Concentrated Differential Privacy
read the original abstract
We introduce Concentrated Differential Privacy, a relaxation of Differential Privacy enjoying better accuracy than both pure differential privacy and its popular "(epsilon,delta)" relaxation without compromising on cumulative privacy loss over multiple computations.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
General Lower Bounds for Differentially Private Federated Learning with Arbitrary Public-Transcript Interactions
Derives a federated van Trees lower bound under total clientwise sample-level zCDP for parameter estimation with squared l2 loss in federated learning protocols with arbitrary public-transcript interactions.
-
Barriers to Counterfactual Credit Attribution for Autoregressive Models
CCA does not compose autoregressively and retrofitting requires exponential query complexity under weak optimality.
-
Conformal-DP: A Density-Aware Mechanism for Differential Privacy over Riemannian Manifolds via Conformal Transformation
Conformal-DP applies conformal transformations to create a density-aware DP mechanism on Riemannian manifolds, proving ε-DP and deriving a closed-form geodesic error bound dependent only on density ratio and independe...
-
Private Minimum Hellinger Distance Estimation via Hellinger Distance Differential Privacy
Private minimum Hellinger distance estimators are introduced to satisfy Hellinger differential privacy while retaining robustness and efficiency properties.
-
Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition
The Edgeworth Accountant uses the Edgeworth expansion on privacy-loss log-likelihood ratios to derive closed-form non-asymptotic (ε, δ)-DP bounds for composed noise-addition mechanisms.
-
Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
Add/remove adjacency in DP overstates attribute privacy relative to substitute adjacency; new auditing attacks confirm inconsistency with add/remove reports but consistency with substitute accounting.
-
The 2020 US Decennial Census is more private than you (might) think
Using f-differential privacy to track losses across eight geographic levels, the 2020 Census provides stronger privacy than its nominal guarantees, enabling 15.08-24.82% noise variance reduction.
-
Privacy Preserving Reinforcement Learning with One-Sided Feedback
POOL is a new RL algorithm that adds privacy protection in continuous spaces with one-sided feedback and achieves sample complexity matching known non-private lower bounds.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.