{"id":"https://openalex.org/W4415003351","doi":"https://doi.org/10.1109/acit65614.2025.11185656","title":"Rethinking Phishing Detection: How Dataset Quality Affects Model Generalization","display_name":"Rethinking Phishing Detection: How Dataset Quality Affects Model Generalization","publication_year":2025,"publication_date":"2025-09-17","ids":{"openalex":"https://openalex.org/W4415003351","doi":"https://doi.org/10.1109/acit65614.2025.11185656"},"language":"en","primary_location":{"id":"doi:10.1109/acit65614.2025.11185656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acit65614.2025.11185656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 15th International Conference on Advanced Computer Information Technologies (ACIT)","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/A5059576222","display_name":"Pedro Afonso","orcid":"https://orcid.org/0000-0002-4618-2589"},"institutions":[{"id":"https://openalex.org/I83863532","display_name":"Polytechnic Institute of Porto","ror":"https://ror.org/04988re48","country_code":"PT","type":"education","lineage":["https://openalex.org/I83863532"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Pedro Afonso","raw_affiliation_strings":["Polytechnic of Porto,GECAD, ISEP,Porto,Portugal"],"affiliations":[{"raw_affiliation_string":"Polytechnic of Porto,GECAD, ISEP,Porto,Portugal","institution_ids":["https://openalex.org/I83863532"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004608532","display_name":"Eva Maia","orcid":"https://orcid.org/0000-0002-8075-531X"},"institutions":[{"id":"https://openalex.org/I83863532","display_name":"Polytechnic Institute of Porto","ror":"https://ror.org/04988re48","country_code":"PT","type":"education","lineage":["https://openalex.org/I83863532"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Eva Maia","raw_affiliation_strings":["Polytechnic of Porto,GECAD, ISEP,Porto,Portugal"],"affiliations":[{"raw_affiliation_string":"Polytechnic of Porto,GECAD, ISEP,Porto,Portugal","institution_ids":["https://openalex.org/I83863532"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006784402","display_name":"Ivone Amorim","orcid":"https://orcid.org/0000-0001-6102-6165"},"institutions":[{"id":"https://openalex.org/I83863532","display_name":"Polytechnic Institute of Porto","ror":"https://ror.org/04988re48","country_code":"PT","type":"education","lineage":["https://openalex.org/I83863532"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Ivone Amorim","raw_affiliation_strings":["Polytechnic of Porto,GECAD, ISEP,Porto,Portugal"],"affiliations":[{"raw_affiliation_string":"Polytechnic of Porto,GECAD, ISEP,Porto,Portugal","institution_ids":["https://openalex.org/I83863532"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005516592","display_name":"Isabel Pra\u00e7a","orcid":"https://orcid.org/0000-0002-2519-9859"},"institutions":[{"id":"https://openalex.org/I83863532","display_name":"Polytechnic Institute of Porto","ror":"https://ror.org/04988re48","country_code":"PT","type":"education","lineage":["https://openalex.org/I83863532"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Isabel Pra\u00e7a","raw_affiliation_strings":["Polytechnic of Porto,GECAD, ISEP,Porto,Portugal"],"affiliations":[{"raw_affiliation_string":"Polytechnic of Porto,GECAD, ISEP,Porto,Portugal","institution_ids":["https://openalex.org/I83863532"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059576222"],"corresponding_institution_ids":["https://openalex.org/I83863532"],"apc_list":null,"apc_paid":null,"fwci":5.9121,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9647503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"542","last_page":"547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9629999995231628,"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":0.9606000185012817,"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/overfitting","display_name":"Overfitting","score":0.7786999940872192},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7778000235557556},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.7372000217437744},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6258999705314636},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6118000149726868},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5953999757766724},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5213000178337097},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4968999922275543}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7786999940872192},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7778000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486000061035156},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.7372000217437744},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6258999705314636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6118000149726868},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5953999757766724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5371999740600586},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4968999922275543},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4465999901294708},{"id":"https://openalex.org/C2780264999","wikidata":"https://www.wikidata.org/wiki/Q7445032","display_name":"Security domain","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3668999969959259},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3621000051498413},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2508000135421753},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acit65614.2025.11185656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acit65614.2025.11185656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 15th International Conference on Advanced Computer Information Technologies (ACIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2625935159","https://openalex.org/W2982523005","https://openalex.org/W2990193135","https://openalex.org/W2999300566","https://openalex.org/W3015534721","https://openalex.org/W3023514002","https://openalex.org/W3085804088","https://openalex.org/W3105217250","https://openalex.org/W3135306750","https://openalex.org/W3173117104","https://openalex.org/W4200587910","https://openalex.org/W4225454120","https://openalex.org/W4310348270","https://openalex.org/W4313196990","https://openalex.org/W4386512177","https://openalex.org/W4394015528","https://openalex.org/W4405338392","https://openalex.org/W4405760810"],"related_works":[],"abstract_inverted_index":{"Phishing":[0],"remains":[1],"a":[2,43,113,153],"pervasive":[3],"cybersecurity":[4],"threat,":[5],"prompting":[6],"the":[7,14,25,49,58,102,118,141],"development":[8],"of":[9,16,28,52,60,104,143],"numerous":[10],"detection":[11,55],"models":[12,56],"and":[13,33,57,80,86,94],"creation":[15],"various":[17],"public":[18],"benchmark":[19,145],"datasets":[20],"for":[21],"evaluation.":[22],"However,":[23],"despite":[24,125],"apparent":[26],"diversity":[27],"these":[29,105],"datasets,":[30,82,146],"their":[31],"quality":[32,69],"consistency":[34],"remain":[35],"largely":[36],"underexamined.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,107],"conduct":[42],"comprehensive":[44],"analysis":[45],"that":[46,90,124,140],"jointly":[47],"evaluates":[48],"generalization":[50,110,131],"ability":[51],"phishing":[53,159],"URL":[54,84],"integrity":[59],"widely":[61],"used":[62],"datasets.":[63],"Our":[64],"findings":[65],"reveal":[66],"critical":[67],"data":[68],"issues,":[70],"such":[71],"as":[72],"high":[73],"internal":[74],"duplication,":[75],"inconsistent":[76],"labeling":[77],"both":[78],"within":[79],"across":[81],"substantial":[83],"overlap,":[85],"severe":[87],"domain":[88],"overrepresentation,":[89],"undermine":[91],"model":[92,149],"evaluation":[93,135],"encourage":[95],"overfitting":[96],"to":[97],"dataset-specific":[98],"artifacts.":[99],"To":[100],"quantify":[101],"impact":[103],"flaws,":[106],"perform":[108],"cross-dataset":[109],"experiments":[111],"comparing":[112],"baseline":[114],"character-level":[115],"CNN":[116],"with":[117],"state-of-the-art":[119],"URLNet":[120],"architecture.":[121],"Results":[122],"show":[123],"URLNet\u2019s":[126],"complexity,":[127],"it":[128],"offers":[129],"limited":[130],"advantage":[132],"under":[133],"realistic":[134],"settings.":[136],"These":[137],"insights":[138],"highlight":[139],"limitations":[142],"current":[144],"rather":[147],"than":[148],"design":[150],"alone,":[151],"form":[152],"significant":[154],"bottleneck":[155],"in":[156],"advancing":[157],"robust":[158],"detection.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-20T07:46:08.049788","created_date":"2025-10-10T00:00:00"}