{"id":"https://openalex.org/W2588813228","doi":"https://doi.org/10.1109/ssci.2016.7850079","title":"Detecting malicious URLs using machine learning techniques","display_name":"Detecting malicious URLs using machine learning techniques","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2588813228","doi":"https://doi.org/10.1109/ssci.2016.7850079","mag":"2588813228"},"language":"en","primary_location":{"id":"doi:10.1109/ssci.2016.7850079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2016.7850079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5043872642","display_name":"Frank Vanhoenshoven","orcid":"https://orcid.org/0000-0003-2848-4492"},"institutions":[{"id":"https://openalex.org/I878454856","display_name":"Hasselt University","ror":"https://ror.org/04nbhqj75","country_code":"BE","type":"education","lineage":["https://openalex.org/I878454856"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Frank Vanhoenshoven","raw_affiliation_strings":["Universiteit Hasselt Campus Diepenbeek, Diepenbeek, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiteit Hasselt Campus Diepenbeek, Diepenbeek, Belgium","institution_ids":["https://openalex.org/I878454856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036962111","display_name":"Gonzalo N\u00e1poles","orcid":"https://orcid.org/0000-0003-1936-3701"},"institutions":[{"id":"https://openalex.org/I878454856","display_name":"Hasselt University","ror":"https://ror.org/04nbhqj75","country_code":"BE","type":"education","lineage":["https://openalex.org/I878454856"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Gonzalo Napoles","raw_affiliation_strings":["Universiteit Hasselt Campus Diepenbeek, Diepenbeek, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiteit Hasselt Campus Diepenbeek, Diepenbeek, Belgium","institution_ids":["https://openalex.org/I878454856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052669824","display_name":"Rafael Falc\u00f3n","orcid":"https://orcid.org/0000-0002-5906-3626"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rafael Falcon","raw_affiliation_strings":["Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042634804","display_name":"Koen Vanhoof","orcid":"https://orcid.org/0000-0001-7084-4223"},"institutions":[{"id":"https://openalex.org/I878454856","display_name":"Hasselt University","ror":"https://ror.org/04nbhqj75","country_code":"BE","type":"education","lineage":["https://openalex.org/I878454856"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Koen Vanhoof","raw_affiliation_strings":["Universiteit Hasselt Campus Diepenbeek, Diepenbeek, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiteit Hasselt Campus Diepenbeek, Diepenbeek, Belgium","institution_ids":["https://openalex.org/I878454856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109235894","display_name":"Mario K\u00f6ppen","orcid":null},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mario Koppen","raw_affiliation_strings":["Network Design and Research Center, Kyushu Institute of Technology, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Network Design and Research Center, Kyushu Institute of Technology, Fukuoka, Japan","institution_ids":["https://openalex.org/I207014233"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2016","issue":null,"first_page":"1","last_page":"8"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9954000115394592,"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":0.8004989624023438},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.7195035219192505},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7090673446655273},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5958556532859802},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5870738625526428},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.584834635257721},{"id":"https://openalex.org/keywords/blacklisting","display_name":"Blacklisting","score":0.574878454208374},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.558875322341919},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4738127291202545},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4646090567111969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45777082443237305},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4171745777130127},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3977421522140503},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38406917452812195},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37567514181137085},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.30588966608047485},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27016139030456543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004989624023438},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.7195035219192505},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7090673446655273},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5958556532859802},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5870738625526428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.584834635257721},{"id":"https://openalex.org/C2779797433","wikidata":"https://www.wikidata.org/wiki/Q632959","display_name":"Blacklisting","level":2,"score":0.574878454208374},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.558875322341919},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4738127291202545},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4646090567111969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45777082443237305},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4171745777130127},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3977421522140503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38406917452812195},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37567514181137085},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.30588966608047485},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27016139030456543}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ssci.2016.7850079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2016.7850079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:documentserver.uhasselt.be:1942/23181","is_oa":false,"landing_page_url":"http://hdl.handle.net/1942/23181","pdf_url":null,"source":{"id":"https://openalex.org/S4306401926","display_name":"Document