw_affiliation_strings":["Indian Institute of Technology,Dharwad,India","Indian Institute of Technology, Dharwad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]},{"raw_affiliation_string":"Indian Institute of Technology, Dharwad, India","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021323754","display_name":"Vivek Balachandran","orcid":"https://orcid.org/0000-0003-4847-7150"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Vivek Balachandran","raw_affiliation_strings":["Singapore Institute of Technology,Singapore","Singapore Institute of Technology, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]},{"raw_affiliation_string":"Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039200449","display_name":"Tamal Das","orcid":"https://orcid.org/0000-0003-0455-2067"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tamal Das","raw_affiliation_strings":["Indian Institute of Technology,Dharwad,India","Indian Institute of Technology, Dharwad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]},{"raw_affiliation_string":"Indian Institute of Technology, Dharwad, India","institution_ids":["https://openalex.org/I4210152718"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8627,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81865967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.984000027179718,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9623000025749207,"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":0.9613101482391357},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7504051923751831},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6861532330513},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6236876249313354},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.47951987385749817},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.43422698974609375},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3206821084022522},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.18481722474098206},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07240557670593262}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.9613101482391357},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7504051923751831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6861532330513},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6236876249313354},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.47951987385749817},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.43422698974609375},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3206821084022522},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.18481722474098206},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07240557670593262}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/soli60636.2023.10425260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/soli60636.2023.10425260","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 Service Operations and Logistics, and Informatics (SOLI)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/27018694","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Bridging_the_Gap_in_Phishing_Detection_A_Comprehensive_Phishing_Dataset_Collector/27018694","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27018694","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Bridging_the_Gap_in_Phishing_Detection_A_Comprehensive_Phishing_Dataset_Collector/27018694","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2026905436","https://openalex.org/W2043034431","https://openalex.org/W2096762731","https://openalex.org/W2139565456","https://openalex.org/W2146729596","https://openalex.org/W2787538540","https://openalex.org/W2800391419","https://openalex.org/W3106934761","https://openalex.org/W4220702949","https://openalex.org/W4242562554","https://openalex.org/W4299301436","https://openalex.org/W4391828056","https://openalex.org/W6748384357","https://openalex.org/W6794959624"],"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":{"To":[0],"combat":[1],"phishing":[2,17,46,56,82,96,109,114,162,200,217,242],"attacks":[3],"-":[4,15],"aimed":[5],"at":[6],"luring":[7],"web":[8],"users":[9],"to":[10,30,53,101,112,134,172],"divulge":[11],"their":[12,204,220],"sensitive":[13],"information":[14],"various":[16,136],"detection":[18,33,57,243],"approaches":[19],"have":[20,36],"been":[21],"proposed.":[22],"As":[23],"attackers":[24],"focus":[25],"on":[26,62,207,213],"devising":[27],"new":[28],"tactics":[29],"bypass":[31],"existing":[32],"solutions,":[34],"researchers":[35,238],"adapted":[37],"by":[38],"integrating":[39],"machine":[40],"learning":[41,44],"and":[42,122,149,198],"deep":[43],"into":[45],"detection.":[47],"Phishing":[48],"dataset":[49,75,98,189],"collection":[50,131],"is":[51,89],"vital":[52],"developing":[54,240],"effective":[55,241],"approaches,":[58],"which":[59,176],"highly":[60],"depend":[61],"the":[63,66,74,156,214],"diversity":[64,72],"of":[65,71],"gathered":[67],"datasets.":[68],"The":[69],"lack":[70],"in":[73,77,225,239],"results":[76],"a":[78,91,113,129,140,181,187,231],"biased":[79],"model.":[80],"Since":[81],"websites":[83],"are":[84],"often":[85],"short-lived,":[86],"collecting":[87],"them":[88],"also":[90,211],"challenge.":[92],"Consequently,":[93],"very":[94],"few":[95],"webpage":[97,118,124,147,169,178],"repositories":[99],"exist":[100],"date.":[102],"No":[103],"single":[104],"repository":[105],"comprehensively":[106],"consolidates":[107],"all":[108],"elements":[110],"corresponding":[111],"webpage,":[115],"namely,":[116],"URL,":[117,141],"source":[119,158],"code,":[120],"screenshot,":[121],"related":[123],"resources.":[125],"This":[126],"paper":[127],"introduces":[128],"resource":[130,233],"tool":[132,152,165,193,229],"designed":[133],"gather":[135],"resources":[137,170,206],"associated":[138,205,221],"with":[139,203,219],"such":[142],"as":[143,155],"CSS,":[144],"Javascript,":[145],"favicons,":[146],"images,":[148],"screenshots.":[150],"Our":[151,164,228],"leverages":[153],"PhishTank":[154],"primary":[157],"for":[159,180],"obtaining":[160],"active":[161],"URLs.":[163],"fetches":[166],"several":[167],"additional":[168],"compared":[171],"PyWebCopy":[173],"Python":[174],"library,":[175],"provides":[177],"content":[179],"given":[182],"URL.":[183],"Additionally,":[184],"we":[185],"share":[186],"sample":[188],"generated":[190],"using":[191],"our":[192,226],"comprising":[194],"4,":[195],"056":[196],"legitimate":[197],"5,666":[199],"URLs":[201],"along":[202],"GitHub":[208],"[1].":[209],"We":[210],"remark":[212],"top":[215],"correlated":[216],"features":[218],"class":[222],"label":[223],"found":[224],"dataset.":[227],"offers":[230],"comprehensive":[232],"set":[234],"that":[235],"can":[236],"aid":[237],"approaches.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}