paper-with-me

홈 › Papers

Secure and Privacy-Preserving Federated Learning via Co-Utility

2021-08-04 · Josep Domingo-Ferrer, Alberto Blanco-Justicia, Jesús Manjón, David Sánchez

The decentralized nature of federated learning, that often leverages the power of edge devices, makes it vulnerable to attacks against privacy and security. The privacy risk for a peer is that the model update she computes on her private data may, when sent to the model manager, leak information on those private data. Even more obvious are security attacks, whereby one or several malicious peers return wrong model updates in order to disrupt the learning process and lead to a wrong model being learned. In this paper we build a federated learning framework that offers privacy to the participating peers as well as security against Byzantine and poisoning attacks. Our framework consists of several protocols that provide strong privacy to the participating peers via unlinkable anonymity and that are rationally sustainable based on the co-utility property. In other words, no rational party is interested in deviating from the proposed protocols. We leverage the notion of co-utility to build a decentralized co-utile reputation management system that provides incentives for parties to adhere to the protocols. Unlike privacy protection via differential privacy, our approach preserves the values of model updates and hence the accuracy of plain federated learning; unlike privacy protection via update aggregation, our approach preserves the ability to detect bad model updates while substantially reducing the computational overhead compared to methods based on homomorphic encryption.

📄 PDF Abstract BibTeX arXiv:2108.01913

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningManagementPrivacy Preserving

Similar Papers 제목 키워드 기반

FastLloyd: Federated, Accurate, Secure, and Tunable $k$-Means Clustering with Differential Privacy

2024-05-03 · Abdulrahman Diaa, Thomas Humphries, Florian Kerschbaum

We study the problem of privacy-preserving $k$-means clustering in the horizontally federated setting. Existing federated approaches using secure computation suffer from substantial overheads and do not offer output priv…

ClusteringConstrained ClusteringPrivacy Preserving

No Free Lunch Theorem for Security and Utility in Federated Learning

2022-03-11 · Xiaojin Zhang, Hanlin Gu, Lixin Fan, Kai Chen 외

In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms. On one hand, private and sensitive tra…

Federated LearningPrivacy Preserving

SecureBoost Hyperparameter Tuning via Multi-Objective Federated Learning

2023-07-20 · Ziyao Ren, Yan Kang, Lixin Fan, Linghua Yang 외

SecureBoost is a tree-boosting algorithm leveraging homomorphic encryption to protect data privacy in vertical federated learning setting. It is widely used in fields such as finance and healthcare due to its interpretab…

Federated LearningPrivacy PreservingVertical Federated Learning

Concentrated Differentially Private and Utility Preserving Federated Learning

2020-03-30 · Rui Hu, Yuanxiong Guo, Yanmin Gong

Federated learning is a machine learning setting where a set of edge devices collaboratively train a model under the orchestration of a central server without sharing their local data. At each communication round of fede…

Federated LearningPrivacy Preserving

SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs

2026-02-13 · Mohamed Shaaban, Mohamed Elmahallawy arxiv

Federated learning (FL) enables collaborative training across organizational silos without sharing raw data, making it attractive for privacy-sensitive applications. With the rapid adoption of large language models (LLMs…

Federated Learning