{"id":"https://openalex.org/W2810769850","doi":"https://doi.org/10.1109/icin.2018.8401597","title":"Classification of URL bitstreams using bag of bytes","display_name":"Classification of URL bitstreams using bag of bytes","publication_year":2018,"publication_date":"2018-02-01","ids":{"openalex":"https://openalex.org/W2810769850","doi":"https://doi.org/10.1109/icin.2018.8401597","mag":"2810769850"},"language":"en","primary_location":{"id":"doi:10.1109/icin.2018.8401597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icin.2018.8401597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.06087","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Keiichi Shima","orcid":null},"institutions":[{"id":"https://openalex.org/I4387153849","display_name":"Internet Initiative Japan","ror":"https://ror.org/05c4bsk60","country_code":null,"type":"company","lineage":["https://openalex.org/I4210145792","https://openalex.org/I4387153849"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Keiichi Shima","raw_affiliation_strings":["Internet Initiative Japan Inc., 2-10-1 Fujimi, Chiyoda-ku, Tokyo 102-0071, Japan"],"affiliations":[{"raw_affiliation_string":"Internet Initiative Japan Inc., 2-10-1 Fujimi, Chiyoda-ku, Tokyo 102-0071, Japan","institution_ids":["https://openalex.org/I4387153849"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daisuke Miyamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Miyamoto","raw_affiliation_strings":["Nara Advanced Institute of Science and Technology, 8916-5 Takayama-cho, Ikoma, Nara 630-0192, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Advanced Institute of Science and Technology, 8916-5 Takayama-cho, Ikoma, Nara 630-0192, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hiroshi Abe","orcid":null},"institutions":[{"id":"https://openalex.org/I4387153849","display_name":"Internet Initiative Japan","ror":"https://ror.org/05c4bsk60","country_code":null,"type":"company","lineage":["https://openalex.org/I4210145792","https://openalex.org/I4387153849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Abe","raw_affiliation_strings":["Internet Initiative Japan Inc., 2-10-1 Fujimi, Chiyoda-ku, Tokyo 102-0071, Japan"],"affiliations":[{"raw_affiliation_string":"Internet Initiative Japan Inc., 2-10-1 Fujimi, Chiyoda-ku, Tokyo 102-0071, Japan","institution_ids":["https://openalex.org/I4387153849"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tomohiro Ishihara","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Ishihara","raw_affiliation_strings":["The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8654, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8654, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kazuya Okada","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Okada","raw_affiliation_strings":["The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8654, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8654, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuji Sekiya","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuji Sekiya","raw_affiliation_strings":["The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8654, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8654, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hirochika Asai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirochika Asai","raw_affiliation_strings":["Preferred Networks, Inc., 1-6-1 Otemachi, Chiyoda-ku, Tokyo 100-0004, Japan"],"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc., 1-6-1 Otemachi, Chiyoda-ku, Tokyo 100-0004, Japan","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yusuke Doi\u00a7","orcid":null},"institutions":[{"id":"https://openalex.org/I4387153849","display_name":"Internet Initiative Japan","ror":"https://ror.org/05c4bsk60","country_code":null,"type":"company","lineage":["https://openalex.org/I4210145792","https://openalex.org/I4387153849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Doi\u00a7","raw_affiliation_strings":["Internet Initiative Japan Inc., 2-10-1 Fujimi, Chiyoda-ku, Tokyo 102-0071, Japan"],"affiliations":[{"raw_affiliation_string":"Internet Initiative Japan Inc., 2-10-1 Fujimi, Chiyoda-ku, Tokyo 102-0071, Japan","institution_ids":["https://openalex.org/I4387153849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4387153849"],"apc_list":null,"apc_paid":null,"fwci":2.053,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90323658,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.996399998664856,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/byte","display_name":"Byte","score":0.642799973487854},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5651000142097473},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5026999711990356},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.426800012588501},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4171999990940094},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.382999986410141},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3822000026702881},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.3772999942302704},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.3474000096321106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993999719619751},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.642799973487854},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5651000142097473},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40709999203681946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39800000190734863},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.3474000096321106},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32919999957084656},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C182590292","wikidata":"https://www.wikidata.org/wiki/Q989632","display_name":"Network security","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C527821871","wikidata":"https://www.wikidata.org/wiki/Q228502","display_name":"Access control","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.26510000228881836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icin.2018.8401597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icin.2018.8401597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.06087","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.06087","pdf_url":"https://arxiv.org/pdf/2111.06087","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.06087","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.06087","pdf_url":"https://arxiv.org/pdf/2111.06087","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1985920648","https://openalex.org/W2053774863","https://openalex.org/W2139565456","https://openalex.org/W2146729596","https://openalex.org/W6734770194"],"related_works":[],"abstract_inverted_index":{"Protecting":[0],"users":[1,28],"from":[2,67,162,178,184],"accessing":[3],"malicious":[4],"web":[5,26,79,91],"sites":[6,27],"is":[7,35,40],"one":[8],"of":[9,77,88,90,116,146,189],"the":[10,134,147,185,202],"important":[11],"management":[12],"tasks":[13],"for":[14],"network":[15,136],"operators.":[16],"There":[17],"are":[18,47],"many":[19],"open-source":[20],"and":[21,169,182],"commercial":[22],"products":[23],"to":[24,58,108,158,201],"control":[25],"can":[29,72,124],"access.":[30],"The":[31,103],"most":[32],"traditional":[33],"approach":[34,71,96,105,157,168,195],"blacklist-based":[36],"filtering.":[37],"This":[38,70],"mechanism":[39],"simple":[41],"but":[42,81],"not":[43],"scalable,":[44],"though":[45],"there":[46],"some":[48],"enhanced":[49],"approaches":[50,56],"utilizing":[51],"fuzzy":[52],"matching":[53],"technologies.":[54],"Other":[55],"try":[57],"use":[59],"machine":[60],"learning":[61,99],"(ML)":[62],"techniques":[63],"by":[64,112,131],"extracting":[65],"features":[66,84,110],"URL":[68,148,163,173],"strings.":[69,164],"cover":[73],"a":[74,114,126,155,179],"wider":[75],"area":[76],"Internet":[78],"sites,":[80],"finding":[82],"good":[83],"requires":[85],"deep":[86,98],"knowledge":[87,145],"trends":[89],"site":[92,188,191],"design.":[93],"Recently,":[94],"another":[95],"using":[97],"(DL)":[100],"has":[101],"appeared.":[102],"DL":[104],"will":[106],"help":[107],"extract":[109],"automatically":[111],"investigating":[113],"lot":[115],"existing":[117,203],"sample":[118],"data.":[119],"Using":[120],"this":[121,151],"technique,":[122],"we":[123,153],"build":[125],"flexible":[127],"filtering":[128],"decision":[129],"module":[130,137],"keep":[132],"teaching":[133],"neural":[135],"about":[138],"recent":[139],"trends,":[140],"without":[141],"any":[142],"specific":[143],"expert":[144],"domain.":[149],"In":[150],"paper,":[152],"apply":[154],"mechanical":[156],"generate":[159],"feature":[160],"vectors":[161],"We":[165],"implemented":[166],"our":[167],"tested":[170],"with":[171],"realistic":[172],"access":[174],"history":[175],"data":[176,183],"taken":[177],"research":[180],"organization":[181],"famous":[186],"archive":[187],"phishing":[190],"information,":[192],"PhishTank.com.":[193],"Our":[194],"achieved":[196],"2~3%":[197],"better":[198],"accuracy":[199],"compared":[200],"DL-":[204],"based":[205],"approach.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-07-10T00:00:00"}
