{"id":"https://openalex.org/W2094603098","doi":"https://doi.org/10.1145/2684793.2684803","title":"Clustering Spam Campaigns with Fuzzy Hashing","display_name":"Clustering Spam Campaigns with Fuzzy Hashing","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2094603098","doi":"https://doi.org/10.1145/2684793.2684803","mag":"2094603098"},"language":"en","primary_location":{"id":"doi:10.1145/2684793.2684803","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2684793.2684803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AINTEC 2014 on Asian Internet Engineering Conference - AINTEC '14","raw_type":"proceedings-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/A5102205844","display_name":"Chen Jianxing","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jianxing Chen","raw_affiliation_strings":["Saarland University","saarland university"],"affiliations":[{"raw_affiliation_string":"Saarland University","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"saarland university","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069426959","display_name":"Romain Fontugne","orcid":"https://orcid.org/0000-0002-9816-5625"},"institutions":[{"id":"https://openalex.org/I4387152154","display_name":"Japanese-French Laboratory for Informatics","ror":"https://ror.org/007xn7v02","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I203951103","https://openalex.org/I39804081","https://openalex.org/I4387152154","https://openalex.org/I74801974"]},{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Romain Fontugne","raw_affiliation_strings":["National Institute of Informatics and Japanese-French Laboratory for Informatics"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics and Japanese-French Laboratory for Informatics","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I4387152154"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083980382","display_name":"Akira Kato","orcid":"https://orcid.org/0000-0002-9083-1443"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Kato","raw_affiliation_strings":["Keio University","Keio Univ"],"affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]},{"raw_affiliation_string":"Keio Univ","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101814201","display_name":"Kensuke Fukuda","orcid":"https://orcid.org/0000-0001-8372-2807"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kensuke Fukuda","raw_affiliation_strings":["National Institute of Informatics","National Institute of Informatics,"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics,","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102205844"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":2.4727,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.91571096,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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":0.9998999834060669,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9864000082015991,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9825000166893005,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.9372560381889343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.781670331954956},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6285205483436584},{"id":"https://openalex.org/keywords/forum-spam","display_name":"Forum spam","score":0.608138918876648},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5720731616020203},{"id":"https://openalex.org/keywords/botnet","display_name":"Botnet","score":0.5592997074127197},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5491528511047363},{"id":"https://openalex.org/keywords/obfuscation","display_name":"Obfuscation","score":0.5436347126960754},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5077391862869263},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.49540770053863525},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.44200417399406433},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4294319450855255},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4043494164943695},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.29757240414619446},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2922697067260742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25064849853515625},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1380082368850708}],"concepts":[{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.9372560381889343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781670331954956},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6285205483436584},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.608138918876648},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5720731616020203},{"id":"https://openalex.org/C22735295","wikidata":"https://www.wikidata.org/wiki/Q317671","display_name":"Botnet","level":3,"score":0.5592997074127197},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5491528511047363},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.5436347126960754},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5077391862869263},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.49540770053863525},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.44200417399406433},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4294319450855255},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4043494164943695},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.29757240414619446},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2922697067260742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25064849853515625},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1380082368850708},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2684793.2684803","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2684793.2684803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AINTEC 2014 on Asian Internet Engineering Conference - AINTEC '14","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":12,"referenced_works":["https://openalex.org/W1655456","https://openalex.org/W1498592591","https://openalex.org/W1550514379","https://openalex.org/W1593657937","https://openalex.org/W2002537105","https://openalex.org/W2102283838","https://openalex.org/W2113344319","https://openalex.org/W2134385885","https://openalex.org/W2168154523","https://openalex.org/W4233802931","https://openalex.org/W6600068801","https://openalex.org/W6635272604"],"related_works":["https://openalex.org/W2018000323","https://openalex.org/W2095720311","https://openalex.org/W2403960249","https://openalex.org/W2898345088","https://openalex.org/W2080521416","https://openalex.org/W1937320931","https://openalex.org/W1502194589","https://openalex.org/W1965586806","https://openalex.org/W4293384513","https://openalex.org/W1481472066"],"abstract_inverted_index":{"Identifying":[0],"spamming":[1],"botnets":[2,22],"is":[3,23,118],"essential":[4],"to":[5,19,46,67,82],"defeat":[6],"spammers":[7],"and":[8,140],"reduce":[9],"the":[10,24,47,74,95,115,122,125,136,141],"harm":[11],"caused":[12],"by":[13,120],"spam":[14,27,69,76,110,138],"emails.":[15,111],"The":[16,112],"first":[17],"step":[18],"uncover":[20],"these":[21],"identification":[25],"of":[26,49,107,114,124,135],"campaigns.":[28],"Simple":[29],"methods":[30],"looking":[31],"for":[32],"common":[33,71],"identifiers":[34,91],"in":[35],"emails,":[36],"such":[37],"as":[38],"URL":[39,53],"or":[40],"email":[41],"addresses,":[42],"are":[43,92],"inefficient":[44],"due":[45],"emergence":[48],"obfuscation":[50],"techniques":[51],"like":[52],"shortening.":[54],"In":[55],"this":[56],"paper":[57],"we":[58,98,131],"propose":[59],"a":[60,100],"new":[61],"method":[62,97,117],"based":[63],"on":[64],"fuzzy":[65],"hashing":[66,79],"cluster":[68],"with":[70,85],"goals":[72],"into":[73],"same":[75],"campaign.":[77],"Fuzzy":[78],"allows":[80],"us":[81],"identify":[83],"emails":[84],"similar":[86],"contents":[87],"even":[88],"though":[89],"usual":[90],"obfuscated.":[93],"Using":[94],"proposed":[96,116],"process":[99],"three":[101],"year":[102],"long":[103],"dataset":[104],"that":[105],"consists":[106],"540":[108],"thousand":[109],"efficiency":[113],"assessed":[119],"inspecting":[121],"characteristics":[123],"top":[126],"100":[127],"campaigns":[128,139],"found.":[129],"Finally,":[130],"present":[132],"typical":[133],"behaviors":[134],"uncovered":[137],"corresponding":[142],"botnets.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
