Network-Level Adversaries in Federated Learning

TL;DR

This paper investigates how network-level adversaries can disrupt federated learning by dropping or poisoning client communications, and proposes defenses to mitigate these attacks.

Contribution

It introduces new network-level attack strategies in federated learning and develops a server-side defense mechanism to counteract these threats.

Findings

Dropping traffic from key clients reduces model accuracy.

Coordinated poisoning amplifies attack effectiveness.

Proposed defense improves model robustness against network attacks.

Abstract

Federated learning is a popular strategy for training models on distributed, sensitive data, while preserving data privacy. Prior work identified a range of security threats on federated learning protocols that poison the data or the model. However, federated learning is a networked system where the communication between clients and server plays a critical role for the learning task performance. We highlight how communication introduces another vulnerability surface in federated learning and study the impact of network-level adversaries on training federated learning models. We show that attackers dropping the network traffic from carefully selected clients can significantly decrease model accuracy on a target population. Moreover, we show that a coordinated poisoning campaign from a few clients can amplify the dropping attacks. Finally, we develop a server-side defense which mitigates the impact of our attacks by identifying and up-sampling clients likely to positively contribute towards target accuracy. We comprehensively evaluate our attacks and defenses on three datasets, assuming encrypted communication channels and attackers with partial visibility of the network.