Research map / Federated learning and privacy / Privacy attacks and secure learning
On the Vulnerability of Backdoor Defenses for Federated Learning
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 |
|---|---|---|---|
| Add focused sign flipping to backdoor training (ablation) | F3BA · CIFAR-10, 50 rounds | ASR: 86.95% -> 88.90% | Helped |
| Add trigger optimization to training with focused flipping (ablation) | F3BA · CIFAR-10, 50 rounds | ASR: 88.90% -> 99.01% | Helped |
| Add focused sign flipping to backdoor training (ablation) | F3BA · Tiny-ImageNet, 50 rounds | ASR: 50.81% -> 71.41% | Helped |
| Add trigger optimization to training with focused flipping (ablation) | F3BA · Tiny-ImageNet, 50 rounds | ASR: 71.41% -> 98.77% | Helped |
| Increase malicious clients from 2/20 to 4/20 | F3BA against Bulyan · Tiny-ImageNet, 100 rounds | ASR: 9.98% -> 92.51% | Helped |
Closest papers by meaning
- Backdoor Federated Learning by Poisoning Backdoor-Critical Layers (ICLR 2024 · similarity 0.91)
- Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective (AAAI 2024 · similarity 0.91)
- Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning (AAAI 2024 · similarity 0.91)
- Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning (NeurIPS 2024 · similarity 0.91)
- MARS: A Malignity-Aware Backdoor Defense in Federated Learning (NeurIPS 2025 · similarity 0.90)
- SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution (ICML 2025 · 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.