Research map / Federated learning and privacy / Privacy attacks and secure learning
A Scalable Approach for Privacy-Preserving Collaborative Machine Learning
Jinhyun So, Basak Guler, Salman Avestimehr
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 |
|---|---|---|---|
| replace baseline MPC protocol [BH08] with COPML Lagrange-coded training (Case 1) | secure logistic regression training · CIFAR-10, N=50 | total run time: 7915 s -> 440 s | Improved |
| replace baseline MPC protocol [BH08] with COPML (Case 2, equal privacy) | secure logistic regression training · CIFAR-10, N=50 | total run time: 7915 s -> 916 s | Improved |
| replace sigmoid and no quantization with degree-1 polynomial sigmoid and quantized finite-field training | logistic regression · CIFAR-10, 50 iterations | test accuracy: 81.75% -> 80.45% | Hurt |
| replace sigmoid and no quantization with degree-1 polynomial sigmoid and quantized finite-field training | logistic regression · GISETTE, 50 iterations | test accuracy: 97.5% -> 97.5% | No clear effect |
| shift resources from parallelization to privacy (Case 1 to Case 2) | COPML · CIFAR-10, N=50 | total run time: 440 s -> 916 s | Hurt |
Closest papers by meaning
- Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks (AAAI 2024 · similarity 0.87)
- The Privacy Power of Correlated Noise in Decentralized Learning (ICML 2024 · similarity 0.87)
- DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing (ICML 2025 · similarity 0.86)
- Towards Trustworthy Federated Learning with Untrusted Participants (ICML 2025 · similarity 0.86)
- Learning from End User Data with Shuffled Differential Privacy over Kernel Densities (ICLR 2025 · similarity 0.86)
- Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation (ICML 2025 · similarity 0.85)
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.
