# Hybrid Differentially Private Federated Learning on Vertically Partitioned Data

arXiv: https://arxiv.org/abs/2009.02763 · HTML: https://mlsanity.com/paper/2009.02763/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2020.

## Built on by (most cited first, 22 of 22)

- [Vertical Federated Learning: Concepts, Advances and Challenges](https://mlsanity.com/paper/2211.12814/) (2022)
- [Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges](https://mlsanity.com/paper/2201.08135/) (2022)
- [A Survey on Heterogeneous Federated Learning](https://mlsanity.com/paper/2210.04505/) (2022)
- [FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Data](https://mlsanity.com/paper/2103.03918/) (2021)
- [A Survey on Vertical Federated Learning: From a Layered Perspective](https://mlsanity.com/paper/2304.01829/) (2023)
- [Differentially Private Label Protection in Split Learning](https://mlsanity.com/paper/2203.02073/) (2022)
- [Vertical Federated Learning: A Structured Literature Review](https://mlsanity.com/paper/2212.00622/) (2022)
- [FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models](https://mlsanity.com/paper/2304.13407/) (2023)
- [Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges](https://mlsanity.com/paper/2407.06754/) (2024)
- [Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey](https://mlsanity.com/paper/2405.17495/) (2024)
- [Differentially Private Vertical Federated Clustering](https://mlsanity.com/paper/2208.01700/) (2022)
- [Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data](https://mlsanity.com/paper/2410.17986/) (2024)
- [A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective](https://mlsanity.com/paper/2402.03688/) (2024)
- [Subject Granular Differential Privacy in Federated Learning](https://mlsanity.com/paper/2206.03617/) (2022)
- [Differentially Private Vertical Federated Learning](https://mlsanity.com/paper/2211.06782/) (2022)
- [URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning](https://mlsanity.com/paper/2404.19582/) (2024)
- [The Sherpa.ai Blind Vertical Federated Learning Paradigm to Minimize the Number of Communications](https://mlsanity.com/paper/2510.17901/) (2025)
- [FedEmb: A Vertical and Hybrid Federated Learning Algorithm using Network And Feature Embedding Aggregation](https://mlsanity.com/paper/2312.00102/) (2023)
- [Flexible Differentially Private Vertical Federated Learning with Adaptive Feature Embeddings](https://mlsanity.com/paper/2308.02362/) (2023)
- [A Novel Framework of Horizontal-Vertical Hybrid Federated Learning for EdgeIoT](https://mlsanity.com/paper/2410.01644/) (2024)
- [Differentially Private Distributed Convex Optimization](https://mlsanity.com/paper/2302.14514/) (2023)
- [Secure and Privacy-Preserving Vertical Federated Learning](https://mlsanity.com/paper/2604.13474/) (2026)

## Abstract (arXiv)

We present HDP-VFL, the first hybrid differentially private (DP) framework for vertical federated learning (VFL) to demonstrate that it is possible to jointly learn a generalized linear model (GLM) from vertically partitioned data with only a negligible cost, w.r.t. training time, accuracy, etc., comparing to idealized non-private VFL. Our work builds on the recent advances in VFL-based collaborative training among different organizations which rely on protocols like Homomorphic Encryption (HE) and Secure Multi-Party Computation (MPC) to secure computation and training. In particular, we analyze how VFL's intermediate result (IR) can leak private information of the training data during communication and design a DP-based privacy-preserving algorithm to ensure the data confidentiality of VFL participants. We mathematically prove that our algorithm not only provides utility guarantees for VFL, but also offers multi-level privacy, i.e. DP w.r.t. IR and joint differential privacy (JDP) w.r.t. model weights. Experimental results demonstrate that our work, under adequate privacy budgets, is quantitatively and qualitatively similar to GLMs, learned in idealized non-private VFL setting, rather than the increased cost in memory and processing time in most prior works based on HE or MPC. Our codes will be released if this paper is accepted.