{"id":"https://openalex.org/W4384158012","doi":"https://doi.org/10.1109/netsoft57336.2023.10175503","title":"Phish Me If You Can \u2013 Lexicographic Analysis and Machine Learning for Phishing Websites Detection with PHISHWEB","display_name":"Phish Me If You Can \u2013 Lexicographic Analysis and Machine Learning for Phishing Websites Detection with PHISHWEB","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W4384158012","doi":"https://doi.org/10.1109/netsoft57336.2023.10175503"},"language":"en","primary_location":{"id":"doi:10.1109/netsoft57336.2023.10175503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/netsoft57336.2023.10175503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","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/A5030894737","display_name":"Lucas Torrealba Aravena","orcid":null},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]},{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["AT","CL"],"is_corresponding":false,"raw_author_name":"L. Torrealba Aravena","raw_affiliation_strings":["AIT Austrian Institute of Technology","NIC Labs, Universidad de Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIT Austrian Institute of Technology","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"NIC Labs, Universidad de Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081556750","display_name":"Pedro Casas","orcid":"https://orcid.org/0000-0002-0951-2331"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"P. Casas","raw_affiliation_strings":["AIT Austrian Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIT Austrian Institute of Technology","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062341453","display_name":"Javier Bustos-Jim\u00e9nez","orcid":"https://orcid.org/0000-0003-0036-2004"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"J. Bustos-Jim\u00e9nez","raw_affiliation_strings":["NIC Labs, Universidad de Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIC Labs, Universidad de Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085287240","display_name":"Germ\u00e1n Capdehourat","orcid":"https://orcid.org/0000-0002-3975-2168"},"institutions":[{"id":"https://openalex.org/I4210134706","display_name":"Plan Ceibal","ror":"https://ror.org/03hqq6242","country_code":"UY","type":"education","lineage":["https://openalex.org/I4210134706"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"G. Capdehourat","raw_affiliation_strings":["Universidad de la Rep&#x00FA;blica &#x0026; Plan Ceibal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de la Rep&#x00FA;blica &#x0026; Plan Ceibal","institution_ids":["https://openalex.org/I4210134706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039503631","display_name":"Mislav Findrik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Findrik","raw_affiliation_strings":["cyan Security Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"cyan Security Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5916,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91296362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"256"},"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":0.998199999332428,"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":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.7964056730270386},{"id":"https://openalex.org/keywords/lexicographical-order","display_name":"Lexicographical order","score":0.7077360153198242},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.667293131351471},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5441173315048218},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5327584743499756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5310528874397278},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5301547646522522},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4992544651031494},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48310184478759766},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4643123149871826},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.44173508882522583},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4415787160396576},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3309375047683716},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1290358304977417},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08864259719848633},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08643582463264465},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.07964026927947998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964056730270386},{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.7077360153198242},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.667293131351471},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5441173315048218},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5327584743499756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310528874397278},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5301547646522522},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4992544651031494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48310184478759766},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4643123149871826},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.44173508882522583},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4415787160396576},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3309375047683716},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1290358304977417},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08864259719848633},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08643582463264465},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.07964026927947998},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/netsoft57336.2023.10175503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/netsoft57336.2023.10175503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","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":10,"referenced_works":["https://openalex.org/W2040750298","https://openalex.org/W2805724970","https://openalex.org/W2913504480","https://openalex.org/W2972765591","https://openalex.org/W2972832672","https://openalex.org/W3114681532","https://openalex.org/W3175769352","https://openalex.org/W3180077975","https://openalex.org/W3180937267","https://openalex.org/W6798199789"],"related_works":["https://openalex.org/W1985455246","https://openalex.org/W2149202530","https://openalex.org/W2807822918","https://openalex.org/W2921723332","https://openalex.org/W2482950156","https://openalex.org/W1993634787","https://openalex.org/W3042334625","https://openalex.org/W3139248031","https://openalex.org/W4200017362","https://openalex.org/W2305322260"],"abstract_inverted_index":{"We":[0,79],"introduce":[1],"PHISHWEB,":[2],"a":[3,17,92,111],"novel":[4],"approach":[5],"to":[6,67,155],"website":[7],"phishing":[8],"detection,":[9],"which":[10],"detects":[11],"and":[12,29,55,74,136,141,166],"categorizes":[13],"malicious":[14],"websites":[15],"through":[16,37,87],"progressive,":[18],"multi-layered":[19],"analysis.":[20],"PHISHWEB\u2019s":[21,82],"detection":[22,83,104],"includes":[23],"forged":[24],"domains":[25,36,86,107],"such":[26],"as":[27,31,33,126,128],"homoglyph":[28],"typosquatting,":[30],"well":[32,127],"automatically":[34],"generated":[35],"DGA":[38,85,106,124],"technology.":[39],"The":[40],"focus":[41],"of":[42,48,57,65,84,95,105,119,139,153,172],"PHISHWEB":[43,66,120,123,154],"is":[44],"on":[45,62,102,150],"lexicographic-based":[46],"analysis":[47],"the":[49,58,63,103,117,151,158,173],"domain":[50,99],"name":[51],"itself,":[52],"improving":[53],"applicability":[54],"scalability":[56],"approach.":[59],"Preliminary":[60],"results":[61,76,149],"application":[64,152],"multiple":[68],"open":[69],"domain-name":[70],"datasets":[71],"show":[72,108],"precision":[73,135],"recall":[75,137],"above":[77],"90%.":[78],"additionally":[80],"extend":[81],"Machine":[88],"Learning":[89],"(ML),":[90],"using":[91],"small":[93],"set":[94],"highly":[96],"specialized":[97],"lexicographic":[98],"features.":[100],"Results":[101],"that,":[109],"for":[110],"false":[112],"alarm":[113],"rate":[114],"below":[115],"1%,":[116],"ML-extension":[118],"improves":[121],"non-ML":[122],"detector":[125],"state-of-the-art":[129],"by":[130],"at":[131,163],"least":[132],"60%,":[133],"realizing":[134],"values":[138],"93.1%":[140],"84.8%,":[142],"respectively.":[143],"Finally,":[144],"we":[145],"also":[146],"present":[147],"preliminary":[148],"real,":[156],"in":[157],"wild":[159],"DNS":[160],"requests":[161],"collected":[162],"large":[164],"mobile":[165],"fixed-line":[167],"operational":[168],"networks,":[169],"discussing":[170],"some":[171],"findings.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
