Security and Privacy in Communication Networks. 13th International Conference, SecureComm 2017, Niagara Falls, ON, Canada, October 22–25, 2017, Proceedings

Research Article

VCIDS: Collaborative Intrusion Detection of Sensor and Actuator Attacks on Connected Vehicles

  • @INPROCEEDINGS{10.1007/978-3-319-78813-5_19,
        author={Pinyao Guo and Hunmin Kim and Le Guan and Minghui Zhu and Peng Liu},
        title={VCIDS: Collaborative Intrusion Detection of Sensor and Actuator Attacks on Connected Vehicles},
        proceedings={Security and Privacy in Communication Networks. 13th International Conference, SecureComm 2017, Niagara Falls, ON, Canada, October 22--25, 2017, Proceedings},
        proceedings_a={SECURECOMM},
        year={2018},
        month={4},
        keywords={Urban vehicular networks Intrusion detection Cyber-physical systems},
        doi={10.1007/978-3-319-78813-5_19}
    }
    
  • Pinyao Guo
    Hunmin Kim
    Le Guan
    Minghui Zhu
    Peng Liu
    Year: 2018
    VCIDS: Collaborative Intrusion Detection of Sensor and Actuator Attacks on Connected Vehicles
    SECURECOMM
    Springer
    DOI: 10.1007/978-3-319-78813-5_19
Pinyao Guo1,*, Hunmin Kim1,*, Le Guan1,*, Minghui Zhu1,*, Peng Liu1,*
  • 1: Pennsylvania State University
*Contact email: pug132@ist.psu.edu, huk164@psu.edu, lug14@ist.psu.edu, muz16@psu.edu, pliu@ist.psu.edu

Abstract

Modern urban vehicles adopt sensing, communication and computing modules into almost every functioning aspect to assist humans in driving. However, the advanced technologies are inherently vulnerable to attacks, exposing vehicles to severe security risks. In this work, we focus on the detection of sensor and actuator attacks that are capable of actively altering vehicle behavior and directly causing damages to human beings and vehicles. We develop a collaborative intrusion detection system where each vehicle leverages sensing data from its onboard sensors and neighboring vehicles to detect sensor and actuator attacks without a centralized authority. The detection utilizes the unique feature that clean data and contaminated data are correlated through the physical dynamics of the vehicle. We demonstrate the effectiveness of the detection system in a scaled autonomous vehicle testbed by launching attacks through various attack channels.