{"id":"https://openalex.org/W2078799390","doi":"https://doi.org/10.1109/infcomw.2014.6849281","title":"Hashdoop: A MapReduce framework for network anomaly detection","display_name":"Hashdoop: A MapReduce framework for network anomaly detection","publication_year":2014,"publication_date":"2014-04-01","ids":{"openalex":"https://openalex.org/W2078799390","doi":"https://doi.org/10.1109/infcomw.2014.6849281","mag":"2078799390"},"language":"en","primary_location":{"id":"doi:10.1109/infcomw.2014.6849281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcomw.2014.6849281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","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/A5069426959","display_name":"Romain Fontugne","orcid":"https://orcid.org/0000-0002-9816-5625"},"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":"Romain Fontugne","raw_affiliation_strings":["National Institute of Informatics","Nat. Inst. of Inf., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Nat. Inst. of Inf., Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078574033","display_name":"Johan Mazel","orcid":"https://orcid.org/0009-0002-0222-6794"},"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":"Johan Mazel","raw_affiliation_strings":["National Institute of Informatics","Nat. Inst. of Inf., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Nat. Inst. of Inf., Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"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","Nat. Inst. of Inf., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Nat. Inst. of Inf., Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.3571,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.98100685,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"494","last_page":"499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":1.0,"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"}},{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9997000098228455,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9993000030517578,"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/anomaly-detection","display_name":"Anomaly detection","score":0.8567224740982056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7655943632125854},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6127537488937378},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5888113379478455},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5871589183807373},{"id":"https://openalex.org/keywords/internet-traffic","display_name":"Internet traffic","score":0.5612326264381409},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5055854320526123},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.46989676356315613},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4650047719478607},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4623855650424957},{"id":"https://openalex.org/keywords/traffic-generation-model","display_name":"Traffic generation model","score":0.4524790048599243},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.41520655155181885},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4004942774772644},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3585311770439148},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1662212610244751},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0855470597743988},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07643163204193115},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07349202036857605}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.8567224740982056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655943632125854},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6127537488937378},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5888113379478455},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5871589183807373},{"id":"https://openalex.org/C63969886","wikidata":"https://www.wikidata.org/wiki/Q3536440","display_name":"Internet traffic","level":3,"score":0.5612326264381409},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5055854320526123},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.46989676356315613},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4650047719478607},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4623855650424957},{"id":"https://openalex.org/C176715033","wikidata":"https://www.wikidata.org/wiki/Q2080768","display_name":"Traffic generation model","level":2,"score":0.4524790048599243},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.41520655155181885},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4004942774772644},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3585311770439148},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1662212610244751},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0855470597743988},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07643163204193115},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07349202036857605},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infcomw.2014.6849281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcomw.2014.6849281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W16186195","https://openalex.org/W1598064945","https://openalex.org/W1858168446","https://openalex.org/W2040333627","https://openalex.org/W2055434856","https://openalex.org/W2065202763","https://openalex.org/W2088134864","https://openalex.org/W2108673751","https://openalex.org/W2120664731","https://openalex.org/W2127084909","https://openalex.org/W2150517569","https://openalex.org/W2155915275","https://openalex.org/W2160615184","https://openalex.org/W2164210932","https://openalex.org/W2173213060","https://openalex.org/W2215904967","https://openalex.org/W2995564009","https://openalex.org/W3138598418","https://openalex.org/W6600634475","https://openalex.org/W6639080731","https://openalex.org/W6683352490"],"related_works":["https://openalex.org/W2806741695","https://openalex.org/W4290647774","https://openalex.org/W3189286258","https://openalex.org/W3207797160","https://openalex.org/W3210364259","https://openalex.org/W4300558037","https://openalex.org/W2667207928","https://openalex.org/W2912112202","https://openalex.org/W4377864969","https://openalex.org/W3120251014"],"abstract_inverted_index":{"Anomaly":[0],"detection":[1,180],"is":[2],"essential":[3],"for":[4,52,181],"preventing":[5],"network":[6,11,24,74,136],"outages":[7],"and":[8,91,98,148,158],"maintaining":[9],"the":[10,18,45,61,83,166,169,182,189,199],"resources":[12],"available.":[13],"However,":[14],"to":[15,30,72,85,123,134],"cope":[16],"with":[17,119,144,172],"increasing":[19],"growth":[20],"of":[21,47,55,130,140,151,168,175],"Internet":[22,57,152],"traffic,":[23,32],"anomaly":[25,92,146],"detectors":[26,93,147,191],"are":[27,142],"only":[28],"exposed":[29],"sampled":[31],"so":[33],"harmful":[34],"traffic":[35,75,100,118,125,154],"may":[36],"avoid":[37],"detector":[38,171],"examination.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"investigate":[44],"benefits":[46,139],"recent":[48],"distributed":[49,131],"computing":[50,132],"approaches":[51],"real-time":[53,179],"analysis":[54],"non-sampled":[56],"traffic.":[58,109,201],"Focusing":[59],"on":[60],"MapReduce":[62,81,114],"model,":[63],"our":[64],"study":[65],"uncovers":[66],"a":[67,113,120,161,173],"fundamental":[68],"difficulty":[69],"in":[70],"order":[71],"detect":[73,135],"anomalies":[76,196],"by":[77,197],"using":[78],"Hadoop.":[79],"Since":[80],"requires":[82],"dataset":[84],"be":[86,105],"divided":[87],"into":[88],"small":[89],"splits":[90,117,194],"compute":[94],"statistics":[95],"from":[96],"spatial":[97],"temporal":[99],"structures,":[101],"special":[102],"care":[103],"should":[104],"taken":[106],"when":[107],"splitting":[108],"We":[110],"propose":[111],"Hashdoop,":[112],"framework":[115],"that":[116],"hash":[121],"function":[122],"preserve":[124],"structures":[126],"and,":[127],"hence,":[128],"profits":[129],"infrastructures":[133],"anomalies.":[137],"The":[138],"Hashdoop":[141,164,186],"evaluated":[143],"two":[145],"fifteen":[149],"traces":[150],"backbone":[153],"captured":[155],"between":[156],"2001":[157],"2013.":[159],"Using":[160],"6-node":[162],"cluster":[163],"increased":[165],"throughput":[167],"slowest":[170],"speed-up":[174],"15;":[176],"thus,":[177],"enabling":[178],"largest":[183],"analyzed":[184],"traces.":[185],"also":[187],"improved":[188],"overall":[190],"accuracy":[192],"as":[193],"emphasized":[195],"reducing":[198],"surrounding":[200]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
