{"id":"https://openalex.org/W3007831685","doi":"https://doi.org/10.1145/3366030.3366064","title":"URL-based Phishing Detection using the Entropy of Non-Alphanumeric Characters","display_name":"URL-based Phishing Detection using the Entropy of Non-Alphanumeric Characters","publication_year":2019,"publication_date":"2019-12-02","ids":{"openalex":"https://openalex.org/W3007831685","doi":"https://doi.org/10.1145/3366030.3366064","mag":"3007831685"},"language":"en","primary_location":{"id":"doi:10.1145/3366030.3366064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366030.3366064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Information Integration and Web-based Applications &amp; Services","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://waseda.repo.nii.ac.jp/?action=repository_action_common_download&item_id=47427&item_no=1&attribute_id=20&file_no=1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054121746","display_name":"Eint Sandi Aung","orcid":"https://orcid.org/0000-0003-4017-1253"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eint Sandi Aung","raw_affiliation_strings":["Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031456992","display_name":"Hayato Yamana","orcid":"https://orcid.org/0000-0001-7542-4826"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayato Yamana","raw_affiliation_strings":["Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":1.5365,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85101661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"392"},"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/T11800","display_name":"User Authentication and Security Systems","score":0.9961000084877014,"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":0.9954000115394592,"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/phishing","display_name":"Phishing","score":0.9434906244277954},{"id":"https://openalex.org/keywords/alphanumeric","display_name":"Alphanumeric","score":0.9034327268600464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7827457189559937},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5291816592216492},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5261416435241699},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4657723605632782},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4592246115207672},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4488907754421234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40255725383758545},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3671911656856537},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.20828792452812195},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2051255702972412}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.9434906244277954},{"id":"https://openalex.org/C2781003394","wikidata":"https://www.wikidata.org/wiki/Q737372","display_name":"Alphanumeric","level":2,"score":0.9034327268600464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827457189559937},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5291816592216492},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5261416435241699},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4657723605632782},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4592246115207672},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4488907754421234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40255725383758545},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3671911656856537},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.20828792452812195},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2051255702972412},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3366030.3366064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366030.3366064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Information Integration and Web-based Applications &amp; Services","raw_type":"proceedings-article"},{"id":"pmh:oai:waseda.repo.nii.ac.jp:00047427","is_oa":true,"landing_page_url":"http://hdl.handle.net/2065/00063248","pdf_url":"https://waseda.repo.nii.ac.jp/?action=repository_action_common_download&item_id=47427&item_no=1&attribute_id=20&file_no=1","source":{"id":"https://openalex.org/S4377196531","display_name":"Waseda University Repository (Waseda University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150744194","host_organization_name":"Waseda University","host_organization_lineage":["https://openalex.org/I150744194"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis or Dissertation"}],"best_oa_location":{"id":"pmh:oai:waseda.repo.nii.ac.jp:00047427","is_oa":true,"landing_page_url":"http://hdl.handle.net/2065/00063248","pdf_url":"https://waseda.repo.nii.ac.jp/?action=repository_action_common_download&item_id=47427&item_no=1&attribute_id=20&file_no=1","source":{"id":"https://openalex.org/S4377196531","display_name":"Waseda University Repository (Waseda University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150744194","host_organization_name":"Waseda University","host_organization_lineage":["https://openalex.org/I150744194"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis or Dissertation"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8502859603","display_name":"Credibility Analysis of Web contents based on 10 billion Web pages","funder_award_id":"17KT0085","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007831685.pdf","grobid_xml":"https://content.openalex.org/works/W3007831685.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2096762731","https://openalex.org/W2166731089","https://openalex.org/W2545733139","https://openalex.org/W2618014102","https://openalex.org/W2625935159","https://openalex.org/W2794598542","https://openalex.org/W2807822918","https://openalex.org/W2903467393"],"related_works":["https://openalex.org/W2049379968","https://openalex.org/W2461009308","https://openalex.org/W2048515600","https://openalex.org/W2322679734","https://openalex.org/W2507454043","https://openalex.org/W2236176244","https://openalex.org/W2509420154","https://openalex.org/W1979637215","https://openalex.org/W1992508337","https://openalex.org/W2048396828"],"abstract_inverted_index":{"Phishing":[0,17],"is":[1,28],"a":[2,41,98],"type":[3],"of":[4,66,92,104],"personal":[5],"information":[6,37],"theft":[7],"in":[8,40],"which":[9,43,134],"phishers":[10,30],"lure":[11],"users":[12],"to":[13,71,141],"steal":[14],"sensitive":[15],"information.":[16],"detection":[18],"mechanisms":[19],"using":[20],"various":[21],"techniques":[22],"have":[23],"been":[24],"developed.":[25],"Our":[26],"hypothesis":[27],"that":[29,83],"create":[31],"fake":[32],"websites":[33],"with":[34,113],"as":[35,38,139],"little":[36],"possible":[39],"webpage,":[42],"makes":[44],"it":[45],"difficult":[46],"for":[47,107],"content-":[48],"and":[49,115,126],"visual":[50],"similarity-based":[51],"detections":[52],"by":[53],"analyzing":[54],"the":[55,64,90,102,123,131,136],"webpage":[56],"content.":[57],"To":[58],"overcome":[59],"this,":[60],"we":[61,81],"focus":[62],"on":[63,122,130],"use":[65],"Uniform":[67],"Resource":[68],"Locators":[69],"(URLs)":[70],"detect":[72],"phishing.":[73],"Since":[74],"previous":[75],"work":[76],"extracts":[77],"specific":[78],"special-character":[79],"features,":[80],"assume":[82],"non-alphanumeric":[84],"(NAN)":[85],"character":[86],"distributions":[87],"highly":[88],"impact":[89],"performance":[91],"URL-based":[93,108],"detection.":[94,110],"We":[95],"hence":[96],"propose":[97],"new":[99],"feature":[100],"called":[101],"entropy":[103],"NAN":[105],"characters":[106],"phishing":[109],"Experimental":[111],"evaluation":[112],"balanced":[114,124],"imbalanced":[116,132],"datasets":[117],"shows":[118],"96%":[119],"ROC":[120,128,137],"AUC":[121,129,138],"dataset":[125],"89%":[127],"dataset,":[133],"increases":[135],"5":[140],"6%":[142],"from":[143],"without":[144],"adopting":[145],"our":[146],"proposed":[147],"feature.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
