UAV Resilience Against Stealthy Attacks

2025-03-21

AI Summary

Unmanned aerial vehicles (UAVs) face severe security threats—including covert attacks and zero-day exploit campaigns—when both ground stations and onboard software are simultaneously compromised. Method: This paper proposes a collaborative defense architecture built upon the seL4 microkernel, integrating software-defined isolation, lightweight runtime behavioral monitoring, and enhanced MAVLink protocol security mechanisms. Contribution/Results: To the best of our knowledge, this is the first solution enabling joint protection against dual-end compromise. The architecture is fully compatible with mainstream open-source flight controllers and legacy UAV platforms, requiring no modification to existing functional code for seamless deployment. Evaluated on real UAV hardware, the approach effectively blocks zero-day exploit attempts and covert channel attacks while significantly strengthening system-level defense-in-depth capabilities.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Unmanned aerial vehicles (UAVs) depend on untrusted software components to automate dangerous or critical missions, making them a desirable target for attacks. Some work has been done to prevent an attacker who has either compromised a ground control station or parts of a UAV's software from sabotaging the vehicle, but not both. We present an architecture running a UAV software stack with runtime monitoring and seL4-based software isolation that prevents attackers from both exploiting software bugs and utilizing stealthy attacks. Our architecture retrofits legacy UAVs and secures the popular MAVLink protocol, making wide adoption possible.

Problem

• Prevent UAV attacks via compromised software components
• Secure MAVLink protocol against stealthy exploits
• Enable runtime monitoring and isolation for legacy UAVs

Innovation

• Runtime monitoring for UAV security
• seL4-based software isolation
• Secures MAVLink protocol retrofitting