Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Recurso digital |
| Sprache: | Englisch |
| Veröffentlicht: |
Zenodo
2025
|
| Schlagworte: | |
| Online-Zugang: | https://doi.org/10.5281/zenodo.19367290 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866901080807309312 |
|---|---|
| author | Wang, Yu Tian |
| author_facet | Wang, Yu Tian |
| contents | <p><span>Federated learning (FL) enables collaborative training across distributed clients without centralizing raw data, making it an attractive approach for privacy-sensitive applications. However, shared model updates in FL may still leak information, leaving systems vulnerable to inference attacks. Differential privacy (DP) provides formal guarantees but often degrades performance, especially in non-independent and identically distributed (non-IID) settings. This work proposes an adaptive noise scaling mechanism to integrate DP into FL more effectively. The method dynamically adjusts client level noise based on local loss variance, balancing privacy preservation and model utility across heterogeneous clients. In addition, an enhanced Convolutional Neural Network (CNN) architecture with Group Normalization and residual connections is employed to stabilize training and improve generalization under noisy updates. Experiments on the MNIST dataset with 50 clients show that the adaptive federated DP model achieves 96.16% accuracy with a privacy budget of </span><span> </span><span> = </span><span> </span><span>. </span><span> </span><span> At a noise multiplier of 1.0. This performance surpasses the centralized DP baseline (94.15%) while approaching the non-private FL baseline (99.57%).<span> </span>Overall, the results highlight adaptive differential privacy as a practical and scalable approach for privacy-preserving federated learning, with strong potential in domains such as healthcare, finance, and mobile edge computing. </span></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19367290 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | ADVANCING SECURE FEDERATED LEARNING WITH ADAPTIVE PRIVACY CONTROLS AND HIGH-PERFORMANCE CNN MODELS Wang, Yu Tian Federated learning, differential privacy, Adaptive noise scaling, Privacy-utility trade-off, Convolutional neural networks <p><span>Federated learning (FL) enables collaborative training across distributed clients without centralizing raw data, making it an attractive approach for privacy-sensitive applications. However, shared model updates in FL may still leak information, leaving systems vulnerable to inference attacks. Differential privacy (DP) provides formal guarantees but often degrades performance, especially in non-independent and identically distributed (non-IID) settings. This work proposes an adaptive noise scaling mechanism to integrate DP into FL more effectively. The method dynamically adjusts client level noise based on local loss variance, balancing privacy preservation and model utility across heterogeneous clients. In addition, an enhanced Convolutional Neural Network (CNN) architecture with Group Normalization and residual connections is employed to stabilize training and improve generalization under noisy updates. Experiments on the MNIST dataset with 50 clients show that the adaptive federated DP model achieves 96.16% accuracy with a privacy budget of </span><span> </span><span> = </span><span> </span><span>. </span><span> </span><span> At a noise multiplier of 1.0. This performance surpasses the centralized DP baseline (94.15%) while approaching the non-private FL baseline (99.57%).<span> </span>Overall, the results highlight adaptive differential privacy as a practical and scalable approach for privacy-preserving federated learning, with strong potential in domains such as healthcare, finance, and mobile edge computing. </span></p> |
| title | ADVANCING SECURE FEDERATED LEARNING WITH ADAPTIVE PRIVACY CONTROLS AND HIGH-PERFORMANCE CNN MODELS |
| topic | Federated learning, differential privacy, Adaptive noise scaling, Privacy-utility trade-off, Convolutional neural networks |
| url | https://doi.org/10.5281/zenodo.19367290 |