Resilient Nash Equilibrium Seeking in the Partial Information Setting

TL;DR

This paper introduces a distributed Nash equilibrium seeking algorithm that is resilient to adversarial misinformation, communication failures, and attacks, ensuring convergence to the NE despite unverified and potentially false information.

Contribution

It proposes a novel resilient NE seeking algorithm that leverages observation and communication graphs to filter misinformation and withstand various network attacks.

Findings

Algorithm converges to Nash equilibrium despite adversarial agents.

Resilience against communication failures and external attacks demonstrated.

Effective filtering of false information using dual-graph approach.

Abstract

Current research in distributed Nash equilibrium (NE) seeking in the partial information setting assumes that information is exchanged between agents that are "truthful". However, in general noncooperative games agents may consider sending misinformation to neighboring agents with the goal of further reducing their cost. Additionally, communication networks are vulnerable to attacks from agents outside the game as well as communication failures. In this paper, we propose a distributed NE seeking algorithm that is robust against adversarial agents that transmit noise, random signals, constant singles, deceitful messages, as well as being resilient to external factors such as dropped communication, jammed signals, and man in the middle attacks. The core issue that makes the problem challenging is that agents have no means of verifying if the information they receive is correct, i.e. there is no "ground truth". To address this problem, we use an observation graph, that gives truthful action information, in conjunction with a communication graph, that gives (potentially incorrect) information. By filtering information obtained from these two graphs, we show that our algorithm is resilient against adversarial agents and converges to the Nash equilibrium.