Research map / Federated learning and privacy / Privacy attacks and secure learning
Towards Attack-tolerant Federated Learning via Critical Parameter Analysis
Sungwon Han, Sungwon Park, Fangzhao Wu, Sundong Kim, Bin Zhu, Xing Xie, Meeyoung Cha
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 |
|---|---|---|---|
| add bottom-k parameter comparison to the normality score (ablation) | FedCPA · CIFAR-10 targeted attack | attack success rate (%): 36.8 -> 12.5 | Improved |
| add top-k parameter comparison to the normality score (ablation) | FedCPA · CIFAR-10 targeted attack | attack success rate (%): 18.9 -> 12.5 | Improved |
| add similarity to previous-round global model (ablation) | FedCPA · CIFAR-10 targeted attack | attack success rate (%): 24.1 -> 12.5 | Improved |
| add similarity among local models (ablation) | FedCPA · CIFAR-10 targeted attack | attack success rate (%): 20.2 -> 12.5 | Improved |
| set k to 1% rather than 0.5% or 5% (ablation) | FedCPA · CIFAR-10 targeted attack | attack success rate (%): 63.4 (0.5%) / 51.6 (5%) -> 12.5 (1%) | Improved |
| use FedCPA instead of baseline aggregators under targeted attack | FedAvg · CIFAR-10 targeted (pollution 0.5) | attack success rate (%): 51.4 -> 21.9 | Improved |
| use FedCPA instead of baselines on clean accuracy under TinyImageNet targeted attack | FedAvg · TinyImageNet targeted (pollution 0.5) | accuracy (%): 39.6 -> 30.1 | Hurt |
| use FedCPA instead of ResidualBase under Gaussian noise attack | FedAvg · TinyImageNet Gaussian attack | accuracy (%): 37.0 -> 36.1 | No clear effect |
Closest papers by meaning
- Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning (AAAI 2025 · similarity 0.90)
- Model Poisoning Attacks to Federated Learning via Multi-Round Consistency (CVPR 2025 · similarity 0.90)
- RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation (NeurIPS 2024 · similarity 0.89)
- Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning (NeurIPS 2024 · similarity 0.88)
- FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error (ICML 2024 · similarity 0.88)
- Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning (NeurIPS 2025 · similarity 0.88)
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.
