Differentially Private Database Release via Kernel Mean Embeddings
| cam.issuedOnline | 2018-05-31 | |
| cam.orpheus.counter | 12 | |
| cam.orpheus.success | Thu Nov 05 11:53:17 GMT 2020 - Embargo updated | |
| dc.contributor.author | Balog, Matej | |
| dc.contributor.author | Tolstikhin, Ilya | |
| dc.contributor.author | Schölkopf, Bernhard | |
| dc.contributor.orcid | Balog, Matej [0000-0002-5552-9855] | |
| dc.date.accessioned | 2019-01-11T00:30:25Z | |
| dc.date.available | 2019-01-11T00:30:25Z | |
| dc.date.issued | 2017-10-04 | |
| dc.description.abstract | We lay theoretical foundations for new database release mechanisms that allow third-parties to construct consistent estimators of population statistics, while ensuring that the privacy of each individual contributing to the database protected. The proposed framework rests on two main ideas. First, releasing (an estimate of) the kernel mean embedding of the data generating random variable instead of the database itself still allows third-parties to construct consistent estimators of a wide class of population statistics. Second, the algorithm can satisfy the definition of differential privacy by basing the released kernel mean embedding on entirely synthetic data points, while controlling accuracy through the metric available in a Reproducing Kernel Hilbert Space. We describe two instantiations of the proposed framework, suitable under different scenarios, and prove theoretical results guaranteeing differential privacy of the resulting algorithms and the consistency of estimators constructed from their outputs. | |
| dc.identifier.doi | 10.17863/CAM.35099 | |
| dc.identifier.uri | https://www.repository.cam.ac.uk/handle/1810/287784 | |
| dc.language.iso | eng | |
| dc.publisher | MIR Press | |
| dc.publisher.url | http://proceedings.mlr.press/v80/ | |
| dc.subject | stat.ML | |
| dc.subject | stat.ML | |
| dc.title | Differentially Private Database Release via Kernel Mean Embeddings | |
| dc.type | Conference Object | |
| prism.endingPage | 431 | |
| prism.publicationName | Proceedings of Machine Learning Research Volume 80: | |
| prism.startingPage | 423 | |
| prism.volume | 80 | |
| pubs.conference-finish-date | 2018-07-15 | |
| pubs.conference-name | International Conference on Machine Learning | |
| pubs.conference-start-date | 2018-07-10 | |
| pubs.funder-project-id | EPSRC (1626332) | |
| rioxxterms.licenseref.uri | http://www.rioxx.net/licenses/all-rights-reserved | |
| rioxxterms.type | Conference Paper/Proceeding/Abstract | |
| rioxxterms.version | AM | |
| rioxxterms.versionofrecord | 10.17863/CAM.35099 |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- RKHSprivacy_ICML.pdf
- Size:
- 3.17 MB
- Format:
- Adobe Portable Document Format
- Description:
- Accepted version
- Licence
- http://www.rioxx.net/licenses/all-rights-reserved
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- DepositLicenceAgreement.pdf
- Size:
- 417.78 KB
- Format:
- Adobe Portable Document Format