[ { "key": "CE73WSIS", "version": 1, "library": { "type": "group", "id": 23021, "name": "privacy", "links": { "alternate": { "href": "https://www.zotero.org/groups/privacy", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/23021/items/CE73WSIS", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/privacy/items/CE73WSIS", "type": "text/html" } }, "meta": { "createdByUser": { "id": 207095, "username": "Haksoo Choi", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/haksoo_choi", "type": "text/html" } } }, "creatorSummary": "Agrawal et al.", "parsedDate": "2002", "numChildren": 0 }, "data": { "key": "CE73WSIS", "version": 1, "itemType": "conferencePaper", "title": "Hippocratic Databases", "creators": [ { "creatorType": "author", "firstName": "Rakesh", "lastName": "Agrawal" }, { "creatorType": "author", "firstName": "Jerry", "lastName": "Kiernan" }, { "creatorType": "author", "firstName": "Ramakrishnan", "lastName": "Srikant" }, { "creatorType": "author", "firstName": "Yirong", "lastName": "Xu" } ], "abstractNote": "The Hippocratic Oath has guided the conduct of physicians for centuries. Inspired by its tenet of preserving privacy, we argue that future database systems must include responsibility for the privacy of data they manage as a founding tenet. We enunciate the key privacy principles for such Hippocratic database systems. We propose a strawman design for Hippocratic databases, identify the technical challenges and problems in designing such databases, and suggest some approaches that may lead to solutions. Our hope is that this paper will serve to catalyze a fruitful and exciting direction for future database research.", "proceedingsTitle": "Proceedings of the 28th international conference on Very Large Data Bases", "conferenceName": "", "publisher": "VLDB Endowment", "place": "Hong Kong, China", "date": "2002", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "143-154", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1287369.1287383", "accessDate": "2010-04-05T22:29:00Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": { "owl:sameAs": "http://zotero.org/groups/23022/items/8HTJNPT9" }, "dateAdded": "2010-08-09T18:25:01Z", "dateModified": "2010-08-09T18:25:01Z" } }, { "key": "3MXRT7C8", "version": 1, "library": { "type": "group", "id": 23021, "name": "privacy", "links": { "alternate": { "href": "https://www.zotero.org/groups/privacy", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/23021/items/3MXRT7C8", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/privacy/items/3MXRT7C8", "type": "text/html" } }, "meta": { "createdByUser": { "id": 207095, "username": "Haksoo Choi", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/haksoo_choi", "type": "text/html" } } }, "creatorSummary": "Brickell and Shmatikov", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "3MXRT7C8", "version": 1, "itemType": "conferencePaper", "title": "The cost of privacy: destruction of data-mining utility in anonymized data publishing", "creators": [ { "creatorType": "author", "firstName": "Justin", "lastName": "Brickell" }, { "creatorType": "author", "firstName": "Vitaly", "lastName": "Shmatikov" } ], "abstractNote": "Re-identification is a major privacy threat to public datasets containing individual records. Many privacy protection algorithms rely on generalization and suppression of \"quasi-identifier\" attributes such as ZIP code and birthdate. Their objective is usually syntactic sanitization: for example, k-anonymity requires that each \"quasi-identifier\" tuple appear in at least k records, while l-diversity requires that the distribution of sensitive attributes for each quasi-identifier have high entropy. The utility of sanitized data is also measured syntactically, by the number of generalization steps applied or the number of records with the same quasi-identifier. In this paper, we ask whether generalization and suppression of quasi-identifiers offer any benefits over trivial sanitization which simply separates quasi-identifiers from sensitive attributes. Previous work showed that k-anonymous databases can be useful for data mining, but k-anonymization does not guarantee any privacy. By contrast, we measure the tradeoff between privacy (how much can the adversary learn from the sanitized records?) and utility, measured as accuracy of data-mining algorithms executed on the same sanitized records.", "proceedingsTitle": "Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining", "conferenceName": "", "publisher": "ACM", "place": "Las Vegas, Nevada, USA", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "70-78", "series": "", "seriesNumber": "", "DOI": "10.1145/1401890.1401904", "ISBN": "978-1-60558-193-4", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1401904", "accessDate": "2010-04-09T05:21:34Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "The cost of privacy", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "anonymity", "type": 1 }, { "tag": "data mining", "type": 1 }, { "tag": "privacy", "type": 1 }, { "tag": "utility", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2010-08-09T18:21:39Z", "dateModified": "2010-08-09T18:21:39Z" } }, { "key": "3N9FTISB", "version": 1, "library": { "type": "group", "id": 23021, "name": "privacy", "links": { "alternate": { "href": "https://www.zotero.org/groups/privacy", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/23021/items/3N9FTISB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/privacy/items/3N9FTISB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 207095, "username": "Haksoo Choi", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/haksoo_choi", "type": "text/html" } } }, "creatorSummary": "Li and Li", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "3N9FTISB", "version": 1, "itemType": "journalArticle", "title": "t-Closeness: