Research map / Federated learning and privacy / Differential privacy
Identification, Amplification and Measurement: A bridge to Gaussian Differential Privacy
Yi Liu, Ke Sun, Bei Jiang, Linglong Kong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| tighten mu for the Laplace mechanism using the proposed measurement algorithm instead of the epsilon-DP-to-GDP theorem | 0.2-DP Laplace mechanism · single mechanism GDP mu | GDP mu: 0.2505 -> 0.2391 | Improved |
| tighten mu for the Laplace mechanism, 50-fold composition | GDP composition · 50-fold composition of 0.2-DP algorithms | GDP mu: 1.771 -> 1.691 | Improved |
| GDP composition instead of basic composition | 50-fold composition of 0.2-DP · 50-fold composition of 0.2-DP algorithms | privacy guarantee: 10 -> 1.771 | Improved |
| use GDPT numeric procedure instead of central limit theorem approximation | 50-fold composition · 50-fold composition of 0.2-DP algorithms | GDP mu: 1.771 vs 1.420 | Mixed |
| Poisson subsampling | GDPT of mechanisms · privacy profile plots | GDP mu | Mixed |
Closest papers by meaning
- Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising (ICML 2018 · similarity 0.90)
- Private Adaptive Covariance Estimation via Gaussian Graphical Models (NeurIPS 2026 · similarity 0.89)
- A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility (AAAI 2024 · similarity 0.89)
- Privacy Amplification for Matrix Mechanisms (ICLR 2024 · similarity 0.88)
- Instance-Specific Asymmetric Sensitivity in Differential Privacy (NeurIPS 2024 · similarity 0.88)
- Privacy Amplification Persists under Unlimited Synthetic Data Release (NeurIPS 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
