A Zeroth-order Resilient Algorithm for Distributed Online Optimization against Byzantine Edge Attacks

TL;DR

This paper introduces a zeroth-order resilient distributed online optimization algorithm designed to withstand Byzantine edge attacks in dynamic network environments, providing theoretical guarantees and simulation validation.

Contribution

It presents a novel zeroth-order distributed online algorithm that is resilient to Byzantine edge attacks and handles time-varying objectives with limited observability.

Findings

Provides an upper bound on dynamic regret.

Demonstrates effectiveness through simulation.

Ensures resilience against Byzantine edge attacks.

Abstract

In this paper, we propose a zeroth-order resilient distributed online algorithm for networks under Byzantine edge attacks. We assume that both the edges attacked by Byzantine adversaries and the objective function are time-varying. Moreover, we focus on the scenario where the complete time-varying objective function cannot be observed, and only its value at a certain point is available. Using deterministic difference, we design a zeroth-order distributed online optimization algorithm against Byzantine edge attacks and provide an upper bound on the dynamic regret of the algorithm. Finally, a simulation example is given justifying the theoretical results.