Integrating historical noisy answers for improving data utility under differential privacy
Differential privacy is a robust principle for privacy preserving data analysis tasks, and has been successfully applied to a variety of applications. However, the number of queries that can be answered is limited for preventing privacy disclosure. Once the privacy budget is exhausted, all succeedin...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2013
|
| Online Access: | https://hdl.handle.net/10356/84235 http://hdl.handle.net/10220/12280 |
| _version_ | 1826129255761707008 |
|---|---|
| author | Bhowmick, Sourav S. Chen, Shixi Zhou, Shuigeng |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Bhowmick, Sourav S. Chen, Shixi Zhou, Shuigeng |
| author_sort | Bhowmick, Sourav S. |
| collection | NTU |
| description | Differential privacy is a robust principle for privacy preserving data analysis tasks, and has been successfully applied to a variety of applications. However, the number of queries that can be answered is limited for preventing privacy disclosure. Once the privacy budget is exhausted, all succeeding queries must be rejected. Therefore, each of the historical query answers is valuable and it is important to exploit them together to learn more about the data. We propose to integrate all available linear query answers into a consistent form that embodies our knowledge learned from the noisy answers, obtaining more accurate answers to past queries and even new queries, improving the data utility. Two distinct approaches are developed for this purpose, one via principle component analysis, and another via maximum entropy method. The second approach also generates a synthetic database, which is useful for differentially private data publishing. One important goal of our work is to ensure that the running time of our approaches does not grow with the cardinality of the universe of a data tuple, so that high-dimensional data with very large domain can still be tackled efficiently. |
| first_indexed | 2024-10-01T07:37:40Z |
| format | Conference Paper |
| id | ntu-10356/84235 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:37:40Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/842352020-05-28T07:18:00Z Integrating historical noisy answers for improving data utility under differential privacy Bhowmick, Sourav S. Chen, Shixi Zhou, Shuigeng School of Computer Engineering International Conference on Extending Database Technology (15th : 2012) Differential privacy is a robust principle for privacy preserving data analysis tasks, and has been successfully applied to a variety of applications. However, the number of queries that can be answered is limited for preventing privacy disclosure. Once the privacy budget is exhausted, all succeeding queries must be rejected. Therefore, each of the historical query answers is valuable and it is important to exploit them together to learn more about the data. We propose to integrate all available linear query answers into a consistent form that embodies our knowledge learned from the noisy answers, obtaining more accurate answers to past queries and even new queries, improving the data utility. Two distinct approaches are developed for this purpose, one via principle component analysis, and another via maximum entropy method. The second approach also generates a synthetic database, which is useful for differentially private data publishing. One important goal of our work is to ensure that the running time of our approaches does not grow with the cardinality of the universe of a data tuple, so that high-dimensional data with very large domain can still be tackled efficiently. 2013-07-25T07:41:43Z 2019-12-06T15:41:05Z 2013-07-25T07:41:43Z 2019-12-06T15:41:05Z 2012 2012 Conference Paper Chen, S., Zhou, S., & Bhowmick, S. S. (2012). Integrating historical noisy answers for improving data utility under differential privacy. Proceedings of the 15th International Conference on Extending Database Technology. https://hdl.handle.net/10356/84235 http://hdl.handle.net/10220/12280 10.1145/2247596.2247605 en © 2012 ACM. |
| spellingShingle | Bhowmick, Sourav S. Chen, Shixi Zhou, Shuigeng Integrating historical noisy answers for improving data utility under differential privacy |
| title | Integrating historical noisy answers for improving data utility under differential privacy |
| title_full | Integrating historical noisy answers for improving data utility under differential privacy |
| title_fullStr | Integrating historical noisy answers for improving data utility under differential privacy |
| title_full_unstemmed | Integrating historical noisy answers for improving data utility under differential privacy |
| title_short | Integrating historical noisy answers for improving data utility under differential privacy |
| title_sort | integrating historical noisy answers for improving data utility under differential privacy |
| url | https://hdl.handle.net/10356/84235 http://hdl.handle.net/10220/12280 |
| work_keys_str_mv | AT bhowmicksouravs integratinghistoricalnoisyanswersforimprovingdatautilityunderdifferentialprivacy AT chenshixi integratinghistoricalnoisyanswersforimprovingdatautilityunderdifferentialprivacy AT zhoushuigeng integratinghistoricalnoisyanswersforimprovingdatautilityunderdifferentialprivacy |