Communication-Efficient and Differentially Private Vertical Federated Learning with Zeroth-Order Optimization
Not on the map. Why?
Abstract (arXiv)
Vertical Federated Learning (VFL) enables collaborative model training across feature-partitioned devices, yet its reliance on device-server information exchange introduces significant communication overhead and privacy risks. Downlink communication from the server to devices in VFL exposes gradient-related signals of the global loss that can be leveraged in inference attacks. Existing privacy-preserving VFL approaches that inject differential privacy (DP) noise on the downlink have the natural repercussion of degraded gradient quality, slowed convergence, and excessive communication rounds. In this work, we propose DPZV, a communication-efficient and differentially private ZO-VFL framework with tunable privacy guarantees. Based on zeroth-order (ZO) optimization, DPZV injects calibrated scalar-valued DP noise on the downlink, significantly reducing variance amplification while providing equivalent protection against targeted inference attacks. Through rigorous theoretical analysis, we establish convergence guarantees comparable to first-order DP-SGD, despite relying solely on ZO estimators, and prove that DPZV satisfies (ε, δ)-DP. Extensive experiments demonstrate that DPZV consistently achieves a superior privacy-utility tradeoff and requires fewer communication rounds than existing DP-VFL baselines under strict privacy constraints (ε ≤ 10).
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 30 of its 46 references that are in the map. First posted on arXiv 27 Feb 2025.
Builds on
30 of 46 references.
References · 30
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2013Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programmingcited by 724
- 2023Fine-Tuning Language Models with Just Forward Passescited by 345
- 2019Why gradient clipping accelerates training: A theoretical justification for adaptivitycited by 341
- 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176
- 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 176
- 2020Understanding Gradient Clipping in Private SGD: A Geometric Perspectivecited by 142
- 2015An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedbackcited by 111
- 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
- 2020Byzantine-Resilient Secure Federated Learningcited by 93
- 2018Wireless Network Intelligence at the Edgecited by 92
18 more
- 2020Privacy Preserving Vertical Federated Learning for Tree-based Modelscited by 89
- 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
- 2022Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learningcited by 59
- 2019HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learningcited by 51
- 2024Private Fine-tuning of Large Language Models with Zeroth-order Optimizationcited by 41
- 2021FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Datacited by 31
- 2020Backdoor attacks and defenses in feature-partitioned collaborative learningcited by 30
- 2020Federated Learning and Wireless Communicationscited by 27
- 2023DPZero: Private Fine-Tuning of Language Models without Backpropagationcited by 26
- 2022Flexible Vertical Federated Learning with Heterogeneous Partiescited by 20
- 2023LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learningcited by 14
- 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
- 2022Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learningcited by 13
- 2022Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMMcited by 10
- 2022Desirable Companion for Vertical Federated Learning: New Zeroth-Order Gradient Based Algorithmcited by 9
- 2020Practical Privacy Attacks on Vertical Federated Learningcited by 3
- 2025Cooperative Decentralized Backdoor Attacks on Vertical Federated Learningcited by 3
- 2022Nonparametric Decentralized Detection and Sparse Sensor Selection via Multi-Sensor Online Kernel Scalar Quantizationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.