Cyber-Physical Security and Safety of Autonomous Connected Vehicles: Optimal Control Meets Multi-Armed Bandit Learning

Aidin Ferdowsi, Samad Ali, Walid Saad, Narayan B. Mandayam

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

Autonomous connected vehicles (ACVs) rely on intra-vehicle sensors such as camera and radar as well as inter-vehicle communication to operate effectively which exposes them to cyber and physical attacks in which an adversary can manipulate sensor readings and physically control the ACVs. In this paper, a comprehensive control and learning framework is proposed to thwart cyber and physical attacks on ACV networks. First, an optimal safe controller for ACVs is derived to maximize the street traffic flow while minimizing the risk of accidents by optimizing the ACV speed and inter-ACV spacing. It is proven that the proposed controller is robust to physical attacks which aim at making ACV systems unstable. Next, two data injection attack (DIA) detection approaches are proposed to address cyber attacks on sensors and their physical impact on the ACV system. The proposed approaches rely on leveraging the stochastic behavior of the sensor readings and on the use of a multi-armed bandit (MAB) algorithm. It is shown that, collectively, the proposed DIA detection approaches minimize the vulnerability of ACV sensors against cyber attacks while maximizing the ACV system's physical robustness. Simulation results show that the proposed optimal safe controller outperforms the current state of the art controllers by maximizing the robustness of ACVs to physical attacks. The results also show that the proposed DIA detection approaches, compared to Kalman filtering, can improve the security of ACV sensors against cyber attacks and ultimately improve the physical robustness of an ACV system.

Original languageEnglish (US)
Article number8758129
Pages (from-to)7228-7244
Number of pages17
JournalIEEE Transactions on Communications
Volume67
Issue number10
DOIs
StatePublished - Oct 2019

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Keywords

  • Autonomous connected vehicles
  • cyber-physical security
  • data injection attack
  • multi-armed bandit learning
  • optimal safe control

Fingerprint Dive into the research topics of 'Cyber-Physical Security and Safety of Autonomous Connected Vehicles: Optimal Control Meets Multi-Armed Bandit Learning'. Together they form a unique fingerprint.

Cite this