{"id":"https://openalex.org/W4318148206","doi":"https://doi.org/10.1109/bigdata55660.2022.10020987","title":"One Stone, Three Birds: Finer-Grained Encryption with Apache Parquet @ Large Scale","display_name":"One Stone, Three Birds: Finer-Grained Encryption with Apache Parquet @ Large Scale","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318148206","doi":"https://doi.org/10.1109/bigdata55660.2022.10020987"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020987","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5086121474","display_name":"Xinli Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinli Shang","raw_affiliation_strings":["Uber Technologies,Apache Parquet PMC Chair","Apache Parquet PMC Chair, Uber Technologies"],"affiliations":[{"raw_affiliation_string":"Uber Technologies,Apache Parquet PMC Chair","institution_ids":["https://openalex.org/I2946016260"]},{"raw_affiliation_string":"Apache Parquet PMC Chair, Uber Technologies","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064600928","display_name":"Pavi Subenderan","orcid":null},"institutions":[{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pavi Subenderan","raw_affiliation_strings":["Uber Technologies,Software Engineer","Software Engineer, Uber Technologies"],"affiliations":[{"raw_affiliation_string":"Uber Technologies,Software Engineer","institution_ids":[]},{"raw_affiliation_string":"Software Engineer, Uber Technologies","institution_ids":["https://openalex.org/I97750245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748842","display_name":"Mohammad Tariqul Islam","orcid":"https://orcid.org/0000-0002-4929-3209"},"institutions":[{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mohammad Islam","raw_affiliation_strings":["Uber Technologies,Software Engineer","Software Engineer, Uber Technologies"],"affiliations":[{"raw_affiliation_string":"Uber Technologies,Software Engineer","institution_ids":[]},{"raw_affiliation_string":"Software Engineer, Uber Technologies","institution_ids":["https://openalex.org/I97750245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102210171","display_name":"Jianchun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jianchun Xu","raw_affiliation_strings":["Uber Technologies,Software Engineer","Software Engineer, Uber Technologies"],"affiliations":[{"raw_affiliation_string":"Uber Technologies,Software Engineer","institution_ids":[]},{"raw_affiliation_string":"Software Engineer, Uber Technologies","institution_ids":["https://openalex.org/I97750245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082373760","display_name":"Jiashen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jiashen Zhang","raw_affiliation_strings":["Uber Technologies,Software Engineer","Software Engineer, Uber Technologies"],"affiliations":[{"raw_affiliation_string":"Uber Technologies,Software Engineer","institution_ids":[]},{"raw_affiliation_string":"Software Engineer, Uber Technologies","institution_ids":["https://openalex.org/I97750245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102150302","display_name":"Nimish Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nimish Gupta","raw_affiliation_strings":["Uber Technologies,Software Engineer","Software Engineer, Uber Technologies"],"affiliations":[{"raw_affiliation_string":"Uber Technologies,Software Engineer","institution_ids":[]},{"raw_affiliation_string":"Software Engineer, Uber Technologies","institution_ids":["https://openalex.org/I97750245"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047669280","display_name":"\u0410. \u041a. \u041f\u0430\u043d\u0434\u0430","orcid":"https://orcid.org/0000-0002-5087-9899"},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajit Panda","raw_affiliation_strings":["Uber Technologies,Engineer Manager","Engineer Manager, Uber Technologies"],"affiliations":[{"raw_affiliation_string":"Uber Technologies,Engineer Manager","institution_ids":["https://openalex.org/I2946016260"]},{"raw_affiliation_string":"Engineer Manager, Uber Technologies","institution_ids":["https://openalex.org/I2946016260"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5086121474"],"corresponding_institution_ids":["https://openalex.org/I2946016260"],"apc_list":null,"apc_paid":null,"fwci":1.0799,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75917686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T14347","display_name":"Big Data and Digital Economy","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9980000257492065,"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/encryption","display_name":"Encryption","score":0.8367767333984375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7859624624252319},{"id":"https://openalex.org/keywords/disk-encryption-hardware","display_name":"Disk encryption