# Flexible Differentially Private Vertical Federated Learning with Adaptive Feature Embeddings

arXiv: https://arxiv.org/abs/2308.02362 · HTML: https://mlsanity.com/paper/2308.02362/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 26 Jul 2023.

## Builds on (most cited first, 20 of 20)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Enhanced Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/2111.09679/) (2021)
- [Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption](https://mlsanity.com/paper/1711.10677/) (2017)
- [Feature Inference Attack on Model Predictions in Vertical Federated Learning](https://mlsanity.com/paper/2010.10152/) (2020)
- [Privacy Preserving Vertical Federated Learning for Tree-based Models](https://mlsanity.com/paper/2008.06170/) (2020)
- [VAFL: a Method of Vertical Asynchronous Federated Learning](https://mlsanity.com/paper/2007.06081/) (2020)
- [CAFE: Catastrophic Data Leakage in Vertical Federated Learning](https://mlsanity.com/paper/2110.15122/) (2021)
- [SplitNN-driven Vertical Partitioning](https://mlsanity.com/paper/2008.04137/) (2020)
- [A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression](https://mlsanity.com/paper/1912.00513/) (2019)
- [FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Data](https://mlsanity.com/paper/2103.03918/) (2021)
- [Hybrid Differentially Private Federated Learning on Vertically Partitioned Data](https://mlsanity.com/paper/2009.02763/) (2020)
- [Flexible Vertical Federated Learning with Heterogeneous Parties](https://mlsanity.com/paper/2208.12672/) (2022)
- [Efficient passive membership inference attack in federated learning](https://mlsanity.com/paper/2111.00430/) (2021)
- [Learning Privately over Distributed Features: An ADMM Sharing Approach](https://mlsanity.com/paper/1907.07735/) (2019)
- [Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning](https://mlsanity.com/paper/2210.06771/) (2022)
- [Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM](https://mlsanity.com/paper/2207.10226/) (2022)
- [Differentially Private Vertical Federated Learning](https://mlsanity.com/paper/2211.06782/) (2022)

## Built on by (most cited first, 1 of 1)

- [Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning](https://mlsanity.com/paper/2412.11689/) (2024)

## Abstract (arXiv)

The emergence of vertical federated learning (VFL) has stimulated concerns about the imperfection in privacy protection, as shared feature embeddings may reveal sensitive information under privacy attacks. This paper studies the delicate equilibrium between data privacy and task utility goals of VFL under differential privacy (DP). To address the generality issue of prior arts, this paper advocates a flexible and generic approach that decouples the two goals and addresses them successively. Specifically, we initially derive a rigorous privacy guarantee by applying norm clipping on shared feature embeddings, which is applicable across various datasets and models. Subsequently, we demonstrate that task utility can be optimized via adaptive adjustments on the scale and distribution of feature embeddings in an accuracy-appreciative way, without compromising established DP mechanisms. We concretize our observation into the proposed VFL-AFE framework, which exhibits effectiveness against privacy attacks and the capacity to retain favorable task utility, as substantiated by extensive experiments.