Privacy Beyond k-Anonymity and ℓ-Diversity", "creators": [ { "creatorType": "author", "firstName": "Ninghui", "lastName": "Li" }, { "creatorType": "author", "firstName": "Tiancheng", "lastName": "Li" } ], "abstractNote": "", "publicationTitle": "IN PROC. OF IEEE 23RD INT’L CONF. ON DATA ENGINEERING (ICDE’07", "publisher": "", "place": "", "date": "2007", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.92.587", "accessDate": "2010-04-09T04:46:44Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "t-Closeness", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-08-09T18:21:29Z", "dateModified": "2010-08-09T18:21:29Z" } }, { "key": "KVGTAV8E", "version": 1, "library": { "type": "group", "id": 23021, "name": "privacy", "links": { "alternate": { "href": "https://www.zotero.org/groups/privacy", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/23021/items/KVGTAV8E", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/privacy/items/KVGTAV8E", "type": "text/html" } }, "meta": { "createdByUser": { "id": 207095, "username": "Haksoo Choi", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/haksoo_choi", "type": "text/html" } } }, "creatorSummary": "Li and Li", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "KVGTAV8E", "version": 1, "itemType": "conferencePaper", "title": "On the tradeoff between privacy and utility in data publishing", "creators": [ { "creatorType": "author", "firstName": "Tiancheng", "lastName": "Li" }, { "creatorType": "author", "firstName": "Ninghui", "lastName": "Li" } ], "abstractNote": "In data publishing, anonymization techniques such as generalization and bucketization have been designed to provide privacy protection. In the meanwhile, they reduce the utility of the data. It is important to consider the tradeoff between privacy and utility. In a paper that appeared in KDD 2008, Brickell and Shmatikov proposed an evaluation methodology by comparing privacy gain with utility gain resulted from anonymizing the data, and concluded that \"even modest privacy gains require almost complete destruction of the data-mining utility\". This conclusion seems to undermine existing work on data anonymization. In this paper, we analyze the fundamental characteristics of privacy and utility, and show that it is inappropriate to directly compare privacy with utility. We then observe that the privacy-utility tradeoff in data publishing is similar to the risk-return tradeoff in financial investment, and propose an integrated framework for considering privacy-utility tradeoff, borrowing concepts from the Modern Portfolio Theory for financial investment. Finally, we evaluate our methodology on the Adult dataset from the UCI machine learning repository. Our results clarify several common misconceptions about data utility and provide data publishers useful guidelines on choosing the right tradeoff between privacy and utility.", "proceedingsTitle": "Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining", "conferenceName": "", "publisher": "ACM", "place": "Paris, France", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "517-526", "series": "", "seriesNumber": "", "DOI": "10.1145/1557019.1557079", "ISBN": "978-1-60558-495-9", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1557079", "accessDate": "2010-04-09T04:51:19Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "anonymity", "type": 1 }, { "tag": "data mining", "type": 1 }, { "tag": "data publishing", "type": 1 }, { "tag": "privacy", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2010-08-09T18:21:09Z", "dateModified": "2010-08-09T18:21:09Z" } }, { "key": "DNX8NSDB", "version": 1, "library": { "type": "group", "id": 23021, "name": "privacy", "links": { "alternate": { "href": "https://www.zotero.org/groups/privacy", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/23021/items/DNX8NSDB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/privacy/items/DNX8NSDB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 207095, "username": "Haksoo Choi", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/haksoo_choi", "type": "text/html" } } }, "creatorSummary": "Xiao and Tao", "parsedDate": "2006", "numChildren": 0 }, "data": { "key": "DNX8NSDB", "version": 1, "itemType": "conferencePaper", "title": "Anatomy: simple and effective privacy preservation", "creators": [ { "creatorType": "author", "firstName": "Xiaokui", "lastName": "Xiao" }, { "creatorType": "author", "firstName": "Yufei", "lastName": "Tao" } ], "abstractNote": "This paper presents a novel technique, anatomy, for publishing sensitive data. Anatomy releases all the quasi-identifier and sensitive values directly in two separate tables. Combined with a grouping mechanism, this approach protects privacy, and captures a large amount of correlation in the microdata. We develop a linear-time algorithm for computing anatomized tables that obey the l-diversity privacy requirement, and minimize the error of reconstructing the microdata. Extensive experiments confirm that our technique allows significantly more effective data analysis than the conventional publication method based on generalization. Specifically, anatomy permits aggregate reasoning with average error below 10%, which is lower than the error obtained from a generalized table by orders of magnitude.", "proceedingsTitle": "Proceedings of the 32nd international conference on Very large data bases", "conferenceName": "", "publisher": "VLDB Endowment", "place": "Seoul, Korea", "date": "2006", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "139-150", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1164127.1164141", "accessDate": "2010-04-09T04:49:40Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Anatomy", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-08-09T18:20:01Z", "dateModified": "2010-08-09T18:20:01Z" } } ]