{"id":"https://openalex.org/W2534071615","doi":"https://doi.org/10.1145/2983323.2983841","title":"Scalable Local-Recoding Anonymization using Locality Sensitive Hashing for Big Data Privacy Preservation","display_name":"Scalable Local-Recoding Anonymization using Locality Sensitive Hashing for Big Data Privacy Preservation","publication_year":2016,"publication_date":"2016-10-24","ids":{"openalex":"https://openalex.org/W2534071615","doi":"https://doi.org/10.1145/2983323.2983841","mag":"2534071615"},"language":"en","primary_location":{"id":"doi:10.1145/2983323.2983841","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","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/A5076120553","display_name":"Xuyun Zhang","orcid":"https://orcid.org/0000-0001-7353-4159"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Xuyun Zhang","raw_affiliation_strings":["The University of Auckland, Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076014464","display_name":"Christopher Leckie","orcid":"https://orcid.org/0000-0002-4388-0517"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christopher Leckie","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038791483","display_name":"Wanchun Dou","orcid":"https://orcid.org/0000-0003-4833-2023"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanchun Dou","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101808353","display_name":"Jinjun Chen","orcid":"https://orcid.org/0000-0003-1677-9525"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jinjun Chen","raw_affiliation_strings":["University of Technology, Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology, Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069895484","display_name":"Kotagiri Ramamohanarao","orcid":"https://orcid.org/0000-0003-3304-9268"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ramamohanarao Kotagiri","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088166627","display_name":"Zoran Sal\u010di\u0107","orcid":"https://orcid.org/0000-0001-7714-9848"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Zoran Salcic","raw_affiliation_strings":["The University of Auckland, Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076120553"],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":null,"apc_paid":null,"fwci":4.2847,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94964307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1793","last_page":"1802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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/T10237","display_name":"Cryptography and Data Security","score":0.9959999918937683,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.965399980545044,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8443912267684937},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7884190082550049},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6970946788787842},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6943036913871765},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6138396263122559},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5388872623443604},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4933251440525055},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.46716320514678955},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4642273783683777},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.45284712314605713},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.43917813897132874},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.351982057094574},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3328855633735657},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.2837100625038147},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27382540702819824},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.18427586555480957},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1520383656024933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13226497173309326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8443912267684937},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7884190082550049},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6970946788787842},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6943036913871765},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6138396263122559},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5388872623443604},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4933251440525055},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.46716320514678955},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4642273783683777},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45284712314605713},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.43917813897132874},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.351982057094574},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3328855633735657},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2837100625038147},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27382540702819824},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.18427586555480957},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1520383656024933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13226497173309326},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2983323.2983841","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:researchbank.swinburne.edu.au:dcd1ab2c-f9c9-46f6-b3da-328a898d762a/1","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.3/436599","pdf_url":null,"source":{"id":"https://openalex.org/S4306401157","display_name":"Swinburne Research Bank (Swinburne University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I57093077","host_organization_name":"Swinburne University of Technology","host_organization_lineage":["https://openalex.org/I57093077"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"25th ACM International on Conference on Information and Knowledge Management (CIKM '16), Indianapolis, Indiana, United States, 24 - 28 October, 2016 , pp. 1793-1802","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4722731998","display_name":null,"funder_award_id":"91318301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1967831627","https://openalex.org/W1979005794","https://openalex.org/W1989135185","https://openalex.org/W1991800036","https://openalex.org/W1992286709","https://openalex.org/W2005991660","https://openalex.org/W2026705124","https://openalex.org/W2034616054","https://openalex.org/W2038688050","https://openalex.org/W2038873345","https://openalex.org/W2040263621","https://openalex.org/W2049758109","https://openalex.org/W2059900053","https://openalex.org/W2069845605","https://openalex.org/W2081416313","https://openalex.org/W2099519519","https://openalex.org/W2118944554","https://openalex.org/W2142291269","https://openalex.org/W2142406320","https://openalex.org/W2145065594","https://openalex.org/W2147717514","https://openalex.org/W2157355837","https://openalex.org/W2159024459","https://openalex.org/W2164649498","https://openalex.org/W2164812149","https://openalex.org/W2911978475","https://openalex.org/W3023203852"],"related_works":["https://openalex.org/W2227807207","https://openalex.org/W2370014100","https://openalex.org/W3137108924","https://openalex.org/W1852009617","https://openalex.org/W4287264924","https://openalex.org/W2042819006","https://openalex.org/W2170165007","https://openalex.org/W1979110442","https://openalex.org/W2156660460","https://openalex.org/W2362866566"],"abstract_inverted_index":{"While":[0],"cloud":[1,20,41,93],"computing":[2,21],"has":[3],"become":[4],"an":[5],"attractive":[6],"platform":[7],"for":[8,42,47,76,109,137],"supporting":[9],"data":[10,48,54,78,119],"intensive":[11],"applications,":[12],"a":[13,85,102,162],"major":[14],"obstacle":[15],"to":[16,37,52,89,113,131,141],"the":[17,30,40,115,124,159,179],"adoption":[18],"of":[19,161,183,188],"in":[22,39,92],"sectors":[23],"such":[24],"as":[25],"health":[26],"and":[27,181],"defense":[28],"is":[29,51,107],"privacy":[31,49],"risk":[32],"associated":[33],"with":[34,111,123,139],"releasing":[35],"datasets":[36,133,172],"third-parties":[38],"analysis.":[43],"A":[44],"widely-adopted":[45],"technique":[46],"preservation":[50],"anonymize":[53,155],"via":[55],"local":[56],"recoding.":[57],"However,":[58],"most":[59],"existing":[60,191],"local-recoding":[61,90,184],"techniques":[62],"are":[63],"either":[64],"serial":[65],"or":[66],"distributed":[67],"without":[68],"directly":[69],"optimizing":[70],"scalability,":[71],"thus":[72],"rendering":[73],"them":[74],"unsuitable":[75],"big":[77],"applications.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83,153],"propose":[84],"highly":[86],"scalable":[87],"approach":[88,176],"anonymization":[91,185],"computing,":[94],"based":[95],"on":[96,170],"Locality":[97],"Sensitive":[98],"Hashing":[99],"(LSH).":[100],"Specifically,":[101],"novel":[103],"semantic":[104],"distance":[105],"metric":[106],"presented":[108],"use":[110,138,160],"LSH":[112,122],"measure":[114],"similarity":[116],"between":[117],"two":[118],"records.":[120],"Then,":[121],"MinHash":[125],"function":[126],"family":[127],"can":[128,154],"be":[129],"employed":[130],"divide":[132],"into":[134],"multiple":[135],"partitions":[136],"MapReduce":[140],"parallelize":[142],"computation":[143],"while":[144],"preserving":[145],"similarity.":[146],"By":[147],"using":[148],"our":[149,175],"efficient":[150],"LSH-based":[151],"scheme,":[152],"each":[156],"partition":[157],"through":[158],"recursive":[163],"agglomerative":[164],"$k$-member":[165],"clustering":[166],"algorithm.":[167],"Extensive":[168],"experiments":[169],"real-life":[171],"show":[173],"that":[174],"significantly":[177],"improves":[178],"scalability":[180],"time-efficiency":[182],"by":[186],"orders":[187],"magnitude":[189],"over":[190],"approaches.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}