Research map / Federated learning and privacy / Privacy attacks and secure learning
FedInv: Byzantine-Robust Federated Learning by Inversing Local Model Updates
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 |
|---|---|---|---|
| Use FedInv instead of FedAvg | Federated learning under Badnet attack · MNIST | accuracy: 95.08% -> 96.02% | Helped |
| Use FedInv instead of LFR | Federated learning under Badnet attack · MNIST | ASR: 93.23% -> 0.07% | Helped |
| Use FedInv instead of LFR | Federated learning under Badnet attack · Fashion-MNIST | accuracy: 80.13% -> 80.88% | Helped |
| Use FedInv instead of MultiKrum | Federated learning under Badnet attack · Fashion-MNIST | ASR: 1.34% -> 0.92% | Helped |
| Use FedInv instead of FedAvg | Federated learning under Backdoor FL attack · MNIST | accuracy: 93.37% -> 94.97% | Helped |
| Use FedInv instead of LFR | Federated learning under Backdoor FL attack · MNIST | ASR: 0.06% -> 0.04% | Helped |
| Use FedInv instead of LFR | Federated learning under Backdoor FL attack · Fashion-MNIST | accuracy: 78.23% -> 79.02% | Helped |
| Use FedInv instead of MultiKrum | Federated learning under Backdoor FL attack · Fashion-MNIST | ASR: 0.94% -> 0.62% | Helped |
| Use FedInv rather than baseline robust aggregation schemes | Federated learning under untargeted poisoning attacks · MNIST and HAR | accuracy | Helped |
| Use FedInv rather than baseline robust aggregation schemes | Federated learning under targeted poisoning attacks · MNIST and Fashion-MNIST | ASR | Helped |
| Increase the proportion of Byzantine clients | FedInv under Badnet attack · MNIST and Fashion-MNIST | ASR | No clear effect |
| Increase the non-IID degree | FedInv under Badnet attack · MNIST and Fashion-MNIST | ASR | No clear effect |
Closest papers by meaning
- Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients (NeurIPS 2025 · similarity 0.91)
- Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates (ICML 2024 · similarity 0.91)
- Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping (CVPR 2024 · similarity 0.90)
- FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error (ICML 2024 · similarity 0.89)
- Towards the Robustness of Differentially Private Federated Learning (AAAI 2024 · similarity 0.89)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 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.