On Poisoned Wardrop Equilibrium in Congestion Games

TL;DR

This paper introduces a game-theoretic framework to analyze how informational poisoning attacks can manipulate traffic patterns in congestion networks, quantifying their impact through the poisoned Price of Anarchy.

Contribution

It develops a novel Stackelberg game model for informational attacks on traffic equilibria and introduces the poisoned Price of Anarchy to measure attack impact.

Findings

Poisoned Wardrop equilibria can be strategically manipulated by attackers.

The poisoned Price of Anarchy quantifies the efficiency loss due to attacks.

A two-time scale zeroth-order learning process can find Stackelberg equilibria.

Abstract

Recent years have witnessed a growing number of attack vectors against increasingly interconnected traffic networks. Informational attacks have emerged as the prominent ones that aim to poison traffic data, misguide users, and manipulate traffic patterns. To study the impact of this class of attacks, we propose a game-theoretic framework where the attacker, as a Stackelberg leader, falsifies the traffic conditions to change the traffic pattern predicted by the Wardrop traffic equilibrium, achieved by the users, or the followers. The intended shift of the Wardrop equilibrium is a consequence of strategic informational poisoning. Leveraging game-theoretic and sensitivity analysis, we quantify the system-level impact of the attack by characterizing the concept of poisoned Price of Anarchy, which compares the poisoned Wardrop equilibrium and its non-poisoned system optimal counterpart. We use an evacuation case study to show that the Stackelberg equilibrium can be found through a two-time scale zeroth-order learning process and demonstrate the disruptive effects of informational poisoning, indicating a compelling need for defense policies to mitigate such security threats.