Server@UHasselt (UHasselt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I878454856","host_organization_name":"Hasselt University","host_organization_lineage":["https://openalex.org/I878454856"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:2790222311","is_oa":false,"landing_page_url":"http://jglobal.jst.go.jp/en/public/201702230335183253","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1506859583","https://openalex.org/W1817561967","https://openalex.org/W1943383135","https://openalex.org/W1975909792","https://openalex.org/W1985920648","https://openalex.org/W2003471189","https://openalex.org/W2008056655","https://openalex.org/W2008353316","https://openalex.org/W2015452969","https://openalex.org/W2037869059","https://openalex.org/W2106401878","https://openalex.org/W2106525823","https://openalex.org/W2107008379","https://openalex.org/W2121990650","https://openalex.org/W2122111042","https://openalex.org/W2125055259","https://openalex.org/W2146241755","https://openalex.org/W2146729596","https://openalex.org/W2152805927","https://openalex.org/W2152929147","https://openalex.org/W2153149612","https://openalex.org/W2164330572","https://openalex.org/W2167460663","https://openalex.org/W2254069754","https://openalex.org/W2490023472","https://openalex.org/W2799148064","https://openalex.org/W2911964244","https://openalex.org/W2998768810","https://openalex.org/W4233045210","https://openalex.org/W6676132248","https://openalex.org/W6722680694"],"related_works":["https://openalex.org/W4281884841","https://openalex.org/W2933056782","https://openalex.org/W2012481173","https://openalex.org/W2043034431","https://openalex.org/W1593211785","https://openalex.org/W2139572494","https://openalex.org/W3033830493","https://openalex.org/W2005813008","https://openalex.org/W3207470445","https://openalex.org/W3215769141"],"abstract_inverted_index":{"The":[0,190],"World":[1],"Wide":[2],"Web":[3],"supports":[4],"a":[5,74,148,178,214],"wide":[6],"range":[7],"of":[8,104,144,156,213],"criminal":[9],"activities":[10],"such":[11,70],"as":[12,71,147],"spam-advertised":[13],"e-commerce,":[14],"financial":[15],"fraud":[16],"and":[17,110,152,172,186,221],"malware":[18],"dissemination.":[19],"Although":[20],"the":[21,29,34,62,87,142,154,211,225],"precise":[22],"motivations":[23],"behind":[24],"these":[25,84],"schemes":[26],"may":[27],"differ,":[28],"common":[30],"denominator":[31],"lies":[32],"in":[33,98],"fact":[35],"that":[36,195],"unsuspecting":[37],"users":[38],"visit":[39],"their":[40],"sites.":[41],"These":[42,95],"visits":[43],"can":[44],"be":[45],"driven":[46],"by":[47,101],"email,":[48],"web":[49,56,88,111],"search":[50],"results":[51],"or":[52,131,134,210],"links":[53],"from":[54],"other":[55],"pages.":[57],"In":[58,80,137,217],"all":[59],"cases,":[60],"however,":[61],"user":[63],"is":[64],"required":[65],"to":[66,82],"take":[67],"some":[68],"action,":[69],"clicking":[72],"on":[73],"desired":[75],"Uniform":[76],"Resource":[77],"Locator":[78],"(URL).":[79],"order":[81],"identify":[83],"malicious":[85,120,145],"sites,":[86],"security":[89],"community":[90],"has":[91],"developed":[92],"blacklisting":[93],"services.":[94],"blacklists":[96],"are":[97,122,128],"turn":[99],"constructed":[100],"an":[102],"array":[103],"techniques":[105,209],"including":[106],"manual":[107],"reporting,":[108],"honeypots,":[109],"crawlers":[112],"combined":[113],"with":[114],"site":[115],"analysis":[116],"heuristics.":[117],"Inevitably,":[118],"many":[119],"sites":[121],"not":[123],"blacklisted":[124],"either":[125,205],"because":[126],"they":[127],"too":[129],"recent":[130],"were":[132],"never":[133],"incorrectly":[135],"evaluated.":[136],"this":[138],"paper,":[139],"we":[140,176],"address":[141],"detection":[143],"URLs":[146,184],"binary":[149],"classification":[150,197],"problem":[151],"study":[153],"performance":[155],"several":[157],"well-known":[158],"classifiers,":[159],"namely":[160],"Na\u00efve":[161],"Bayes,":[162],"Support":[163],"Vector":[164],"Machines,":[165],"Multi-Layer":[166,222],"Perceptron,":[167],"Decision":[168],"Trees,":[169],"Random":[170,219],"Forest":[171,220],"k-Nearest":[173],"Neighbors.":[174],"Furthermore,":[175],"adopted":[177],"public":[179],"dataset":[180],"comprising":[181],"2.4":[182],"million":[183,188],"(instances)":[185],"3.2":[187],"features.":[189],"numerical":[191],"simulations":[192],"have":[193],"shown":[194],"most":[196],"methods":[198],"achieve":[199],"acceptable":[200],"prediction":[201],"rates":[202],"without":[203],"requiring":[204],"advanced":[206],"feature":[207],"selection":[208],"involvement":[212],"domain":[215],"expert.":[216],"particular,":[218],"Perceptron":[223],"attain":[224],"highest":[226],"accuracy.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}