{"id":"https://openalex.org/W1976242982","doi":"https://doi.org/10.1109/infocom.2014.6848073","title":"ProWord: An unsupervised approach to protocol feature word extraction","display_name":"ProWord: An unsupervised approach to protocol feature word extraction","publication_year":2014,"publication_date":"2014-04-01","ids":{"openalex":"https://openalex.org/W1976242982","doi":"https://doi.org/10.1109/infocom.2014.6848073","mag":"1976242982"},"language":"en","primary_location":{"id":"doi:10.1109/infocom.2014.6848073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom.2014.6848073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2014 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},"type":"conference-paper","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/A5040980735","display_name":"Zhuo Zhang","orcid":"https://orcid.org/0000-0001-7286-4535"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Zhang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences (CAS), China","Inst. of Comput. Technol., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences (CAS), China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Inst. of Comput. Technol., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370021","display_name":"Zhibin Zhang","orcid":"https://orcid.org/0000-0003-2090-7999"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibin Zhang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences (CAS), China","Inst. of Comput. Technol., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences (CAS), China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Inst. of Comput. Technol., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012129385","display_name":"Patrick P. C. Lee","orcid":"https://orcid.org/0000-0002-4501-4364"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Patrick P. C. Lee","raw_affiliation_strings":["Chinese University of Hong Kong, New Territories, HK","Chinese Univ. of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, New Territories, HK","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese Univ. of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101690888","display_name":"Yunjie Liu","orcid":"https://orcid.org/0000-0002-9312-7523"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yunjie Liu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China","Beijing Univ. Of Posts & Telecommun., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Beijing Univ. Of Posts & Telecommun., Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030689390","display_name":"Gaogang Xie","orcid":"https://orcid.org/0000-0003-4964-1135"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaogang Xie","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, China","Inst. of Comput. Technol., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Inst. of Comput. Technol., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1393","last_page":"1401"},"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":0.9998000264167786,"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":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.8166173696517944},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5980428457260132},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5647268295288086},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5219656825065613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5214797258377075},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5213438272476196},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.5071988105773926},{"id":"https://openalex.org/keywords/payload","display_name":"Payload (computing)","score":0.49795103073120117},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4882352650165558},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4875780940055847},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.4780048429965973},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4198233187198639},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.40688616037368774},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34991857409477234},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.1776106059551239},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09392902255058289}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166173696517944},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5980428457260132},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5647268295288086},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5219656825065613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5214797258377075},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5213438272476196},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5071988105773926},{"id":"https://openalex.org/C134066672","wikidata":"https://www.wikidata.org/wiki/Q1424639","display_name":"Payload (computing)","level":3,"score":0.49795103073120117},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4882352650165558},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4875780940055847},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.4780048429965973},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4198233187198639},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.40688616037368774},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34991857409477234},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.1776106059551239},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09392902255058289},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","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},{"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/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/infocom.2014.6848073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom.2014.6848073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2014 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.667.9146","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.667.9146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://fi.ict.ac.cn/uploads/PublicationsAmpTalks/2014_ProWord+An+Unsupervised+Approach+to+Protocol+Feature+Word+Extraction.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W38765094","https://openalex.org/W139562302","https://openalex.org/W191098608","https://openalex.org/W1504161274","https://openalex.org/W1526685788","https://openalex.org/W1538375546","https://openalex.org/W1583098994","https://openalex.org/W1964267679","https://openalex.org/W2012095206","https://openalex.org/W2056325176","https://openalex.org/W2069980026","https://openalex.org/W2110890874","https://openalex.org/W2120948237","https://openalex.org/W2134557008","https://openalex.org/W2137432096","https://openalex.org/W2137831706","https://openalex.org/W2140542782","https://openalex.org/W2149600645","https://openalex.org/W2150779517","https://openalex.org/W2152063140","https://openalex.org/W2159715570","https://openalex.org/W4240896209","https://openalex.org/W6601496405","https://openalex.org/W6607784307","https://openalex.org/W6632460521","https://openalex.org/W6634779276","https://openalex.org/W6680261719"],"related_works":["https://openalex.org/W1535080110","https://openalex.org/W306312984","https://openalex.org/W857189463","https://openalex.org/W4288094128","https://openalex.org/W2979675132","https://openalex.org/W2790520092","https://openalex.org/W1574986946","https://openalex.org/W2122429665","https://openalex.org/W2092384028","https://openalex.org/W3015337097"],"abstract_inverted_index":{"Protocol":[0],"feature":[1,43,86,144,168,190],"words":[2,44,87,118,159,191],"are":[3,62],"byte":[4],"subsequences":[5],"within":[6],"traffic":[7,47,89,181],"payload":[8,72,115],"that":[9,83,112,138,149,185],"can":[10,151],"distinguish":[11],"application":[12],"protocols,":[13],"and":[14,32,39,61,123,160,173,194],"they":[15],"form":[16],"the":[17,66,71,106,157,162],"building":[18],"blocks":[19],"of":[20,23,70,142],"many":[21],"constructions":[22],"deep":[24],"packet":[25],"analysis":[26],"rules":[27],"in":[28,64],"network":[29,46],"management,":[30],"measurement,":[31],"security":[33],"systems.":[34],"However,":[35],"how":[36],"to":[37,120],"systematically":[38],"efficiently":[40],"extract":[41],"protocol":[42,85,167,189],"from":[45,88],"remains":[48],"a":[49,135],"challenging":[50],"issue.":[51],"Existing":[52],"n-gram":[53,130,175],"approaches":[54,176],"simply":[55],"break":[56,114],"pay-load":[57],"into":[58,116],"equal-length":[59],"pieces":[60],"ineffective":[63],"capturing":[65],"hidden":[67],"statistical":[68],"structure":[69,155],"content.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,98,113,133,150],"propose":[78,99,134],"ProWord,":[79],"an":[80,100,153],"unsupervised":[81,101],"approach":[82],"extracts":[84],"traces.":[90,182],"ProWord":[91,172,186],"builds":[92],"on":[93,105,156,179],"two":[94],"nontrivial":[95],"algorithms.":[96],"First,":[97],"segmentation":[102,127],"algorithm":[103,137],"based":[104],"modified":[107],"Voting":[108],"Experts":[109],"algorithm,":[110],"such":[111,148],"candidate":[117,158],"according":[119],"entropy":[121],"information":[122],"provide":[124],"more":[125,192],"accurate":[126],"than":[128],"existing":[129,174],"approaches.":[131],"Second,":[132],"ranking":[136],"incorporates":[139],"different":[140],"types":[141],"well-known":[143],"word":[145],"retrieval":[146],"heuristics,":[147],"build":[152],"ordered":[154],"select":[161],"highest":[163],"ranked":[164],"ones":[165],"as":[166],"words.":[169],"We":[170,183],"compare":[171],"via":[177],"evaluation":[178],"real-world":[180],"show":[184],"captures":[187],"true":[188],"accurately":[193],"performs":[195],"significantly":[196],"faster.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}