{"id":"https://openalex.org/W3011774524","doi":"https://doi.org/10.1145/3375708.3380313","title":"Diverse Datasets and a Customizable Benchmarking Framework for Phishing","display_name":"Diverse Datasets and a Customizable Benchmarking Framework for Phishing","publication_year":2020,"publication_date":"2020-03-12","ids":{"openalex":"https://openalex.org/W3011774524","doi":"https://doi.org/10.1145/3375708.3380313","mag":"3011774524"},"language":"en","primary_location":{"id":"doi:10.1145/3375708.3380313","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3375708.3380313","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3375708.3380313","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth International Workshop on Security and Privacy Analytics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3375708.3380313","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017711261","display_name":"Victor Zeng","orcid":"https://orcid.org/0000-0003-0644-9370"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Victor Zeng","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043050771","display_name":"Shahryar Baki","orcid":"https://orcid.org/0000-0002-9814-9270"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shahryar Baki","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015271827","display_name":"Ayman El Aassal","orcid":"https://orcid.org/0000-0002-0225-4544"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayman El Aassal","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050592031","display_name":"Rakesh Verma","orcid":"https://orcid.org/0000-0002-7466-7823"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakesh Verma","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059190978","display_name":"Luis F. T. Moraes","orcid":"https://orcid.org/0000-0002-2643-8647"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Felipe Teixeira De Moraes","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065790431","display_name":"Avisha Das","orcid":"https://orcid.org/0000-0002-5015-2665"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avisha Das","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017711261"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":2.7827,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92157105,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"41"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9947999715805054,"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/benchmarking","display_name":"Benchmarking","score":0.9758727550506592},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.9346926212310791},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8053780794143677},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5088213086128235},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42107701301574707},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3317943215370178},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.17515292763710022}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.9758727550506592},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.9346926212310791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8053780794143677},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5088213086128235},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42107701301574707},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3317943215370178},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.17515292763710022},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3375708.3380313","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3375708.3380313","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3375708.3380313","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth International Workshop on Security and Privacy Analytics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3375708.3380313","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3375708.3380313","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3375708.3380313","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth International Workshop on Security and Privacy Analytics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1666312413","display_name":null,"funder_award_id":"DGE 1433817","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3322060798","display_name":"TWC: Small: Unsupervised and Statistical Natural Language Processing Techniques for Automatic Phishing and Opinion Spam Detection","funder_award_id":"1319212","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3366966419","display_name":null,"funder_award_id":"W911NF-16-1","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G4502811999","display_name":null,"funder_award_id":"W911NF-16-1-0422","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5236241718","display_name":null,"funder_award_id":"DUE 1356705","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5604170710","display_name":null,"funder_award_id":"1356705","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6303296854","display_name":null,"funder_award_id":"1433817","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G657448715","display_name":null,"funder_award_id":"W911NF-16-1-","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7628991547","display_name":null,"funder_award_id":"W911NF-16-1-0422","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8214249994","display_name":null,"funder_award_id":"CNS 1319212","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3011774524.pdf","grobid_xml":"https://content.openalex.org/works/W3011774524.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W150462035","https://openalex.org/W1492288577","https://openalex.org/W1537590135","https://openalex.org/W1635138928","https://openalex.org/W1956559956","https://openalex.org/W1956666414","https://openalex.org/W1964126497","https://openalex.org/W2004291985","https://openalex.org/W2011211026","https://openalex.org/W2051297055","https://openalex.org/W2068185042","https://openalex.org/W2070896531","https://openalex.org/W2134750673","https://openalex.org/W2156852385","https://openalex.org/W2294209216","https://openalex.org/W2488334223","https://openalex.org/W2521200999","https://openalex.org/W2544708643","https://openalex.org/W2555759095","https://openalex.org/W2603197593","https://openalex.org/W2787538540","https://openalex.org/W2886899115","https://openalex.org/W2906351126","https://openalex.org/W2913059114","https://openalex.org/W2953359974","https://openalex.org/W2953817258","https://openalex.org/W2988210345","https://openalex.org/W2994155906","https://openalex.org/W3003583062","https://openalex.org/W3004042307","https://openalex.org/W4293713156","https://openalex.org/W4296918582"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2011676020"],"abstract_inverted_index":{"Phishing":[0],"is":[1],"a":[2,44],"challenging":[3],"problem":[4],"that":[5],"has":[6],"been":[7],"addressed":[8],"by":[9],"many":[10,16],"researchers":[11,94],"in":[12],"several":[13],"papers":[14],"using":[15],"different":[17],"datatsets":[18],"and":[19,31,47,68,72,79,82,97,100,104],"techniques~\\citedas2019sok.":[20],"Researchers":[21],"usually":[22],"test":[23],"their":[24],"proposed":[25],"methods":[26],"with":[27],"limited":[28],"metrics,":[29],"datasets,":[30],"parameters":[32],"when":[33],"presenting":[34],"new":[35],"features":[36,99],"or":[37],"approach(es).":[38],"Hence,":[39],"the":[40,66,107],"need":[41],"arises":[42],"for":[43,75,87],"benchmarking":[45,88],"framework":[46,86],"dataset":[48],"to":[49,95],"evaluate":[50,96],"such":[51],"systems":[52],"as":[53,55],"comprehensively":[54],"possible.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"discuss:":[61],"(i)":[62],"our":[63,85],"efforts":[64],"on":[65,106],"creation":[67],"dissemination":[69],"of":[70],"diverse":[71],"representative":[73],"datasets":[74],"phishing":[76,89],"email,":[77],"website":[78],"URL":[80],"detection,":[81],"(ii)":[83],"PhishBench,":[84],"detection":[90],"systems.":[91],"PhishBench":[92],"allows":[93],"compare":[98],"classification":[101],"approaches":[102],"easily":[103],"efficiently":[105],"provided":[108],"data.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
