Differential privacy: getting more for less
Summary: The key to the success of differential privacy, now the gold standard for privacy-preserving data analysis, is the ability to quantify and reason about cumulative privacy loss over many differentially private interactions. When upper bounds on privacy loss are loose, the deployment of the algorithms is by definition conservative. Under high levels of composition, much potential utility is lost. We survey two general approaches to getting more utility: privacy amplification methods, which are algorithmic, and definitional methods, which admit a wider class of algorithms and lead to tighter analyses of existing algorithms. For the entire collection see [Zbl 07816360].
- Amplification by shuffling: from local to central differential privacy via anonymity
- Bounds on the sample complexity for private learning and private data release
- Composable and versatile privacy via truncated CDP
- Concentrated differential privacy: simplifications, extensions, and lower bounds
- Differential Privacy
- Differential privacy and robust statistics
- Distributed differential privacy via shuffling
- scientific article; zbMATH DE number 5485439 (Why is no real title available?)
- scientific article; zbMATH DE number 5485574 (Why is no real title available?)
- Our Data, Ourselves: Privacy Via Distributed Noise Generation
- Private data release via learning thresholds
- Randomized response: a survey technique for eliminating evasive answer bias
- Rényi Divergence and Kullback-Leibler Divergence
- The algorithmic foundations of differential privacy
- The complexity of computing the optimal composition of differential privacy
- Theory of Cryptography
- What can we learn privately?
This page was built for publication: Differential privacy: getting more for less
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6198644)
