Scenario-based Adaptations of Differential Privacy: A Technical Survey
Differential privacy has been a de facto privacy standard in defining privacy and handling
privacy preservation. It has had great success in scenarios of local data privacy and …
privacy preservation. It has had great success in scenarios of local data privacy and …
Integer subspace differential privacy
We propose new differential privacy solutions for when external invariants and integer
constraints are simultaneously enforced on the data product. These requirements arise in …
constraints are simultaneously enforced on the data product. These requirements arise in …
Privacy-Preserving Multi-Label Propagation Based on Federated Learning
K Guo, D Chen, Q Huang, F Li, C Guo… - … on Network Science …, 2023 - ieeexplore.ieee.org
Multi-label propagation algorithms (MLPAs) aim to find vertex communities in a complex
network or a cloud system by propagating and updating vertex labels, which have been …
network or a cloud system by propagating and updating vertex labels, which have been …
Wasserstein Differential Privacy
Differential privacy (DP) has achieved remarkable results in the field of privacy-preserving
machine learning. However, existing DP frameworks do not satisfy all the conditions for …
machine learning. However, existing DP frameworks do not satisfy all the conditions for …
[PDF][PDF] Can swapping be differentially private? A refreshment stirred, not shaken
Pr (T (X)∈·) at every dataset X in the data universe D. Derivatives measure change in output
per change in input. How do we measure change? 2. Divergence dX on the data input …
per change in input. How do we measure change? 2. Divergence dX on the data input …
The Still Secret Ballot: The Limited Privacy Cost of Transparent Election Results
S Kuriwaki, JB Lewis, M Morse - arXiv preprint arXiv:2308.04100, 2023 - arxiv.org
After an election, should election officials release an electronic record of each ballot? The
release of such cast vote records could bolster the legitimacy of the certified result. But it may …
release of such cast vote records could bolster the legitimacy of the certified result. But it may …
Formal Privacy for Partially Private Data
Differential privacy (DP) quantifies privacy loss by analyzing noise injected into output
statistics. For non-trivial statistics, this noise is necessary to ensure finite privacy loss …
statistics. For non-trivial statistics, this noise is necessary to ensure finite privacy loss …
Differential privacy: general inferential limits via intervals of measures
Differential privacy (DP) is a mathematical standard for assessing the privacy provided by a
data-release mechanism. We provide formulations of pure $\epsilon $-differential privacy …
data-release mechanism. We provide formulations of pure $\epsilon $-differential privacy …
Two views of constrained differential privacy: Belief revision and update
L Liu, K Sun, C Zhou, Y Feng - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
In this paper, we provide two views of constrained differential private (DP) mechanisms. The
first one is as belief revision. A constrained DP mechanism is obtained by standard …
first one is as belief revision. A constrained DP mechanism is obtained by standard …
Canonical noise distributions and private hypothesis tests
Canonical noise distributions and private hypothesis tests Page 1 The Annals of Statistics
2023, Vol. 51, No. 2, 547–572 https://doi.org/10.1214/23-AOS2259 © Institute of Mathematical …
2023, Vol. 51, No. 2, 547–572 https://doi.org/10.1214/23-AOS2259 © Institute of Mathematical …