2026· IEEE Transactions on Network Science and Engineering· Vol 13, pp. 11937-11954· 0 citations· 61 references
Computer Science
TL;DR
FMVFed achieves differential privacy by injecting Gaussian noise into the coefficient space of the training objective, thereby avoiding the utility loss caused by directly perturbing high-dimensional vectors and introduces an adaptive random Top-$k$ Sparsification communication strategy to significantly reduce cross-party communication overhead.
Abstract
Vertical federated learning enables multiple institutions to collaboratively train models without sharing raw features, thereby addressing data-silo challenges while satisfying privacy-compliance requirements. Existing differentially private vertical federated learning methods typically inject noise directly into exchanged gradients and embeddings, but under strong privacy constraints they suffer from degraded model accuracy, unstable convergence, and excessive communication overhead. To address these issues, this paper proposes FMVFed, a differentially private vertical federated learning framework based on the functional mechanism, which effectively balances privacy protection, model utility, and communication efficiency. FMVFed achieves differential privacy by injecting Gaussian noise into the coefficient space of the training objective, thereby avoiding the utility loss caused by directly perturbing high-dimensional vectors. Meanwhile, it introduces an adaptive random Top-$k$ Sparsification communication strategy to significantly reduce cross-party communication overhead. Experimental results show that even under a small privacy budget (e.g., $\varepsilon =1$), FMVFed outperforms methods that directly perturb algorithm outputs by 13.47%, 3.13%, and 2.43% on CIFAR-10, FashionMNIST, and MNIST, respectively.
Results show that clipping, perturbation, and the learning procedure jointly influence the observed privacy–utility behavior of centralized FL and sequential Decentralized Federated Learning.
AlsharifHasan Mohamad Aburbeian, M. Fernández-Veiga, A. Fernández-Vilas et al.· Future Internet· 0 citations
Federated Learning (FL) offers a paradigm for collaborative machine learning model training among clients, preserving data privacy by avoiding direct data sharing. However, the gradient information exchanged in FL has been shown to be vulnerable to Gradient Inversion Attacks (GIA), which can reconstruct sensitive user...
Peng-Xin Guo, Zi-Ying Huang, Shuang Zeng et al.· 0 citations
With the rapid advancement of edge computing, federated learning (FL) has become a widely adopted paradigm for artificial intelligence (AI) applications, especially when data privacy or limited computational resources prevent centralized training. However, even parameter-efficient methods like Low-Rank Adaptation (LoRA...
Meng-Yuan Zhang, Jia-Wei Zhang· IEEE Transactions on Network...· 0 citations
Across MNIST and CIFAR-10, the design matches or outperforms full-model private adaptation across privacy budgets and client heterogeneity, while reducing protected uplink by a factor of 2.67 at \(\varepsilon=16\) on CIFAR-10 with comparable future-client accuracy.
Yi-Lin Xu, Chun Hei Michael Shiu, Chih-Wei Ling et al.· arXiv.org· 0 citations
Federated learning trains a shared model across many decentralized clients while keeping raw data on the device, which addresses data silos and tightening privacy regulation such as GDPR and HIPAA. This paper reviews the methods and the practical trade-offs of federated and privacy-preserving machine learning. The disc...
Saritha E· Eduschool International Jour...· 0 citations
Real-world deployment of federated learning (FL) requires resilience against adversarial clients and data privacy. Byzantine fault captures the worst-case behavior of adversarial clients, while differential privacy (DP) provides statistical guarantees against privacy loss. In particular, user-level DP guards a client's...
Ming Xiang, Stratis Ioannidis, Edmund Yeh et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.