19. How to implement data privacy? A conversation with Klaudius Kalcher, cofounder and chief data scientist of MOSTLY AI
Data Democratization Podcast: Stories about AI, Data, and Privacy
00:00
Is There a Limitation to Differential Privacy?
All the other guarantees in differential privacy are framed in the contust of a barimeter that's called ebsilon. And this ebsilon is basically a factor by which a risk can be increased, or a probability can increase when a single individual is added to a data set or removed. In practice, you will get more lax recommendations tike an apsilon below one, iso wheeol. But even an absint of one means that the probability of guessing this attribute right in an attribute inference attack could increase by a factor up to threeruis.
Transcript
Play full episode
