{"id":"https://openalex.org/W7171928454","doi":"https://doi.org/10.1145/3828820.3828821","title":"A Seed for Privacy - semi-automatic privacy-revealing data detection in databases and data streams","display_name":"A Seed for Privacy - semi-automatic privacy-revealing data detection in databases and data streams","publication_year":2026,"publication_date":"2026-07-31","ids":{"openalex":"https://openalex.org/W7171928454","doi":"https://doi.org/10.1145/3828820.3828821"},"language":null,"primary_location":{"id":"doi:10.1145/3828820.3828821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3828820.3828821","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Scalable Scientific Data Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3828820.3828821","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082103734","display_name":"\u548c\u61b2 \u795e\u8c37","orcid":"https://orcid.org/0009-0000-7512-409X"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"He Gu","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0009-0000-7512-409X","affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058872571","display_name":"Thomas Plagemann","orcid":"https://orcid.org/0000-0002-2598-9228"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Thomas Plagemann","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-2598-9228","affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008729338","display_name":"Vera Goebel","orcid":"https://orcid.org/0000-0002-2850-066X"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Vera Goebel","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-2850-066X","affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.666100025177002},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5410000085830688},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.5138000249862671},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45899999141693115},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.43880000710487366},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.36230000853538513},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385000228881836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6876999735832214},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.666100025177002},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5410000085830688},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.5138000249862671},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3828820.3828821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3828820.3828821","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Scalable Scientific Data Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3828820.3828821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3828820.3828821","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Scalable Scientific Data Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1967689022","https://openalex.org/W1985514943","https://openalex.org/W2041836242","https://openalex.org/W2053154970","https://openalex.org/W2162168677","https://openalex.org/W2284304146","https://openalex.org/W2809658909","https://openalex.org/W2913696439","https://openalex.org/W2959406073","https://openalex.org/W2979667481","https://openalex.org/W2995417065","https://openalex.org/W3032521456","https://openalex.org/W3174730162","https://openalex.org/W4206407665","https://openalex.org/W4380564068","https://openalex.org/W4417190057"],"related_works":[],"abstract_inverted_index":{"Sharing":[0],"databases":[1],"and":[2,24,85,94,184,192],"data":[3,22,39,42,96,105,115,123,201],"streams":[4],"imposes":[5],"the":[6,13,46,100,104,109,112,122,154,165,172,196],"danger":[7],"of":[8,15,81,103,111,171,182,186,209,218],"revealing":[9],"private":[10],"information":[11],"in":[12,90,188],"form":[14],"complex":[16,30,88,231],"events":[17,31,89,232],"which":[18,53],"can":[19,76,227],"comprise":[20],"individual":[21],"elements":[23],"their":[25],"combinations.":[26],"Identifying":[27],"these":[28,51],"privacy-revealing":[29,87,190,230],"is":[32,156],"crucial":[33],"for":[34],"preserving":[35],"privacy":[36,101],"while":[37],"maintaining":[38],"utility.":[40],"However,":[41],"producers":[43],"often":[44],"lack":[45,162],"expertise":[47],"to":[48,83,164,234],"comprehensively":[49],"identify":[50,84],"events,":[52],"undermines":[54],"many":[55],"state-of-the-art":[56,197],"privacy-preserving":[57],"mechanisms":[58],"that":[59,75,161,177,225],"rely":[60],"on":[61,147],"accurate":[62],"event":[63],"labeling.":[64],"To":[65],"address":[66],"this":[67,151,193],"challenge,":[68],"we":[69],"developed":[70],"pArborist":[71,107,132,178,205,226],"-":[72],"a":[73,79,134,207],"tool":[74],"semi-automatically":[77],"create":[78],"set":[80],"queries":[82,160],"label":[86],"both":[91],"static":[92],"datasets":[93],"dynamic":[95],"streams,":[97],"guided":[98],"by":[99,143,158],"requirements":[102],"producer.":[106],"uses":[108],"schema":[110],"database":[113],"or":[114,167],"stream":[116,202],"combined":[117],"with":[118],"initial":[119],"input":[120],"from":[121],"producer,":[124],"i.e.,":[125],"seed":[126,130,166],"queries.":[127],"From":[128],"each":[129],"query,":[131],"grows":[133],"tree":[135,155],"containing":[136],"all":[137],"possible":[138],"syntactically":[139],"correct":[140],"queries,":[141,191],"constrained":[142],"an":[144,214],"upper":[145],"limit":[146],"computational":[148],"resources.":[149],"Following":[150],"growing":[152],"phase,":[153],"refined":[157],"eliminating":[159],"correlation":[163],"are":[168],"conditionally":[169],"independent":[170],"seed.":[173],"Our":[174],"evaluation":[175],"indicates":[176],"achieves":[179],"overall":[180],"recall":[181],"\\(90\\%\\)":[183],"precision":[185],"\\(93\\%\\)":[187],"finding":[189],"significantly":[194],"surpasses":[195],"approach":[198],"FQID.":[199],"In":[200],"processing":[203],"experiments,":[204],"introduces":[206],"delay":[208],"approximately":[210],"1.3":[211],"ms":[212],"following":[213],"average":[215],"warm-up":[216],"period":[217],"920":[219],"ms.":[220],"The":[221],"experiments":[222],"also":[223],"show":[224],"automatically":[228],"detect":[229],"according":[233],"GDPR.":[235]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}