DPZV: Elevating the Tradeoff between Privacy and Utility in Zeroth-Order Vertical Federated Learning

• URL: http://arxiv.org/abs/2502.20565v2
• Date: Mon, 19 May 2025 14:40:29 GMT
• Title: DPZV: Elevating the Tradeoff between Privacy and Utility in Zeroth-Order Vertical Federated Learning
• Authors: Jianing Zhang, Evan Chen, Chaoyue Liu, Christopher G. Brinton,
• Abstract summary: We propose DPZV, the first ZO optimization framework for Vertical Federated Learning (VFL) that achieves tunable differential privacy with performance guarantees.<n>We conduct a comprehensive theoretical analysis showing that DPZV matches the convergence rate of first-order optimization methods while satisfying formal ($epsilon, delta$)-DP guarantees.<n>Experiments on image and language benchmarks demonstrate that DPZV outperforms several baselines in terms of accuracy under a wide range of privacy constraints.
• Score: 9.302691218735406
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vertical Federated Learning (VFL) enables collaborative training with feature-partitioned data, yet remains vulnerable to privacy leakage through gradient transmissions. Standard differential privacy (DP) techniques such as DP-SGD are difficult to apply in this setting due to VFL's distributed nature and the high variance incurred by vector-valued noise. On the other hand, zeroth-order (ZO) optimization techniques can avoid explicit gradient exposure but lack formal privacy guarantees. In this work, we propose DPZV, the first ZO optimization framework for VFL that achieves tunable DP with performance guarantees. DPZV overcomes these limitations by injecting low-variance scalar noise at the server, enabling controllable privacy with reduced memory overhead. We conduct a comprehensive theoretical analysis showing that DPZV matches the convergence rate of first-order optimization methods while satisfying formal ($\epsilon, \delta$)-DP guarantees. Experiments on image and language benchmarks demonstrate that DPZV outperforms several baselines in terms of accuracy under a wide range of privacy constraints ($\epsilon \le 10$), thereby elevating the privacy-utility tradeoff in VFL.

