Research map / Federated learning and privacy / Privacy attacks and secure learning
Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| aggregate gradients with noise added once inside MPC instead of locally per party | gradient perturbation DP-ERM · noise generation | noise std: 5.63 ×10−3 -> 0.572 ×10−3 | Helped |
| aggregate models with output perturbation inside MPC instead of local perturbation | output perturbation DP-ERM · noise generation | noise std: 112 ×10−3 -> 12.2 ×10−3 | Helped |
| use MPC-based DP methods instead of local DP baselines | logistic regression · KDDCup99 m=1000 | relative accuracy loss | Helped |
| use MPC Out P instead of model aggregation baselines | ridge regression · KDDCup98 | optimality gap | Helped |
Closest papers by meaning
- Differentially Private Learning with Small Public Data (AAAI 2020 · similarity 0.92)
- Renyi Differential Privacy of The Subsampled Shuffle Model In Distributed Learning (NeurIPS 2021 · similarity 0.91)
- Certification for Differentially Private Prediction in Gradient-Based Training (ICML 2025 · similarity 0.90)
- Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation (ICML 2025 · similarity 0.90)
- The Privacy Power of Correlated Noise in Decentralized Learning (ICML 2024 · similarity 0.90)
- Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks (AAAI 2024 · similarity 0.89)
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.