Research map / Federated learning and privacy / Privacy attacks and secure learning
Provably Secure Federated Learning against Malicious Clients
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 |
|---|---|---|---|
| Replace one global model with a majority vote over client-subsample models | FedAvg · MNIST and HAR | certified accuracy at m>0: 0 certified accuracy for single-model FedAvg at one malicious client; ensemble FedAvg reaches 0 at 61 clients on MNIST a | Helped |
| Use a larger client subsample size k (ablation) | Ensemble FedAvg · MNIST and HAR | certified accuracy | Mixed |
| Increase the number of trained subsample models N (ablation) | Ensemble FedAvg · MNIST and HAR | certified accuracy: 100 to 500; 1,000 | Helped |
| Increase alpha (ablation) | Ensemble FedAvg certification algorithm · MNIST and HAR | certified accuracy | Helped |
| Increase the degree of non-IID client data q from 0.5 to 0.9 (ablation) | Ensemble FedAvg · MNIST | certified accuracy: 0.5 to 0.9 | Hurt |
| Use ensemble FedAvg with q=0.9 client data (ablation) | Ensemble FedAvg · MNIST at 10 malicious clients | certified accuracy: 83\% | Helped |
Closest papers by meaning
- SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution (ICML 2025 · similarity 0.87)
- Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning (ICML 2024 · similarity 0.87)
- Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients (NeurIPS 2025 · similarity 0.87)
- Towards Trustworthy Federated Learning with Untrusted Participants (ICML 2025 · similarity 0.87)
- Attribute Inference Attacks for Federated Regression Tasks (AAAI 2025 · similarity 0.86)
- Towards the Robustness of Differentially Private Federated Learning (AAAI 2024 · similarity 0.86)
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.