Related papers

• Machine Learning with Privacy for Protected Attributes [56.44253915927481]
  We refine the definition of differential privacy (DP) to create a more general and flexible framework that we call feature differential privacy (FDP)<n>Our definition is simulation-based and allows for both addition/removal and replacement variants of privacy, and can handle arbitrary separation of protected and non-protected features.<n>We apply our framework to various machine learning tasks and show that it can significantly improve the utility of DP-trained models when public features are available.
  arXiv  Detail & Related papers  (2025-06-24T17:53:28Z)
• Linear-Time User-Level DP-SCO via Robust Statistics [55.350093142673316]
  User-level differentially private convex optimization (DP-SCO) has garnered significant attention due to the importance of safeguarding user privacy in machine learning applications.<n>Current methods, such as those based on differentially private gradient descent (DP-SGD), often struggle with high noise accumulation and suboptimal utility.<n>We introduce a novel linear-time algorithm that leverages robust statistics, specifically the median and trimmed mean, to overcome these challenges.
  arXiv  Detail & Related papers  (2025-02-13T02:05:45Z)
• Providing Differential Privacy for Federated Learning Over Wireless: A Cross-layer Framework [19.381425127772054]
  Federated Learning (FL) is a distributed machine learning framework that inherently allows edge devices to maintain their local training data.<n>We propose a wireless physical layer (PHY) design for OTA-FL which improves differential privacy (DP) through a decentralized, dynamic power control.<n>This adaptation showcases the flexibility and effectiveness of our design across different learning algorithms while maintaining a strong emphasis on privacy.
  arXiv  Detail & Related papers  (2024-12-05T18:27:09Z)
• Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings [23.687702204151872]
  Textual Inversion (TI) learns an embedding vector for an image or set of images, to enable adaptation under differential privacy constraints.<n>We show DPAgg-TI outperforms DP-SGD finetuning in both utility and robustness under the same privacy budget.
  arXiv  Detail & Related papers  (2024-11-22T00:09:49Z)
• DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction [57.83978915843095]
  This paper introduces DiSK, a novel framework designed to significantly enhance the performance of differentially private gradients.<n>To ensure practicality for large-scale training, we simplify the Kalman filtering process, minimizing its memory and computational demands.
  arXiv  Detail & Related papers  (2024-10-04T19:30:39Z)
• Convergent Differential Privacy Analysis for General Federated Learning: the $f$-DP Perspective [57.35402286842029]
  Federated learning (FL) is an efficient collaborative training paradigm with a focus on local privacy. differential privacy (DP) is a classical approach to capture and ensure the reliability of private protections.
  arXiv  Detail & Related papers  (2024-08-28T08:22:21Z)
• Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence [22.946928984205588]
  Differentially private federated learning (DP-FL) is a promising technique for collaborative model training. We propose the first DP-FL framework (namely UDP-FL) which universally harmonizes any randomization mechanism. We show that UDP-FL exhibits substantial resilience against different inference attacks.
  arXiv  Detail & Related papers  (2024-07-20T00:11:59Z)
• Share Your Secrets for Privacy! Confidential Forecasting with Vertical Federated Learning [5.584904689846748]
  Key challenges to address in manufacturing include data privacy and over-fitting on small and noisy datasets. We propose 'Secret-shared Time Series Forecasting with VFL', a novel framework that exhibits the following key features. Our results demonstrate that STV's forecasting accuracy is comparable to those of centralized approaches.
  arXiv  Detail & Related papers  (2024-05-31T12:27:38Z)
• TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data [50.797729676285876]
  We propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously. We theoretically quantify the privacy guarantee through the lens of the emerging f-differential privacy (DP) and the Byzantine resilience of the proposed algorithm.
  arXiv  Detail & Related papers  (2024-02-16T16:41:14Z)
• Binary Federated Learning with Client-Level Differential Privacy [7.854806519515342]
  Federated learning (FL) is a privacy-preserving collaborative learning framework. Existing FL systems typically adopt Federated Average (FedAvg) as the training algorithm. We propose a communication-efficient FL training algorithm with differential privacy guarantee.
  arXiv  Detail & Related papers  (2023-08-07T06:07:04Z)
• Differentially Private Wireless Federated Learning Using Orthogonal Sequences [56.52483669820023]
  We propose a privacy-preserving uplink over-the-air computation (AirComp) method, termed FLORAS. We prove that FLORAS offers both item-level and client-level differential privacy guarantees. A new FL convergence bound is derived which, combined with the privacy guarantees, allows for a smooth tradeoff between the achieved convergence rate and differential privacy levels.
  arXiv  Detail & Related papers  (2023-06-14T06:35:10Z)
• sqSGD: Locally Private and Communication Efficient Federated Learning [14.60645909629309]
  Federated learning (FL) is a technique that trains machine learning models from decentralized data sources. We develop a gradient-based learning algorithm called sqSGD that addresses communication efficiency and high-dimensional compatibility. Experiment results show sqSGD successfully learns large models like LeNet and ResNet with local privacy constraints.
  arXiv  Detail & Related papers  (2022-06-21T17:45:35Z)
• Decentralized Stochastic Optimization with Inherent Privacy Protection [103.62463469366557]
  Decentralized optimization is the basic building block of modern collaborative machine learning, distributed estimation and control, and large-scale sensing. Since involved data, privacy protection has become an increasingly pressing need in the implementation of decentralized optimization algorithms.
  arXiv  Detail & Related papers  (2022-05-08T14:38:23Z)
• Desirable Companion for Vertical Federated Learning: New Zeroth-Order Gradient Based Algorithm [140.25480610981504]
  A complete list of metrics to evaluate VFL algorithms should include model applicability, privacy, communication, and computation efficiency. We propose a novel VFL framework with black-box scalability, which is inseparably inseparably scalable.
  arXiv  Detail & Related papers  (2022-03-19T13:55:47Z)
• Differentially Private Federated Bayesian Optimization with Distributed Exploration [48.9049546219643]
  We introduce differential privacy (DP) into the training of deep neural networks through a general framework for adding DP to iterative algorithms. We show that DP-FTS-DE achieves high utility (competitive performance) with a strong privacy guarantee. We also use real-world experiments to show that DP-FTS-DE induces a trade-off between privacy and utility.
  arXiv  Detail & Related papers  (2021-10-27T04:11:06Z)
• Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updating [159.48259714642447]
  Vertical scalable learning (VFL) attracts increasing attention due to the demands of multi-party collaborative modeling and concerns of privacy leakage. We propose a novel bftextlevel parallel architecture (VF$bfB2$), under which three new algorithms, including VF$B2$, are proposed.
  arXiv  Detail & Related papers  (2021-03-01T12:34:53Z)
• Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization [27.243322019117144]
  Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. We propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient perturbation on each agent to amplify privacy guarantee.
  arXiv  Detail & Related papers  (2020-08-01T20:22:57Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)
• User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization [77.43075255745389]
  Federated learning (FL) is capable of preserving private data from mobile terminals (MTs) while training the data into useful models. From a viewpoint of information theory, it is still possible for a curious server to infer private information from the shared models uploaded by MTs. We propose a user-level differential privacy (UDP) algorithm by adding artificial noise to the shared models before uploading them to servers.
  arXiv  Detail & Related papers  (2020-02-29T10:13:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.