Research map / Federated learning and privacy / Privacy attacks and secure learning
Robust and Actively Secure Serverless Collaborative Learning
Nicholas Franzese, Adam Dziedzic, Christopher A. Choquette-Choo, Mark R. Thomas, Muhammad Ahmad Kaleem, Stephan Rabanser, Congyu Fang, Somesh Jha, Nicolas Papernot, Xiao Wang
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 |
|---|---|---|---|
| Use malicious-secure P2P RSA aggregation | P2P collaborative learning · Aggregation step, 1000 peers, 10^5 parameters | CPU time: 46 seconds | Improved |
| Represent updates as bits using RSA rather than fixed-point updates with Centered Clipping | P2P aggregation · RSA vs. Centered Clipping | aggregation speed: around ~30X | Improved |
| Represent updates as bits using RSA rather than fixed-point updates with FLTrust | P2P aggregation · RSA vs. FLTrust | aggregation speed: around ~6X | Improved |
| Use malicious-secure Centered Clipping and FLTrust instead of RSA | P2P learning · EMNIST | convergence speed | Improved |
| Use Centered Clipping or FLTrust instead of RSA | P2P learning · EMNIST | final accuracy | Improved |
| Use Centered Clipping instead of FLTrust | P2P learning · EMNIST | accuracy | Improved |
| Modify Centered Clipping from ℓ2 clipping to ℓ∞ box clipping (ablation) | Centered Clipping · IID EMNIST and MNIST under attacks | robustness | No clear effect |
| Lower Centered Clipping numerical precision to fixed-point (ablation) | Centered Clipping · IID MNIST under ALIE attack | robustness | No clear effect |
| Use the modified malicious-secure versions of CC, FLTrust, and RSA (ablation) | Robust aggregation algorithms · Robustness evaluations | model performance | No clear effect |
| Reduce FLTrust fixed-point length from 32 bits to 16 bits relative to CC | FLTrust · P2P training | computational efficiency: 16 bits vs 32 bits | Improved |
Closest papers by meaning
- The Promise of Serverless Computing within Peer-to-Peer Architectures for Distributed ML Training (AAAI 2024 · similarity 0.88)
- Towards Trustworthy Federated Learning with Untrusted Participants (ICML 2025 · similarity 0.86)
- On the Robustness of Distributed Machine Learning Against Transfer Attacks (AAAI 2025 · similarity 0.85)
- SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution (ICML 2025 · similarity 0.85)
- RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation (NeurIPS 2024 · similarity 0.84)
- Incorporating Serverless Computing into P2P Networks for ML Training: In-Database Tasks and Their Scalability Implications (Student Abstract) (AAAI 2024 · similarity 0.84)
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.
