{"id":"https://openalex.org/W2072123701","doi":"https://doi.org/10.1080/15567280600995501","title":"REGAP: A Tool for Unicode-Based Web Identity Fraud Detection","display_name":"REGAP: A Tool for Unicode-Based Web Identity Fraud Detection","publication_year":2006,"publication_date":"2006-07-01","ids":{"openalex":"https://openalex.org/W2072123701","doi":"https://doi.org/10.1080/15567280600995501","mag":"2072123701"},"language":"en","primary_location":{"id":"doi:10.1080/15567280600995501","is_oa":false,"landing_page_url":"https://doi.org/10.1080/15567280600995501","pdf_url":null,"source":{"id":"https://openalex.org/S127916260","display_name":"Journal of Digital Forensic Practice","issn_l":"1556-7281","issn":["1556-7281","1556-7346"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Digital Forensic Practice","raw_type":"journal-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/A5018802389","display_name":"Anthony Y. Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Anthony Y. Fu","raw_affiliation_strings":["Department of Computer Science , City University of Hong Kong, 83, Tat Chee Avenue , Kow Long Tong, Hong Kong SAR, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science , City University of Hong Kong, 83, Tat Chee Avenue , Kow Long Tong, Hong Kong SAR, P. R. China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638710","display_name":"Xiaotie Deng","orcid":"https://orcid.org/0000-0002-5282-6467"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaotie Deng","raw_affiliation_strings":["Department of Computer Science , City University of Hong Kong, 83, Tat Chee Avenue , Kow Long Tong, Hong Kong SAR, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science , City University of Hong Kong, 83, Tat Chee Avenue , Kow Long Tong, Hong Kong SAR, P. R. China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":null,"display_name":"Liu Wenyin","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liu Wenyin","raw_affiliation_strings":["Department of Computer Science , City University of Hong Kong, 83, Tat Chee Avenue , Kow Long Tong, Hong Kong SAR, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science , City University of Hong Kong, 83, Tat Chee Avenue , Kow Long Tong, Hong Kong SAR, P. R. China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018802389"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":1.7238,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89047229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":"2","first_page":"83","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9976000189781189,"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":0.9976000189781189,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9940999746322632,"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":0.9927999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/unicode","display_name":"Unicode","score":0.9755378365516663},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7416893243789673},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6811622381210327},{"id":"https://openalex.org/keywords/ascii","display_name":"ASCII","score":0.4939480423927307},{"id":"https://openalex.org/keywords/character-encoding","display_name":"Character encoding","score":0.4312222898006439},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.4208594560623169},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3336211144924164},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.3291284739971161},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.30403077602386475},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28298890590667725},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.16612228751182556},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.092312753200531}],"concepts":[{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.9755378365516663},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7416893243789673},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6811622381210327},{"id":"https://openalex.org/C196832560","wikidata":"https://www.wikidata.org/wiki/Q8815","display_name":"ASCII","level":2,"score":0.4939480423927307},{"id":"https://openalex.org/C32717103","wikidata":"https://www.wikidata.org/wiki/Q184759","display_name":"Character encoding","level":3,"score":0.4312222898006439},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.4208594560623169},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3336211144924164},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3291284739971161},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30403077602386475},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28298890590667725},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.16612228751182556},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.092312753200531},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/15567280600995501","is_oa":false,"landing_page_url":"https://doi.org/10.1080/15567280600995501","pdf_url":null,"source":{"id":"https://openalex.org/S127916260","display_name":"Journal