Paper 2024/671
Exploiting Internal Randomness for Privacy in Vertical Federated Learning
Abstract
Vertical Federated Learning (VFL) is becoming a standard collaborative learning paradigm with various practical applications. Randomness is essential to enhancing privacy in VFL, but introducing too much external randomness often leads to an intolerable performance loss. Instead, as it was demonstrated for other federated learning settings, leveraging internal randomness —as provided by variational autoencoders (VAEs) —can be beneficial. However, the resulting privacy has never been quantified so far, nor has the approach been investigated for VFL. We therefore propose a novel differential privacy (DP) estimate, denoted as distance-based empirical local differential privacy (dELDP). It allows us to empirically bound DP parameters of models or model components, quantifying the internal randomness with appropriate distance and sensitivity metrics. We apply dELDP to investigate the DP of VAEs and observe values up to ε ≈ 6.4 and δ = 2−32. Based on this, to link the dELDP parameters to the privacy of VAE-including VFL systems in practice, we conduct comprehensive experiments on the robustness against state-of-the-art privacy attacks. The results illustrate that the VAE system is robust against feature reconstruction attacks and outperforms other privacy-enhancing methods for VFL, especially when the adversary holds 75% of the features during label inference attacks.
Metadata
- Available format(s)
-
PDF
- Category
- Applications
- Publication info
- Preprint.
- Keywords
- privacyVFLdistance-based empirical DPVAE
- Contact author(s)
-
yulian sun @ edu ruhr-uni-bochum de
liduan @ mail upb de
ricardo mendes1 @ huawei com
derui zhu @ tum de
yue1 xia @ tum de
yong li1 @ huawei com
asja fischer @ rub de - History
- 2024-07-01: revised
- 2024-05-02: received
- See all versions
- Short URL
- https://ia.cr/2024/671
- License
-
CC BY-NC
BibTeX
@misc{cryptoeprint:2024/671,
author = {Yulian Sun and Li Duan and Ricardo Mendes and Derui Zhu and Yue Xia and Yong Li and Asja Fischer},
title = {Exploiting Internal Randomness for Privacy in Vertical Federated Learning},
howpublished = {Cryptology {ePrint} Archive, Paper 2024/671},
year = {2024},
url = {https://eprint.iacr.org/2024/671}
}