Secure Byzantine-Robust Machine Learning

TL;DR

This paper introduces a secure, communication-efficient two-server protocol for federated machine learning that ensures input privacy, Byzantine-robustness, fault tolerance, and local differential privacy, addressing multiple security concerns simultaneously.

Contribution

It presents a novel protocol combining privacy preservation and Byzantine robustness in distributed machine learning, which was rarely studied together before.

Findings

Protocol is secure against Byzantine failures.

Ensures input privacy and local differential privacy.

Achieves communication efficiency and fault tolerance.

Abstract

Increasingly machine learning systems are being deployed to edge servers and devices (e.g. mobile phones) and trained in a collaborative manner. Such distributed/federated/decentralized training raises a number of concerns about the robustness, privacy, and security of the procedure. While extensive work has been done in tackling with robustness, privacy, or security individually, their combination has rarely been studied. In this paper, we propose a secure two-server protocol that offers both input privacy and Byzantine-robustness. In addition, this protocol is communication-efficient, fault-tolerant and enjoys local differential privacy.