Beyond Class-Level Privacy Leakage: Breaking Record-Level Privacy in Federated Learning
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Internet of Things Journal"
DOI: 10.1109/jiot.2021.3089713
Abstract: Federated learning (FL) enables multiple clients to collaboratively build a global learning model without sharing their own raw data for privacy protection. Unfortunately, recent research still found privacy leakage in FL, especially on image classification… read more here.
Keywords: privacy leakage; level; privacy; record level ... See more keywords
Analyzing User-Level Privacy Attack Against Federated Learning
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Journal on Selected Areas in Communications"
DOI: 10.1109/jsac.2020.3000372
Abstract: Federated learning has emerged as an advanced privacy-preserving learning technique for mobile edge computing, where the model is trained in a decentralized manner by the clients, preventing the server from directly accessing those private data… read more here.
Keywords: federated learning; level privacy; user level; client ... See more keywords