Research map / Federated learning and privacy / Privacy attacks and secure learning
FedMOP: Achieving Enhanced Privacy and Performance in Federated Learning via Momentum Orthogonal Projection
Yunlong Zhao, Xiaoheng Deng, Hongyan Xu, Zhuohua Qiu, Xiaowen Hu, Shan You, Yi Chen, Chang Xu, Xiu Su
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 gradient orthogonal projection offset to FedAvg (ablation) | FedAvg · CIFAR-10 (ablation) | accuracy (%): 68.3 -> 70.4 | Improved |
| add random scaling beta without momentum (ablation) | orthogonal offset · CIFAR-10 (ablation) | attack MSE: 0.08 -> 0.31 | Improved |
| add momentum-based trajectory hiding (ablation) | orthogonal offset with random beta · CIFAR-10 (ablation) | attack MSE: 0.31 -> 0.85 | Improved |
| add momentum-based trajectory hiding (ablation) | orthogonal offset with random beta · CIFAR-10 (ablation) | accuracy (%): 70.2 -> 72.7 | Improved |
| increase sigma_gamma from 0.02 to 0.05 (ablation) | FedMOP · CIFAR-10 (ablation) | accuracy and attack MSE: accuracy 72.7 -> 71.5; MSE 0.85 -> 0.93 | Mixed |
| increase sigma_beta from 0.10 to 0.15 (ablation) | FedMOP · CIFAR-10 (ablation) | accuracy and attack MSE: accuracy 72.7 -> 71.3; MSE 0.85 -> 0.96 | Mixed |
| vary initial offset variance sigma_0 by 10x (ablation) | FedMOP · CIFAR-10 (ablation) | accuracy: 72.6 / 72.7 / 72.2 | No clear effect |
| vary mean momentum coefficient gamma from 0.85 to 0.95 (ablation) | FedMOP · CIFAR-10 (ablation) | accuracy: 72.3 / 72.7 / 72.1 | No clear effect |
| use FedMOP instead of FedAvg | FedAvg · CIFAR-100 (full participation, D1) | top-1 accuracy (%): 31.61 -> 42.07 | Improved |
| use FedMOP instead of HierFed under 20% participation, D1 | convergence speed · CIFAR-100 rounds to 30% accuracy | communication rounds: 48 -> 64 | Hurt |
| use FedMOP instead of Soteria/DP-style defenses against csDLG | gradient leakage defense · csDLG, batch size 1 | attack MSE: 0.46 -> 0.85 (vs OUTPOST) | Improved |
Closest papers by meaning
- Concealing Sensitive Samples against Gradient Leakage in Federated Learning (AAAI 2024 · similarity 0.88)
- Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation (ICCV 2023 · similarity 0.87)
- DictPFL: Efficient and Private Federated Learning on Encrypted Gradients (NeurIPS 2025 · similarity 0.87)
- Sketched Gaussian Mechanism for Private Federated Learning (NeurIPS 2025 · similarity 0.87)
- One-shot Empirical Privacy Estimation for Federated Learning (ICLR 2024 · 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.