hardware","score":0.5638177394866943},{"id":"https://openalex.org/keywords/filesystem-level-encryption","display_name":"Filesystem-level encryption","score":0.5400271415710449},{"id":"https://openalex.org/keywords/on-the-fly-encryption","display_name":"On-the-fly encryption","score":0.5278056859970093},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4763379693031311},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.4493551254272461},{"id":"https://openalex.org/keywords/client-side-encryption","display_name":"Client-side encryption","score":0.431018590927124},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4232943654060364},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3799857497215271}],"concepts":[{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.8367767333984375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859624624252319},{"id":"https://openalex.org/C61719626","wikidata":"https://www.wikidata.org/wiki/Q17081362","display_name":"Disk encryption hardware","level":5,"score":0.5638177394866943},{"id":"https://openalex.org/C18319499","wikidata":"https://www.wikidata.org/wiki/Q5448402","display_name":"Filesystem-level encryption","level":4,"score":0.5400271415710449},{"id":"https://openalex.org/C147977885","wikidata":"https://www.wikidata.org/wiki/Q117010","display_name":"On-the-fly encryption","level":3,"score":0.5278056859970093},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4763379693031311},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4493551254272461},{"id":"https://openalex.org/C166501710","wikidata":"https://www.wikidata.org/wiki/Q5132476","display_name":"Client-side encryption","level":4,"score":0.431018590927124},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4232943654060364},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3799857497215271}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020987","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2511107577","https://openalex.org/W2790778843","https://openalex.org/W2954268688","https://openalex.org/W4285413283"],"related_works":["https://openalex.org/W2539357035","https://openalex.org/W2744406407","https://openalex.org/W2783985713","https://openalex.org/W2765754337","https://openalex.org/W1025240641","https://openalex.org/W2013897752","https://openalex.org/W4283388250","https://openalex.org/W2054187149","https://openalex.org/W2354820549","https://openalex.org/W26885421"],"abstract_inverted_index":{"Data":[0,31,62,125],"access":[1,44,67],"control,":[2],"retention,":[3],"and":[4,13,24,77,86,138,152,179],"encryption-at-rest":[5],"are":[6,21,119],"fundamental":[7],"security":[8,85,103],"goals":[9,20,104],"for":[10,43,192,203],"data":[11,36,54,71,75,197,208],"privacy":[12],"compliance.":[14],"Often":[15],"each":[16],"of":[17,28,112,163,206],"these":[18,117],"three":[19,102],"implemented":[22],"independently":[23],"in":[25,72,159],"various":[26],"layers":[27],"the":[29,47,51,60,69,108],"Big":[30,35,124],"stack.":[32],"For":[33],"example,":[34],"query":[37],"engines":[38],"may":[39],"add":[40],"custom":[41],"support":[42],"control":[45],"at":[46,88,105],"engine":[48,90],"level":[49,123,132,137,140],"but":[50],"underlying":[52,70],"stored":[53],"is":[55,65,80,201],"not":[56,81],"necessarily":[57],"secured.":[58],"In":[59],"modern":[61],"Lakehouse,":[63],"there":[64],"open":[66],"to":[68,83,99,172,210],"many":[73],"companies\u2019":[74],"lakes":[76],"therefore":[78],"it":[79],"sufficient":[82],"implement":[84],"compliance":[87],"an":[89],"level.In":[91],"this":[92],"paper":[93],"we":[94,185],"present":[95,186],"a":[96,187,207],"unified":[97],"way":[98],"address":[100],"all":[101],"once":[106],"through":[107],"shared":[109],"lower":[110],"layer":[111],"Apache":[113,195,211],"Parquet":[114,196,212],"which":[115,200],"ensures":[116],"controls":[118],"enforced":[120],"by":[121,143,167],"higher":[122],"tools.":[126],"We":[127,146],"introduce":[128],"performant":[129],"file":[130,164],"format":[131,165],"encryption":[133,166,174,182,199],"with":[134,198],"both":[135],"column":[136],"cell":[139],"granularity":[141],"controlled":[142],"schema":[144],"tagging.":[145],"achieve":[147],"less":[148,153],"than":[149,154],"8%":[150],"write":[151],"5%":[155],"read":[156],"performance":[157],"overhead":[158],"most":[160],"common":[161],"scenarios":[162],"minimizing":[168],"RPC":[169],"calls":[170],"required":[171],"perform":[173],"/":[175],"decryption,":[176],"leveraging":[177],"AESNI":[178],"choosing":[180],"optimal":[181],"options.":[183],"Lastly":[184],"novel":[188],"high":[189],"throughput":[190],"method":[191],"rewriting":[193],"existing":[194],"critical":[202],"practical":[204],"onboarding":[205],"lake":[209],"encryption.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}