On the Resilience of Traffic Networks under Non-Equilibrium Learning

TL;DR

This paper studies the resilience of learning-based traffic navigation systems against data manipulation attacks, introducing a new solution concept and demonstrating that certain online learning algorithms can recover from attacks with bounded performance loss.

Contribution

It introduces the Wardrop Non-Equilibrium Solution (WANES) to analyze traffic flow under learning, and shows that mirror descent-based systems can recover from attacks with bounded performance degradation.

Findings

Traffic flow can recover to WANES after bounded attacks.

Resilience is demonstrated with a Sioux-Fall evacuation case study.

Performance loss is bounded by a sublinear order in time.

Abstract

We investigate the resilience of learning-based \textit{Intelligent Navigation Systems} (INS) to informational flow attacks, which exploit the vulnerabilities of IT infrastructure and manipulate traffic condition data. To this end, we propose the notion of \textit{Wardrop Non-Equilibrium Solution} (WANES), which captures the finite-time behavior of dynamic traffic flow adaptation under a learning process. The proposed non-equilibrium solution, characterized by target sets and measurement functions, evaluates the outcome of learning under a bounded number of rounds of interactions, and it pertains to and generalizes the concept of approximate equilibrium. Leveraging finite-time analysis methods, we discover that under the mirror descent (MD) online-learning framework, the traffic flow trajectory is capable of restoring to the Wardrop non-equilibrium solution after a bounded INS attack. The resulting performance loss is of order $\tilde{\mathcal{O}}(T^{\beta})$ ($-\frac{1}{2} \leq \beta < 0 )$), with a constant dependent on the size of the traffic network, indicating the resilience of the MD-based INS. We corroborate the results using an evacuation case study on a Sioux-Fall transportation network.