Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging

TL;DR

This paper introduces Adaptive Federated Averaging, a robust federated learning algorithm that detects and discards malicious updates using a Hidden Markov Model, improving robustness and efficiency against attacks and faulty data.

Contribution

The paper presents a novel adaptive aggregation method with a Hidden Markov Model to identify and exclude bad updates, enhancing robustness and efficiency in federated learning.

Findings

Outperforms Multi-KRUM and median methods in robustness.

Effectively detects malicious and noisy updates.

Reduces computational and communication costs.

Abstract

Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets. Standard federated learning techniques are vulnerable to Byzantine failures, biased local datasets, and poisoning attacks. In this paper we introduce Adaptive Federated Averaging, a novel algorithm for robust federated learning that is designed to detect failures, attacks, and bad updates provided by participants in a collaborative model. We propose a Hidden Markov Model to model and learn the quality of model updates provided by each participant during training. In contrast to existing robust federated learning schemes, we propose a robust aggregation rule that detects and discards bad or malicious local model updates at each training iteration. This includes a mechanism that blocks unwanted participants, which also increases the computational and communication efficiency. Our experimental evaluation on 4 real datasets show that our algorithm is significantly more robust to faulty, noisy and malicious participants, whilst being computationally more efficient than other state-of-the-art robust federated learning methods such as Multi-KRUM and coordinate-wise median.