DPrivBench is a new benchmark for evaluating LLMs on differential privacy reasoning, with results showing good performance on textbook mechanisms but substantial failures on advanced algorithms.
The permute-and-flip mechanism is identical to report-noisy-max with exponential noise.arXiv preprint arXiv:2105.07260
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Fed-Sparse-BNSL combines differential privacy with sparse greedy updates to learn linear Gaussian Bayesian network structures in a federated setting while keeping communication low and utility close to non-private baselines.
New privacy analysis for SVT enables exponential noise plus threshold correction and appending, raising precision and recall up to 50%.
citing papers explorer
-
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
DPrivBench is a new benchmark for evaluating LLMs on differential privacy reasoning, with results showing good performance on textbook mechanisms but substantial failures on advanced algorithms.
-
Differentially Private and Federated Structure Learning in Bayesian Networks
Fed-Sparse-BNSL combines differential privacy with sparse greedy updates to learn linear Gaussian Bayesian network structures in a federated setting while keeping communication low and utility close to non-private baselines.
-
Unleash the Power of Ellipsis: Accuracy-enhanced Sparse Vector Technique with Exponential Noise
New privacy analysis for SVT enables exponential noise plus threshold correction and appending, raising precision and recall up to 50%.