Research map / Federated learning and privacy / Differential privacy
Capacity Bounded Differential Privacy
Kamalika Chaudhuri, Jacob Imola, Ashwin Machanavajjhala
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 |
|---|---|---|---|
| Restrict the adversary to linear functions | Laplace mechanism · Laplace mechanism, 1D | KL privacy parameter: The linear-adversary parameter is the expression in Table; the unrestricted parameter is $ \epsilon-1 + e^{-\epsilon} $. | Improved |
| Restrict the adversary to linear functions | Gaussian mechanism · Gaussian mechanism, 1D | KL privacy parameter: $ \nicefrac{1}{2\sigma^2} $ -> $ \nicefrac{1}{2\sigma^2} $ | No clear effect |
| Restrict the adversary to linear functions | Laplace mechanism · Laplace mechanism, 1D | α-Renyi privacy parameter: Linear upper bound: $ \leq \frac{1}{\alpha-1}\log(1+2^{\alpha-1}\epsilon^\alpha)$; unrestricted lower bound: $ \geq \eps | Improved |
| Restrict the adversary to linear functions | Gaussian mechanism · Gaussian mechanism, 1D | α-Renyi privacy parameter: Linear upper bound: $\leq \frac{1}{\alpha-1}\log(1+\nicefrac{\sqrt{2\pi}^{\alpha-1}}{\sigma^\alpha})$; unrestricted para | Mixed |
| Use the Matrix mechanism with a linear-adversary privacy analysis | Matrix mechanism · Matrix mechanism | α-Renyi privacy parameter: $\frac{1}{\alpha-1}\log(1+2^{s(\alpha-1)}\epsilon^\alpha)$ | Improved |
| Require the adversarial function class to include query evaluation functions | Capacity-bounded private query mechanism · Statistical queries | Expected absolute generalization gap: $8 \sqrt{\epsilon}$ | Improved |
Closest papers by meaning
- The Limits of Differential Privacy in Online Learning (NeurIPS 2024 · similarity 0.88)
- A Unified Framework for Adversary-Aware Differential Privacy Bounds (NeurIPS 2026 · similarity 0.88)
- Shifted Interpolation for Differential Privacy (ICML 2024 · similarity 0.87)
- Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness (ICLR 2025 · similarity 0.87)
- The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD (ICLR 2025 · similarity 0.87)
- Certification for Differentially Private Prediction in Gradient-Based Training (ICML 2025 · similarity 0.87)
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.
