{"id":"https://openalex.org/W2083773633","doi":"https://doi.org/10.1145/1179601.1179608","title":"Scanning electronic documents for personally identifiable information","display_name":"Scanning electronic documents for personally identifiable information","publication_year":2006,"publication_date":"2006-10-30","ids":{"openalex":"https://openalex.org/W2083773633","doi":"https://doi.org/10.1145/1179601.1179608","mag":"2083773633"},"language":"en","primary_location":{"id":"doi:10.1145/1179601.1179608","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1179601.1179608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM workshop on Privacy in electronic society","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/A5030176989","display_name":"Tuomas Aura","orcid":"https://orcid.org/0000-0003-1648-8875"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Tuomas Aura","raw_affiliation_strings":["Microsoft Research, Cambridge, UK","Microsoft Research, Cambridge, UK;"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, UK","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research, Cambridge, UK;","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004322808","display_name":"Thomas Kuhn","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas A. Kuhn","raw_affiliation_strings":["Technische Universit\u00e3t M\u00fcnchen Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e3t M\u00fcnchen Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108547932","display_name":"Michael Roe","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Michael Roe","raw_affiliation_strings":["Microsoft Research, Cambridge, UK","Microsoft Research, Cambridge, UK;"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, UK","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research, Cambridge, UK;","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030176989"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":2.34,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.89402003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9973999857902527,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9973999857902527,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9966999888420105,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6209469437599182},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35797685384750366},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32518649101257324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6209469437599182},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35797685384750366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32518649101257324}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1179601.1179608","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1179601.1179608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM workshop on Privacy in electronic society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1499241274","https://openalex.org/W1550189296","https://openalex.org/W1631722984","https://openalex.org/W1642192185","https://openalex.org/W2016971609","https://openalex.org/W2099964107","https://openalex.org/W2134826720","https://openalex.org/W2296211620","https://openalex.org/W2969782748"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Sometimes,":[0],"it":[1,48],"is":[2,49,55],"necessary":[3],"to":[4,58],"remove":[5],"author":[6],"names":[7],"and":[8,46,62,65],"other":[9,66],"personally":[10],"identifiable":[11],"information":[12],"(PII)":[13],"from":[14],"documents":[15,45,72],"before":[16],"publication.":[17],"We":[18],"have":[19,36],"implemented":[20],"a":[21,75,82],"novel":[22],"defensive":[23],"tool":[24],"for":[25],"detecting":[26],"such":[27,80],"data":[28],"automatically.":[29],"By":[30],"using":[31],"the":[32,94],"detection":[33],"tool,":[34],"we":[35],"learned":[37],"about":[38],"where":[39],"PII":[40],"may":[41],"be":[42],"stored":[43],"in":[44,71],"how":[47],"put":[50],"there.":[51],"A":[52],"key":[53],"observation":[54],"that,":[56],"contrary":[57],"common":[59],"belief,":[60],"user":[61],"machine":[63],"identifiers":[64],"metadata":[67],"are":[68],"not":[69],"embedded":[70],"only":[73],"by":[74,86],"single":[76],"piece":[77],"of":[78,93],"software,":[79],"as":[81],"word":[83],"processor,":[84],"but":[85],"various":[87],"tools":[88],"used":[89],"at":[90],"different":[91],"stages":[92],"document":[95],"authoring":[96],"process.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}