paper-with-me

Papers

Protecting Data from all Parties: Combining FHE and DP in Federated Learning

2022-05-09 · Arnaud Grivet Sébert, Renaud Sirdey, Oana Stan, Cédric Gouy-Pailler

This paper tackles the problem of ensuring training data privacy in a federated learning context. Relying on Homomorphic Encryption (HE) and Differential Privacy (DP), we propose a framework addressing threats on the privacy of the training data. Notably, the proposed framework ensures the privacy of the training data from all actors of the learning process, namely the data owners and the aggregating server. More precisely, while HE blinds a semi-honest server during the learning protocol, DP protects the data from semi-honest clients participating in the training process as well as end-users with black-box or white-box access to the trained model. In order to achieve this, we provide new theoretical and practical results to allow these techniques to be rigorously combined. In particular, by means of a novel stochastic quantisation operator, we prove DP guarantees in a context where the noise is quantised and bounded due to the use of HE. The paper is concluded by experiments which show the practicality of the entire framework in terms of both model quality (impacted by DP) and computational overhead (impacted by HE).

📄 PDF Abstract BibTeX arXiv:2205.04330

Code (0)

등록된 구현이 없습니다.

Tasks

AllFederated LearningQuantization

Similar Papers 제목 키워드 기반

Measure Contribution of Participants in Federated Learning

2019-09-17 · Guan Wang, Charlie Xiaoqian Dang, Ziye Zhou

Federated Machine Learning (FML) creates an ecosystem for multiple parties to collaborate on building models while protecting data privacy for the participants. A measure of the contribution for each party in FML enables…

BIG-bench Machine LearningFeature ImportanceFederated Learning

Differentially-private Federated Neural Architecture Search

2020-06-16 · Ishika Singh, Haoyi Zhou, Kunlin Yang, Meng Ding 외

Neural architecture search, which aims to automatically search for architectures (e.g., convolution, max pooling) of neural networks that maximize validation performance, has achieved remarkable progress recently. In man…

Neural Architecture Search

Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data

2024-10-23 · Zhaomin Wu, Junyi Hou, Yiqun Diao, Bingsheng He

Federated Learning (FL) is an evolving paradigm that enables multiple parties to collaboratively train models without sharing raw data. Among its variants, Vertical Federated Learning (VFL) is particularly relevant in re…

Entity AlignmentFederated LearningVertical Federated Learning

Robust and IP-Protecting Vertical Federated Learning against Unexpected Quitting of Parties

2023-03-28 · Jingwei Sun, Zhixu Du, Anna Dai, Saleh Baghersalimi 외

Vertical federated learning (VFL) enables a service provider (i.e., active party) who owns labeled features to collaborate with passive parties who possess auxiliary features to improve model performance. Existing VFL ap…

Federated LearningVertical Federated Learning

FedZKP: Federated Model Ownership Verification with Zero-knowledge Proof

2023-05-08 · Wenyuan Yang, Yuguo Yin, Gongxi Zhu, Hanlin Gu 외

Federated learning (FL) allows multiple parties to cooperatively learn a federated model without sharing private data with each other. The need of protecting such federated models from being plagiarized or misused, there…

Federated Learning