of Digital Forensic Practice","issn_l":"1556-7281","issn":["1556-7281","1556-7346"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Digital Forensic Practice","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320322170","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2415401904","https://openalex.org/W3214708461","https://openalex.org/W172151579","https://openalex.org/W3125384896","https://openalex.org/W2227498953","https://openalex.org/W4386331007","https://openalex.org/W4210506626","https://openalex.org/W2950192240","https://openalex.org/W3125143615","https://openalex.org/W1524330646"],"abstract_inverted_index":{"ABSTRACT":[0],"We":[1,208,217,263,331,356],"anticipate":[2],"the":[3,19,31,44,53,63,112,143,155,158,182,199,203,276,282,326],"widespread":[4],"usage":[5],"of":[6,18,30,43,66,124,129,145,149,206,251,271,293],"an":[7,60,78,303,321],"internationalized":[8,64,70],"resource":[9,21,33,118],"identifier":[10,22,119],"(IRI)":[11],"1":[12],"1.":[13],"IRI":[14,61],"is":[15,25,62,77,122,140,163,242,280,290],"a":[16,28,41,67,127,133,146,210,219,234,243,269,272,333,361],"generalization":[17,29],"uniform":[20,32],"(URI),":[23],"which":[24,341],"in":[26,126,198,320],"turn":[27],"locator":[34],"(URL).":[35],"While":[36],"URIs":[37],"are":[38,193],"limited":[39],"to":[40,116,166,181,196,212,267,302,324,366],"subset":[42,128],"ASCII":[45],"character":[46,55,156,221],"set,":[47],"IRIs":[48],"may":[49,177,257],"contain":[50,91],"characters":[51,102,125],"from":[52,103],"universal":[54,117],"set":[56,292],"(Unicode/ISO":[57],"10646).":[58],"Basically,":[59],"version":[65],"URI":[68],"or":[69,101,109,172],"domain":[71,80,88],"name":[72,81],"(IDN)":[73],"2":[74],"2.":[75],"IDN":[76],"Internet":[79],"that":[82,132,298],"(potentially)":[83],"contains":[84],"non-ASCII":[85],"characters.":[86],"Such":[87],"names":[89],"could":[90,168,296],"letters":[92],"with":[93,202],"diacritics,":[94],"as":[95,107,114],"required":[96],"by":[97,142,340],"many":[98],"European":[99],"languages,":[100],"non-Latin":[104],"scripts":[105],"such":[106,131,214,360],"Arabic":[108],"Chinese.":[110],"on":[111,190,226],"web":[113],"complement":[115],"(URI).":[120],"IRI/IDN":[121,167,335,343,354],"composed":[123],"Unicode,":[130],"Unicode":[134,138,152,161],"attack":[135,139,162],"3":[136],"3.":[137],"caused":[141],"coexistence":[144],"large":[147],"number":[148],"visual/semantically":[150],"similar":[151,160],"strings.":[153],"On":[154],"level,":[157],"visually":[159,171],"homograph":[164],"attack.":[165,216],"happen.":[169],"Hence,":[170],"semantically,":[173],"certain":[174,273],"phishing":[175,187,215,329,334,342,353],"IRI/IDNs":[176],"show":[178],"high":[179],"similarity":[180,222],"real":[183],"ones.":[184],"The":[185],"potential":[186,327],"attacks":[188],"based":[189,225],"this":[191],"strategy":[192],"very":[194],"likely":[195],"happen":[197],"near":[200],"future":[201],"boosting":[204],"utilization":[205],"IRI/IDN.":[207],"invented":[209],"method":[211],"detect":[213],"constructed":[218],"unicode":[220],"list":[223],"(UC-SimList)":[224],"char-char":[227],"visual":[228],"and":[229,232,253,286],"semantic":[230],"similarities":[231],"use":[233,265],"nondeterministic":[235],"finite":[236,244],"automaton":[237],"(NFA)":[238],"4":[239],"4.":[240],"NFA":[241,283],"state":[245,252],"machine":[246],"where":[247],"for":[248,352],"each":[249],"pair":[250],"input":[254,278],"symbol":[255,279],"there":[256,289],"be":[258,346,364],"several":[259],"possible":[260],"next":[261],"states.":[262],"can":[264,345,363],"it":[266,295,301,307,314,316],"recognize":[268],"string":[270],"pattern.":[274],"When":[275],"last":[277],"consumed":[281],"accepts":[284],"if":[285,288,309],"only":[287],"some":[291],"transitions":[294],"make":[297],"will":[299],"take":[300],"accepting":[304,322],"state.":[305,323],"Equivalently,":[306],"rejects":[308],"no":[310],"matter":[311],"what":[312],"choices":[313],"makes":[315],"would":[317],"not":[318],"end":[319],"identify":[325],"IRI/IDN-based":[328],"patterns.":[330],"implemented":[332],"pattern":[336],"generation":[337],"tool,":[338],"REGAP,":[339],"patterns":[344],"generated":[347],"into":[348],"regular":[349],"expressions":[350],"(RE)":[351],"detection.":[355],"also":[357],"address":[358],"how":[359],"tool":[362],"applied":[365],"investigations.":[367]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
