{"id":"https://openalex.org/W1501893885","doi":"https://doi.org/10.1109/infocom.2015.7218634","title":"Do we need a perfect ground-truth for benchmarking Internet traffic classifiers?","display_name":"Do we need a perfect ground-truth for benchmarking Internet traffic classifiers?","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1501893885","doi":"https://doi.org/10.1109/infocom.2015.7218634","mag":"1501893885"},"language":"en","primary_location":{"id":"doi:10.1109/infocom.2015.7218634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom.2015.7218634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computer Communications (INFOCOM)","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/A5024449512","display_name":"M. Ros\u00e1rio Oliveira","orcid":"https://orcid.org/0000-0002-5234-3713"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"M. Rosario Oliveira","raw_affiliation_strings":["CEMAT and Departmento de Matem\u00a1tica, Universidade de Lisboa, Portugal","CEMAT and Departmento de Matem\u00e1tica, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"CEMAT and Departmento de Matem\u00a1tica, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]},{"raw_affiliation_string":"CEMAT and Departmento de Matem\u00e1tica, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022026306","display_name":"Jo\u00e3o Carvalho das Neves","orcid":"https://orcid.org/0000-0003-3780-8823"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joao Neves","raw_affiliation_strings":["CEMAT and Departmento de Matem\u00a1tica, Universidade de Lisboa, Portugal","CEMAT and Departmento de Matem\u00e1tica, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"CEMAT and Departmento de Matem\u00a1tica, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]},{"raw_affiliation_string":"CEMAT and Departmento de Matem\u00e1tica, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018484137","display_name":"Rui Valadas","orcid":"https://orcid.org/0000-0002-7420-4386"},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Rui Valadas","raw_affiliation_strings":["DEEC and Instituto de Telecomunica\u00e7\u00f5es, Universidade de Lisboa, Portugal","DEEC and Institute de Telecomunica\u00e7\u00f5es, Institute Superior T\u00e9cnico, Universidade de Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"DEEC and Instituto de Telecomunica\u00e7\u00f5es, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I141596103"]},{"raw_affiliation_string":"DEEC and Institute de Telecomunica\u00e7\u00f5es, Institute Superior T\u00e9cnico, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012996391","display_name":"Paulo Salvador","orcid":"https://orcid.org/0000-0001-6832-9417"},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]},{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Paulo Salvador","raw_affiliation_strings":["DETI and Instituto de Telecomunica\u00e7\u00f5es, Universidade de Aveiro, Portugal","DETI and Institute de Telecomunica\u00e7\u00f5es, Universidade de Aveiro, Portugal"],"affiliations":[{"raw_affiliation_string":"DETI and Instituto de Telecomunica\u00e7\u00f5es, Universidade de Aveiro, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I60858718"]},{"raw_affiliation_string":"DETI and Institute de Telecomunica\u00e7\u00f5es, Universidade de Aveiro, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I60858718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024449512"],"corresponding_institution_ids":["https://openalex.org/I141596103"],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74711707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2452","last_page":"2460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":1.0,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9998999834060669,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/ground-truth","display_name":"Ground truth","score":0.8305617570877075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7759135365486145},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6691985130310059},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6051158308982849},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5958492755889893},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5702322125434875},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5273067951202393},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42430877685546875},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41481342911720276}],"concepts":[{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.8305617570877075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7759135365486145},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6691985130310059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6051158308982849},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5958492755889893},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5702322125434875},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5273067951202393},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42430877685546875},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41481342911720276},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom.2015.7218634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom.2015.7218634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computer Communications (INFOCOM)","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":37,"referenced_works":["https://openalex.org/W1952056635","https://openalex.org/W1963821364","https://openalex.org/W1985987493","https://openalex.org/W2010716466","https://openalex.org/W2011628134","https://openalex.org/W2012095206","https://openalex.org/W2021891366","https://openalex.org/W2027355980","https://openalex.org/W2027664152","https://openalex.org/W2055261595","https://openalex.org/W2061892850","https://openalex.org/W2061921865","https://openalex.org/W2087405576","https://openalex.org/W2087922528","https://openalex.org/W2096118443","https://openalex.org/W2105934885","https://openalex.org/W2115379950","https://openalex.org/W2118931532","https://openalex.org/W2121856130","https://openalex.org/W2122226347","https://openalex.org/W2127589913","https://openalex.org/W2141177935","https://openalex.org/W2149600645","https://openalex.org/W2150779517","https://openalex.org/W2156916299","https://openalex.org/W2161062125","https://openalex.org/W2164210932","https://openalex.org/W2169623711","https://openalex.org/W2554987453","https://openalex.org/W3009746682","https://openalex.org/W3150719513","https://openalex.org/W3160447194","https://openalex.org/W4236506014","https://openalex.org/W4255738146","https://openalex.org/W4292494783","https://openalex.org/W4301689241","https://openalex.org/W6677197789"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W4399363378","https://openalex.org/W4323323165","https://openalex.org/W2745033168"],"abstract_inverted_index":{"The":[0,129,147],"classification":[1],"of":[2,18,58,63,70,80,122,163],"Internet":[3,19,71,142,174],"traffic":[4,175],"using":[5,133],"supervised":[6],"or":[7,48],"semi-supervised":[8],"statistical":[9],"learning":[10],"techniques,":[11],"both":[12,32,94],"for":[13],"anomaly":[14],"detection":[15],"and":[16,37,66,87,96,144,166],"identification":[17],"applications,":[20],"has":[21],"been":[22],"impaired":[23],"by":[24,119],"difficulties":[25],"in":[26],"obtaining":[27],"a":[28,111,134],"reliable":[29],"ground-truth,":[30],"required":[31],"to":[33,38,51,54,171],"train":[34],"the":[35,55,61,67,78,81,85,105,126,139],"classifier":[36,86],"evaluate":[39],"its":[40,89],"performance.":[41],"A":[42],"perfect":[43],"ground-truth":[44,82,100,164,181],"is":[45,131,182],"increasingly":[46],"difficult,":[47],"sometimes":[49],"impossible,":[50],"obtain":[52],"due":[53],"growing":[56],"percentage":[57],"cyphered":[59],"traffic,":[60],"sophistication":[62],"network":[64,145],"attacks,":[65],"constant":[68],"updates":[69],"applications.":[72],"In":[73],"this":[74,117],"paper,":[75],"we":[76],"study":[77],"impact":[79],"on":[83],"training":[84],"estimating":[88],"performance":[90,106,158],"measures.":[91],"We":[92,108],"show":[93,149],"theoretically":[95],"through":[97],"simulation":[98],"that":[99,115,137,150],"imperfections":[101],"can":[102,167],"severely":[103],"bias":[104],"estimates.":[107],"then":[109],"propose":[110],"latent":[112,152],"class":[113,153],"model":[114,130,154],"overcomes":[116],"problem":[118],"combining":[120],"estimates":[121,159],"several":[123],"classifiers":[124,176],"over":[125],"same":[127],"dataset.":[128],"evaluated":[132],"high-quality":[135],"dataset":[136],"includes":[138],"most":[140],"representative":[141],"applications":[143],"attacks.":[146],"results":[148],"our":[151],"produces":[155],"very":[156],"good":[157],"under":[160],"mild":[161],"levels":[162],"imperfection,":[165],"thus":[168],"be":[169],"used":[170],"correctly":[172],"benchmark":[173],"when":[177],"only":[178],"an":[179],"imperfect":[180],"available.":[183]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}