Multi-agent system keeps tracking targets despite cyberattacks
Resilient Multi-Agent Target Localization and Tracking via BAG-Aware Mutual Information Maximization under False Data Injection Attacks
Multiagent Systems
Summary
Tracking moving targets using teams of cooperating agents can be disrupted when some agents send false information due to cyberattacks. The authors propose a method that helps identify which agents are compromised and avoids using their faulty data. Their system also guides safe agents to adjust their positions and recover accurate tracking by sharing trustworthy data. Tests show their approach maintains good tracking even when some agents are under attack.
What this means in practice
- •For autonomous vehicle teams: Maintain accurate tracking of dynamic targets in vehicle networks despite compromised sensors sending false data.
- •For industrial robot operators: Improve reliability of coordinated robotic localization in environments vulnerable to cyberattacks by isolating compromised sensor data and guiding trustworthy robots.
Authors
Bibek Adhikari, Samrat Chaulagain, Kamesh Subbarao
Abstract
Cooperative multi-agent networks deployed for target localization and tracking remain critically vulnerable to malicious cyberattacks, since a single compromised agent can corrupt the centralized target belief and mislead the estimation process across the entire network. This paper presents a resilient multi-agent target localization and tracking framework under a limited agent sensing range and false-data injection (FDI) attacks. The proposed method combines information-based navigation for target search and posterior target state uncertainty reduction, Bayesian attack graph (BAG) based attack detection for probabilistic identification of the compromised agents, and reachable set-guided recovery that guides the uncompromised agents to relocalize the target when the sole localizing agent is attacked. The framework preserves the network localization capability after an attack by trust-gating compromised sensing information and guiding attack-immune agents toward a dynamically constructed recovery set representing the new target belief using a Linear Quadratic Regulator (LQR). Simulation validates that the proposed framework maintains a robust tracking performance under FDI attacks, demonstrating the potential for resilient autonomy in safety-critical applications.