FRIDA: Free-Rider Detection using Privacy Attacks

TL;DR

FRIDA is a novel method that detects free-riders in federated learning by leveraging privacy attacks to directly identify non-contributing participants, improving the integrity and efficiency of collaborative training.

Contribution

FRIDA introduces a privacy attack-based approach for free-rider detection, providing a direct and effective method to identify non-contributing clients in federated learning.

Findings

FRIDA effectively detects free-riders across various scenarios.

The approach improves the integrity of federated learning systems.

FRIDA demonstrates high accuracy in identifying non-contributing participants.

Abstract

Federated learning is increasingly popular as it enables multiple parties with limited datasets and resources to train a machine learning model collaboratively. However, similar to other collaborative systems, federated learning is vulnerable to free-riders - participants who benefit from the global model without contributing. Free-riders compromise the integrity of the learning process and slow down the convergence of the global model, resulting in increased costs for honest participants. To address this challenge, we propose FRIDA: free-rider detection using privacy attacks. Instead of focusing on implicit effects of free-riding, FRIDA utilizes membership and property inference attacks to directly infer evidence of genuine client training. Our extensive evaluation demonstrates that FRIDA is effective across a wide range of scenarios.