Adversarial Reinforcement Learning for Detecting False Data Injection Attacks in Vehicular Routing

2026-03-11

AI Summary

This work addresses the vulnerability of traffic networks to false data injection attacks—such as fabricated congestion reports—that mislead vehicle routing decisions and exacerbate traffic congestion. To counter this threat, the paper proposes a zero-sum game–based adversarial multi-agent reinforcement learning framework, which, to the best of our knowledge, is the first application of such an approach to detecting false data attacks in vehicular routing. By modeling the attacker and defender as opposing players in a zero-sum game and computing the Nash equilibrium, the method yields a theoretically grounded, robust detection policy that minimizes the worst-case total travel time. Experimental results demonstrate that the proposed approach effectively approximates equilibrium strategies and significantly outperforms existing baselines in both defensive and offensive capabilities, thereby substantially enhancing the resilience of traffic networks against adversarial attacks.

Technology Category

• Multiagent Systems: Adversarial Agents
• Computer Vision: Adversarial Attacks & Robustness
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

In modern transportation networks, adversaries can manipulate routing algorithms using false data injection attacks, such as simulating heavy traffic with multiple devices running crowdsourced navigation applications, to mislead vehicles toward suboptimal routes and increase congestion. To address these threats, we formulate a strategically zero-sum game between an attacker, who injects such perturbations, and a defender, who detects anomalies based on the observed travel times of network edges. We propose a computational method based on multi-agent reinforcement learning to compute a Nash equilibrium of this game, providing an optimal detection strategy, which ensures that total travel time remains within a worst-case bound, even in the presence of an attack. We present an extensive experimental evaluation that demonstrates the robustness and practical benefits of our approach, providing a powerful framework to improve the resilience of transportation networks against false data injection. In particular, we show that our approach yields approximate equilibrium policies and significantly outperforms baselines for both the attacker and the defender.

Problem

• False Data Injection Attacks
• Vehicular Routing
• Adversarial Reinforcement Learning
• Anomaly Detection
• Transportation Networks

Innovation

• Adversarial Reinforcement Learning
• False Data Injection Attacks
• Multi-agent Reinforcement Learning
• Nash Equilibrium
• Vehicular Routing