Harmful Bias: A General Label-Leakage Attack on Federated Learning from Bias Gradients
Year: 2024
Type: conference-paper
Abstract: Federated learning (FL) enables several users to train machine-learning models jointly without explicitly sharing data with one another. This regime is particularly helpful in cases where keeping the data private and secure is essential (e.g., medical records). However, recent work has shown that FL does not guarantee privacy--in classification tasks, the training-data labels, and even the inputs, may be reconstructed from information users share during training.
Authors: Nadav Gat, Mahmood Sharif
Institution: Tel Aviv University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Funder: Universitas Brawijaya
OpenAlex ID: W4404612273