RobIn: Robust-Invariant-Based Physical Attack Detector for Autonomous Aerial Vehicles

Autonomous aerial vehicles (UAVs) are widespread in Internet of Things (IoT) systems applications. However, UAVs suffer cyberspace security threats, especially physical attacks that leverage physics signals to deceive sensors, disrupt missions, and potentially crash the UAVs. Such attack detection demands not only guaranteeing detection accuracy and timeliness but also robustness. Prior studies consider physical laws (Invariant) to detect inconsistency, but they sacrifice robustness requirements of uncertainties and lack theoretical guarantees of detection performance. To achieve the sensitivity-specificity tradeoff, this article proposes RobIn, a Robust Invariant-based physical attacks detector design incorporating scenario optimization. The key idea behind RobIn is robustifying the invariant model via scenario optimization theory to ensure modality untouched and trustworthy detection. With an offline robustification scheme and an onboard detection algorithm, RobIn can balance attack sensitivity and robustness to uncertainties. We theoretically provide the detection specificity lower bound guarantees under highlighting sensitivity in finite scenarios. We evaluate RobIn in both four virtual and three real UAVs, achieving 96.2% detection rates and 1.6% false alarm rates against 6 types of existing attacks, with only 3.82% runtime overhead (on average). Moreover, we illustrate the resilience of RobIn against the worst-case attack.