{"id":"https://openalex.org/W2018175892","doi":"https://doi.org/10.1145/2046707.2046742","title":"BitShred","display_name":"BitShred","publication_year":2011,"publication_date":"2011-10-17","ids":{"openalex":"https://openalex.org/W2018175892","doi":"https://doi.org/10.1145/2046707.2046742","mag":"2018175892"},"language":"en","primary_location":{"id":"doi:10.1145/2046707.2046742","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2046707.2046742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Computer and communications security","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/A5037719518","display_name":"Jiyong Jang","orcid":"https://orcid.org/0000-0001-8111-2503"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiyong Jang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016565332","display_name":"David Brumley","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Brumley","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079497548","display_name":"Shobha Venkataraman","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shobha Venkataraman","raw_affiliation_strings":["AT&T Labs - Research, Florham Park, NJ, USA","AT&T Labs---Research, Florham Park, NJ, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs---Research, Florham Park, NJ, USA#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037719518"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":19.9466,"has_fulltext":false,"cited_by_count":251,"citation_normalized_percentile":{"value":0.99660197,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"309","last_page":"320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9955000281333923,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9743000268936157,"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/malware","display_name":"Malware","score":0.9353543519973755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8252095580101013},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6762850880622864},{"id":"https://openalex.org/keywords/malware-analysis","display_name":"Malware analysis","score":0.6750304698944092},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6349416971206665},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5864555239677429},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.586248517036438},{"id":"https://openalex.org/keywords/triage","display_name":"Triage","score":0.5010721683502197},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4495049715042114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3238504230976105},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.16096198558807373},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1422118842601776}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.9353543519973755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252095580101013},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6762850880622864},{"id":"https://openalex.org/C2779395397","wikidata":"https://www.wikidata.org/wiki/Q15731404","display_name":"Malware analysis","level":3,"score":0.6750304698944092},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6349416971206665},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5864555239677429},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.586248517036438},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.5010721683502197},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4495049715042114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3238504230976105},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.16096198558807373},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1422118842601776},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C194828623","wikidata":"https://www.wikidata.org/wiki/Q2861470","display_name":"Emergency medicine","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2046707.2046742","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2046707.2046742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Computer and communications security","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W113396932","https://openalex.org/W1508225132","https://openalex.org/W1562646198","https://openalex.org/W1591082683","https://openalex.org/W1827212170","https://openalex.org/W1910686388","https://openalex.org/W1993284846","https://openalex.org/W2038276547","https://openalex.org/W2068211976","https://openalex.org/W2070996757","https://openalex.org/W2096921767","https://openalex.org/W2111295912","https://openalex.org/W2111537739","https://openalex.org/W2112490010","https://openalex.org/W2117030266","https://openalex.org/W2121749752","https://openalex.org/W2126734536","https://openalex.org/W2127164716","https://openalex.org/W2128389850","https://openalex.org/W2132832062","https://openalex.org/W2132874238","https://openalex.org/W2138644293","https://openalex.org/W2140807364","https://openalex.org/W2141806397","https://openalex.org/W2145056020","https://openalex.org/W2151300580","https://openalex.org/W2170770919","https://openalex.org/W2171500543","https://openalex.org/W2173213060","https://openalex.org/W2951154109","https://openalex.org/W4238996902","https://openalex.org/W6639864006","https://openalex.org/W6677103492","https://openalex.org/W6685115719"],"related_works":["https://openalex.org/W2768892939","https://openalex.org/W2469507153","https://openalex.org/W2008790809","https://openalex.org/W2134874482","https://openalex.org/W4285507391","https://openalex.org/W2397240470","https://openalex.org/W2602767565","https://openalex.org/W170652726","https://openalex.org/W2883822334","https://openalex.org/W3164408430"],"abstract_inverted_index":{"The":[0,64],"sheer":[1],"volume":[2],"of":[3,142],"new":[4],"malware":[5,23,29,33,48,84,96,111],"found":[6],"each":[7],"day":[8],"is":[9,30,34,69],"growing":[10],"at":[11],"an":[12],"exponential":[13],"pace.":[14],"This":[15],"growth":[16],"has":[17],"created":[18],"a":[19,44,126,139],"need":[20],"for":[21,46,54],"automatic":[22],"triage":[24,112],"techniques":[25],"that":[26,80,106],"determine":[27],"what":[28,32],"similar,":[31],"unique,":[35],"and":[36,51,53,59,98,118,144],"why.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"present":[42],"BitShred,":[43,143],"system":[45],"large-scale":[47],"similarity":[49],"analysis":[50],"clustering,":[52],"automatically":[55],"uncovering":[56],"semantic":[57],"inter-":[58],"intra-family":[60],"relationships":[61],"within":[62,147],"clusters.":[63],"key":[65],"idea":[66],"behind":[67],"BitShred":[68,107],"using":[70,100],"feature":[71,78],"hashing":[72,87],"to":[73,91,116,121,133],"dramatically":[74],"reduce":[75],"the":[76,148],"high-dimensional":[77],"spaces":[79],"are":[81],"common":[82],"in":[83],"analysis.":[85],"Feature":[86],"also":[88,137],"allows":[89],"us":[90],"mine":[92],"correlated":[93],"features":[94],"between":[95],"families":[97],"samples":[99],"co-clustering":[101],"techniques.":[102],"Our":[103],"evaluation":[104],"shows":[105],"speeds":[108],"up":[109,115,120],"typical":[110],"tasks":[113],"by":[114],"2,365x":[117],"uses":[119],"82x":[122],"less":[123],"memory":[124],"on":[125],"single":[127],"CPU,":[128],"all":[129],"with":[130],"comparable":[131],"accuracy":[132],"previous":[134],"approaches.":[135],"We":[136],"develop":[138],"parallelized":[140],"version":[141],"demonstrate":[145],"scalability":[146],"Hadoop":[149],"framework.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":33},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":33},{"year":2012,"cited_by_count":12}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2016-06-24T00:00:00"}