Enhancing Security and Privacy in Federated Learning using Low-Dimensional Update Representation and Proximity-Based Defense

TL;DR

FLURP enhances federated learning by using low-dimensional update representations and proximity-based defenses to improve security, privacy, and efficiency against malicious attacks with minimal communication overhead.

Contribution

The paper introduces FLURP, a novel framework that reduces computational overhead and enhances privacy and security in federated learning through low-dimensional update representations and proximity-based defenses.

Findings

FLURP effectively detects malicious updates with low communication overhead.

The framework reduces Secure Multi-Party Computation overhead by three orders of magnitude.

Experiments show FLURP's robustness against Byzantine adversaries.

Abstract

Federated Learning (FL) is a promising privacy-preserving machine learning paradigm that allows data owners to collaboratively train models while keeping their data localized. Despite its potential, FL faces challenges related to the trustworthiness of both clients and servers, particularly against curious or malicious adversaries. In this paper, we introduce a novel framework named \underline{F}ederated \underline{L}earning with Low-Dimensional \underline{U}pdate \underline{R}epresentation and \underline{P}roximity-Based defense (FLURP), designed to address privacy preservation and resistance to Byzantine attacks in distributed learning environments. FLURP employs $\mathsf{LinfSample}$ method, enabling clients to compute the $l_{\infty}$ norm across sliding windows of updates, resulting in a Low-Dimensional Update Representation (LUR). Calculating the shared distance matrix among LURs, rather than updates, significantly reduces the overhead of Secure Multi-Party Computation (SMPC) by three orders of magnitude while effectively distinguishing between benign and poisoned updates. Additionally, FLURP integrates a privacy-preserving proximity-based defense mechanism utilizing optimized SMPC protocols to minimize communication rounds. Our experiments demonstrate FLURP's effectiveness in countering Byzantine adversaries with low communication and runtime overhead. FLURP offers a scalable framework for secure and reliable FL in distributed environments, facilitating its application in scenarios requiring robust data management and security.