Diagnosis-guided Attack Recovery for Securing Robotic Vehicles from Sensor Deception Attacks

Pritam Dash, Guanpeng Li, Mehdi Karimibiuki, and Karthik Pattabiraman, To appear in the ACM Asia Conference on Computer and Communications Security (AsiaCCS), 2024. (Acceptance Rate: TBD) [PDF | Talk] (Code) (arXIV version)

Abstract: Sensors are crucial for autonomous operation in robotic vehicles (RV). Unfortunately, RV sensors can be compromised by physical attacks such as tampering or spoofing, leading to a crash. In this paper, we present DeLorean, a unified framework for attack detection, attack diagnosis, and recovering RVs from sensor deception attacks (SDA). DeLorean is designed to recover RVs even from strong SDAs in which the adversary targets multiple heterogeneous sensors simultaneously. We propose a novel attack diagnosis technique that inspects the attack-induced errors under SDA, and using causal analysis identifies the targeted sensors. DeLorean then uses historic state information to selectively reconstruct physical state estimates for compromised sensors, enabling targeted attack recovery under single or multi-sensor SDAs. Our evaluation on four real and two simulated RVs shows that DeLorean can recover RVs from SDAs, and ensure mission success in 93% of the cases on average.

Comments are closed.