Game-Theoretic Foundations for Cyber Resilience Against Deceptive Information Attacks in Intelligent Transportation Systems

TL;DR

This work addresses the threat of deceptive information attacks in Intelligent Transportation Systems (ITS) by introducing a game-theoretic framework augmented with control and learning to model adversarial interactions across intra-vehicle, inter-vehicle, transportation infrastructure, and human domains. It develops a cross-layer resilience approach, including dynamic games, asymmetric-information handling, and learning-enabled adaptations, to assess risk and design adaptive defenses. The PRADA case study demonstrates a Stackelberg-based defense for navigational recommendation systems against misinformed demand attacks, using a three-layer analysis (UE, Stackelberg, meta-game) and metrics TI and NI to quantify risk. The results underscore the importance of trust-based, cross-domain resilience mechanisms that can adapt to evolving threats, offering actionable guidance for securing ITS in practice and guiding future extensions to spoofing, APTs, and DoS scenarios.

Abstract

The growing complexity and interconnectivity of Intelligent Transportation Systems (ITS) make them increasingly vulnerable to advanced cyber threats, particularly deceptive information attacks. These sophisticated threats exploit vulnerabilities to manipulate data integrity and decision-making processes through techniques such as data poisoning, spoofing, and phishing. They target multiple ITS domains, including intra-vehicle systems, inter-vehicle communications, transportation infrastructure, and human interactions, creating cascading effects across the ecosystem. This chapter introduces a game-theoretic framework, enhanced by control and learning theories, to systematically analyze and mitigate these risks. By modeling the strategic interactions among attackers, users, and system operators, the framework facilitates comprehensive risk assessment and the design of adaptive, scalable resilience mechanisms. A prime example of this approach is the Proactive Risk Assessment and Mitigation of Misinformed Demand Attacks (PRADA) system, which integrates trust mechanisms, dynamic learning processes, and multi-layered defense strategies to counteract deceptive attacks on navigational recommendation systems. In addition, the chapter explores the broader applicability of these methodologies to address various ITS threats, including spoofing, Advanced Persistent Threats (APTs), and denial-of-service attacks. It highlights cross-domain resilience strategies, offering actionable insights to bolster the security, reliability, and adaptability of ITS. By providing a robust game-theoretic foundation, this work advances the development of comprehensive solutions to the evolving challenges in ITS cybersecurity.

Figures (7)

• Figure 1: Intra-vehicle domain attacks: An attacker can exploit vulnerabilities in the in-vehicle infotainment system, such as audio, video, or navigation modules, to compromise the central gateway unit. Once the gateway is breached, the attack can propagate through vehicle-to-infrastructure (V2I) communications using technologies like cellular networks (4G/5G), DSRC/WAVE, GNSS, or Wi-Fi, potentially impacting cloud servers and disrupting critical services across the connected vehicle ecosystem
• Figure 2: Attacks in the Inter-Vehicle Domain: Smart transportation systems rely on the integration of GNSS, roadside units (RSUs), and enhanced Node BS (eNBs) to facilitate seamless vehicle-to-infrastructure communication and optimize traffic flow at urban intersections. However, these systems are vulnerable to deceptive information attacks. For instance, an attacker can compromise an edge server, poisoning the traffic data it collects. This misinformation can then be propagated to vehicles, leading to incorrect routing decisions and the deliberate creation of traffic congestion.
• Figure 3: Attacks in the Transportation Domain: Malware can infiltrate the enterprise network of a transportation control center, often originating from a compromised workstation through phishing, malicious downloads, or other attack vectors. Once inside, the malware can corrupt or poison critical databases that store and process real-time traffic data. This can lead to falsified decision-making, such as generating inaccurate traffic flow recommendations or manipulating vehicle routing algorithms, thereby causing congestion or unsafe road conditions. Additionally, the attack can escalate to the OT level, where the malware targets interconnected physical assets such as traffic light signaling systems, toll collection points, or electronic message boards. By compromising these systems, attackers can manipulate traffic lights to cause accidents, disrupt toll collection to create revenue loss, or display misleading information to drivers, amplifying the overall impact on road safety and traffic management. The cascading effects of such attacks can result in significant economic and social disruption.
• Figure 4: The process for navigational recommendations and where the demand attacks exist.
• Figure 5: The PRADA framework is analyzed through three layers of games between users, the NRS, the threat model of the attacker, and the PRADA risk evaluator.

Theorems & Definitions (2)

• definition 1: User Equilibrium Recommendation
• definition 2: Trust Constraint (TC)