Towards Explainable Privacy Preservation in Federated Learning via Shapley Value-Guided Noise Injection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914436262920192 |
|---|---|
| author | Li, Yunbo Gui, Jiaping Wu, Yue |
| author_facet | Li, Yunbo Gui, Jiaping Wu, Yue |
| contents | This paper proposes FedSVA, an explainable differential privacy (DP) mechanism for federated learning (FL) that dynamically calibrates noise injection based on the privacy contribution of attributes via Shapley Values. Unlike heuristic DP methods, FedSVA quantifies each attribute's influence on model training and adjusts noise accordingly, providing rigorous privacy guarantees while minimizing utility loss. Theoretical analysis confirms convergence and DP properties. Experiments on CIFAR-10 and FEMNIST show state-of-the-art privacy-utility trade-offs and robust defense against reconstruction attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12958 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Explainable Privacy Preservation in Federated Learning via Shapley Value-Guided Noise Injection Li, Yunbo Gui, Jiaping Wu, Yue Cryptography and Security This paper proposes FedSVA, an explainable differential privacy (DP) mechanism for federated learning (FL) that dynamically calibrates noise injection based on the privacy contribution of attributes via Shapley Values. Unlike heuristic DP methods, FedSVA quantifies each attribute's influence on model training and adjusts noise accordingly, providing rigorous privacy guarantees while minimizing utility loss. Theoretical analysis confirms convergence and DP properties. Experiments on CIFAR-10 and FEMNIST show state-of-the-art privacy-utility trade-offs and robust defense against reconstruction attacks. |
| title | Towards Explainable Privacy Preservation in Federated Learning via Shapley Value-Guided Noise Injection |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2503.12958 |