{"id":"https://openalex.org/W7204654167","doi":"https://doi.org/10.21227/7zkt-a868","title":"\"PHISHING 2026 DATASET\"","display_name":"\"PHISHING 2026 DATASET\"","publication_year":2026,"publication_date":"2026-08-29","ids":{"openalex":"https://openalex.org/W7204654167","doi":"https://doi.org/10.21227/7zkt-a868"},"language":"en","primary_location":{"id":"doi:10.21227/7zkt-a868","doi":"https://doi.org/10.21227/7zkt-a868","is_oa":true,"landing_page_url":"https://doi.org/10.21227/7zkt-a868","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"parent_works":[],"lineage":["https://openalex.org/W7204654167"],"child_works_count":0,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/7zkt-a868","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123014661","display_name":"Ashvini jadhav","orcid":"https://orcid.org/0000-0001-6087-7208","observed_orcids":["https://orcid.org/0000-0001-6087-7208"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"ASHVINI JADHAV","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5123014661"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.0,"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/T11800","display_name":"User Authentication and Security Systems","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/phishing-url-detection","display_name":"phishing URL detection","score":0.9629999995231628},{"id":"https://openalex.org/keywords/url-classification","display_name":"URL classification","score":0.6389999985694885},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.7110000252723694},{"id":"https://openalex.org/keywords/information-gain","display_name":"information gain","score":0.7049999833106995},{"id":"https://openalex.org/keywords/typosquatting","display_name":"typosquatting","score":0.8090000152587891},{"id":"https://openalex.org/keywords/unicode","display_name":"Unicode","score":0.6029999852180481},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.6010000109672546},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"multi-objective optimization","score":0.8009999990463257},{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.4560000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591999769210815},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5593000054359436},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5357000231742859},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44519999623298645},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.4332999885082245},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3587000072002411},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.3452000021934509},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.26350000500679016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/7zkt-a868","doi":"https://doi.org/10.21227/7zkt-a868","is_oa":true,"landing_page_url":"https://doi.org/10.21227/7zkt-a868","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.21227/7zkt-a868","doi":"https://doi.org/10.21227/7zkt-a868","is_oa":true,"landing_page_url":"https://doi.org/10.21227/7zkt-a868","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204627672","https://openalex.org/W7083686362","https://openalex.org/W6963772735","https://openalex.org/W7207810905","https://openalex.org/W7212550059","https://openalex.org/W7120000499","https://openalex.org/W7115601344","https://openalex.org/W6977838531","https://openalex.org/W7212293982","https://openalex.org/W7101442820"],"abstract_inverted_index":{"\"The":[0],"Proposed":[1],"Multi-Domain":[2],"Phishing":[3],"URL":[4,17,33,42,59,116,202],"Feature":[5,131],"Dataset":[6],"(PMPUFD)":[7],"is":[8,52,102,194],"a":[9,146,197],"structured":[10],"dataset":[11,30,121,141,193,227],"designed":[12],"for":[13,126,179,200],"research":[14,198],"on":[15],"phishing":[16,115,201],"detection,":[18],"feature":[19,50,109,112],"selection,":[20,113],"classification,":[21],"optimization,":[22],"ablation":[23,214],"analysis,":[24],"and":[25,35,44,62,66,70,73,77,81,90,93,114,134,163,218],"robustness":[26,216],"evaluation.":[27],"The":[28],"validated":[29],"contains":[31],"911,728":[32],"records":[34],"187":[36],"columns,":[37],"with":[38,145],"'URL'":[39],"representing":[40,46],"the":[41,47,99,120,170,183,226],"field":[43],"'label'":[45],"classification":[48],"target.The":[49],"space":[51],"organized":[53],"into":[54],"multiple":[55],"analytical":[56],"domains,":[57],"including":[58],"structure,":[60],"domain":[61],"subdomain":[63],"characteristics,":[64,79,84],"character":[65],"ratio":[67],"statistics,":[68],"entropy":[69],"randomness,":[71],"protocol":[72],"TLD":[74],"indicators,":[75,88,92],"IP":[76],"port":[78],"obfuscation":[80],"encoding,":[82],"webpage\\/HTML":[83],"URL-domain-title":[85],"similarity,":[86],"brand\\/similarity":[87],"typosquatting":[89],"attack-pattern":[91],"homograph\\/Unicode":[94],"indicators":[95],"where":[96],"represented":[97],"by":[98],"submitted":[100],"columns.PMPUFD":[101],"intended":[103],"to":[104],"support":[105],"systematic":[106],"investigation":[107],"of":[108],"relevance,":[110],"redundancy,":[111],"classification.":[117],"In":[118],"particular,":[119],"provides":[122],"an":[123],"experimental":[124,148],"foundation":[125],"evaluating":[127],"Information":[128,156],"Gain-guided":[129],"Heuristic-Constrained":[130],"Selection":[132],"(IG-HC\\u00b2FS)":[133],"subsequent":[135],"hyperparameter":[136],"or":[137],"multi-objective":[138],"optimization":[139,164],"strategies.The":[140],"should":[142,166,176,187,207],"be":[143,167,177,208],"used":[144,178],"leakage-safe":[147],"protocol.":[149],"For":[150],"final":[151,191],"predictive":[152],"experiments,":[153],"preprocessing":[154],"parameters,":[155],"Gain":[157],"calculations,":[158],"correlation":[159],"thresholds,":[160],"feature-selection":[161],"decisions,":[162,181],"decisions":[165],"fitted":[168],"using":[169],"training":[171],"partition":[172,186],"only.":[173],"Validation":[174],"data":[175],"model-selection":[180],"while":[182],"held-out":[184],"test":[185],"remain":[188],"unseen":[189],"until":[190],"evaluation.The":[192],"provided":[195],"as":[196],"resource":[199],"detection":[203],"experiments.":[204],"Performance":[205],"superiority":[206],"established":[209],"through":[210],"controlled":[211],"baseline":[212],"comparisons,":[213],"studies,":[215],"testing,":[217],"appropriate":[219],"statistical":[220],"evaluation":[221],"rather":[222],"than":[223],"inferred":[224],"from":[225],"composition":[228],"alone.":[229],"\"":[230]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-30T00:00:00"}