OptiGradTrust: Byzantine-Robust Federated Learning with Multi-Feature Gradient Analysis and Reinforcement Learning-Based Trust Weighting
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916873683075072 |
|---|---|
| author | Karami, Mohammad Ghassemi, Fatemeh Kebriaei, Hamed Azadegan, Hamid |
| author_facet | Karami, Mohammad Ghassemi, Fatemeh Kebriaei, Hamed Azadegan, Hamid |
| contents | Federated Learning (FL) enables collaborative model training across distributed medical institutions while preserving patient privacy, but remains vulnerable to Byzantine attacks and statistical heterogeneity. We present OptiGradTrust, a comprehensive defense framework that evaluates gradient updates through a novel six-dimensional fingerprint including VAE reconstruction error, cosine similarity metrics, $L_2$ norm, sign-consistency ratio, and Monte Carlo Shapley value, which drive a hybrid RL-attention module for adaptive trust scoring. To address convergence challenges under data heterogeneity, we develop FedBN-Prox (FedBN-P), combining Federated Batch Normalization with proximal regularization for optimal accuracy-convergence trade-offs. Extensive evaluation across MNIST, CIFAR-10, and Alzheimer's MRI datasets under various Byzantine attack scenarios demonstrates significant improvements over state-of-the-art defenses, achieving up to +1.6 percentage points over FLGuard under non-IID conditions while maintaining robust performance against diverse attack patterns through our adaptive learning approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23638 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OptiGradTrust: Byzantine-Robust Federated Learning with Multi-Feature Gradient Analysis and Reinforcement Learning-Based Trust Weighting Karami, Mohammad Ghassemi, Fatemeh Kebriaei, Hamed Azadegan, Hamid Machine Learning Artificial Intelligence Federated Learning (FL) enables collaborative model training across distributed medical institutions while preserving patient privacy, but remains vulnerable to Byzantine attacks and statistical heterogeneity. We present OptiGradTrust, a comprehensive defense framework that evaluates gradient updates through a novel six-dimensional fingerprint including VAE reconstruction error, cosine similarity metrics, $L_2$ norm, sign-consistency ratio, and Monte Carlo Shapley value, which drive a hybrid RL-attention module for adaptive trust scoring. To address convergence challenges under data heterogeneity, we develop FedBN-Prox (FedBN-P), combining Federated Batch Normalization with proximal regularization for optimal accuracy-convergence trade-offs. Extensive evaluation across MNIST, CIFAR-10, and Alzheimer's MRI datasets under various Byzantine attack scenarios demonstrates significant improvements over state-of-the-art defenses, achieving up to +1.6 percentage points over FLGuard under non-IID conditions while maintaining robust performance against diverse attack patterns through our adaptive learning approach. |
| title | OptiGradTrust: Byzantine-Robust Federated Learning with Multi-Feature Gradient Analysis and Reinforcement Learning-Based Trust Weighting |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.23638 |