{"id":"https://openalex.org/W2103528122","doi":"https://doi.org/10.1145/1458082.1458194","title":"Efficient techniques for document sanitization","display_name":"Efficient techniques for document sanitization","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2103528122","doi":"https://doi.org/10.1145/1458082.1458194","mag":"2103528122"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458194","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM 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/A5008813690","display_name":"Venkatesan T. Chakaravarthy","orcid":"https://orcid.org/0000-0002-9422-7243"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"Venkatesan T. Chakaravarthy","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101643160","display_name":"Himanshu Gupta","orcid":"https://orcid.org/0000-0003-3271-3032"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Himanshu Gupta","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100836787","display_name":"Prasan Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I111368775","display_name":"ASTER","ror":"https://ror.org/0504r6d12","country_code":"CA","type":"facility","lineage":["https://openalex.org/I111368775"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Prasan Roy","raw_affiliation_strings":["Aster Data Systems, Redwood City, CA, USA","Aster Data Systems, Redwood City, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Aster Data Systems, Redwood City, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Aster Data Systems, Redwood City, CA, USA#TAB#","institution_ids":["https://openalex.org/I111368775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047987914","display_name":"Mukesh Mohania","orcid":"https://orcid.org/0000-0003-4429-1412"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Mukesh K. Mohania","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008813690"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":4.2595,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.9451902,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"843","last_page":"852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.9975000023841858,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8512153625488281},{"id":"https://openalex.org/keywords/confidentiality","display_name":"Confidentiality","score":0.6814119219779968},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5162944197654724},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33382976055145264},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.20806244015693665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8512153625488281},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.6814119219779968},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5162944197654724},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33382976055145264},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.20806244015693665}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1458082.1458194","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.178.4319","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.178.4319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cscdb.nku.edu/pais09/pdf/p-pais01.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1262131959","https://openalex.org/W1506285740","https://openalex.org/W1574887592","https://openalex.org/W2011039300","https://openalex.org/W2069140227","https://openalex.org/W2113273510","https://openalex.org/W2126186592","https://openalex.org/W2159024459","https://openalex.org/W2159491434","https://openalex.org/W2161030490","https://openalex.org/W2161344493","https://openalex.org/W2164806297","https://openalex.org/W2293888039","https://openalex.org/W2610183793","https://openalex.org/W2614756271"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W2748952813","https://openalex.org/W1531601525"],"abstract_inverted_index":{"Sanitization":[0],"of":[1,74,115],"a":[2,18,64],"document":[3,52,65,77],"involves":[4],"removing":[5],"sensitive":[6,29],"information":[7,32],"from":[8,103],"the":[9,47,75,88,98,104,111,116],"document,":[10],"so":[11,67],"that":[12,68],"it":[13],"may":[14],"be":[15,60],"distributed":[16],"to":[17,62,84,101],"broader":[19],"audience.":[20],"Such":[21],"sanitization":[22,53],"is":[23],"needed":[24],"while":[25],"declassifying":[26],"documents":[27],"involving":[28],"or":[30],"confidential":[31],"such":[33],"as":[34],"corporate":[35],"emails,":[36],"intelligence":[37],"reports,":[38],"medical":[39],"records,":[40],"etc.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"present":[46,91],"ERASE":[48,58,95],"framework":[49],"for":[50,96],"performing":[51],"in":[54,94],"an":[55],"automated":[56],"manner.":[57],"can":[59],"used":[61,93],"sanitize":[63],"dynamically,":[66],"different":[69,72],"users":[70],"get":[71],"views":[73],"same":[76],"based":[78],"on":[79],"what":[80],"they":[81],"are":[82],"authorized":[83],"know.":[85],"We":[86],"formalize":[87],"problem":[89],"and":[90,113],"algorithms":[92],"finding":[97],"appropriate":[99],"terms":[100],"remove":[102],"document.":[105],"Our":[106],"preliminary":[107],"experimental":[108],"study":[109],"demonstrates":[110],"efficiency":[112],"efficacy":[114],"proposed":[117],"algorithms.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
