Research map / Federated learning and privacy / Differential privacy
In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning
Jiaqi Wang, Roei Schuster, Ilia Shumailov, David Lie, Nicolas Papernot
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 |
|---|---|---|---|
| increase Gaussian noise scale sigma (40 to 100) in PATE (ablation) | Histogram reconstruction attack · MNIST and SVHN, 10^4 queries | attack error rate | Improved |
| low-consensus vs high-consensus histograms used as minority-group signal (consensus threshold 75%) | PhD-holder detection attack · UCI Adult-Income | precision: 75% | Improved |
| set sigma near 0 or very large (400) for the attacked PATE (ablation) | Histogram reconstruction attack · SVHN median-consensus histogram | attack error rate | Hurt |
| tighter privacy budget / higher noise (lower privacy cost) | PATE defense against attack · MNIST and SVHN | attack error rate | No clear effect |
Closest papers by meaning
- Scalable Private Learning with PATE (ICLR 2018 · similarity 0.91)
- Label differential privacy and private training data release (ICML 2023 · similarity 0.89)
- Certification for Differentially Private Prediction in Gradient-Based Training (ICML 2025 · similarity 0.89)
- Attack-Aware Noise Calibration for Differential Privacy (NeurIPS 2024 · similarity 0.88)
- Learning from End User Data with Shuffled Differential Privacy over Kernel Densities (ICLR 2025 · similarity 0.87)
- The Limits of Differential Privacy in Online Learning (NeurIPS 2024 · 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.
