| Speaker : | Ilia Shilov |
| Inria | |
| Date: | 22/02/2023 |
| Time: | 10:30 am - 11:30 am |
| Location: | Room 4B01 |
Abstract
Consider an individual who is deciding whether to allow their data to be included in a database. For example, it may be a patient deciding whether their medical records can be used in a study, or someone deciding whether to answer a survey. A useful notion of privacy would be an assurance that allowing their data to be included should have negligible impact on them in the future. Absolute privacy is inherently impossible but what we want to be guaranteed is that that the chance of a privacy violation is small. This is precisely what differential privacy (DP) provides. We will have an introduction to differential privacy, in which we will cover the fundamentals of differential privacy, such as epsilon-differential privacy, the Laplace mechanism, and the exponential mechanism. We will also discuss the strengths and limitations of differential privacy, and the challenges associated with its implementation.