Abstract：This paper proposes a method to detect the compromised actuators and then determine the attack types. Based on sensor measurements, the actual control command conducted by the actuator can be estimated using maximum likelihood estimation method; and then by comparing the estimated command with the reference one which is sent from the on-board computer, we are able to figure out whether the control command is successfully conducted by the actuator or not. Experimental results based on simulation platform show that the detector can effectively detect error once the attack occurs and precisely identify the specific type of the sensor attack.
[1] 彭育辉, 江铭, 马中原, 等. 汽车自动驾驶关键技术研究进展[J]. 福州大学学报(自然科学版), 2021, 49(5): 691-703. PENG Y H, JIANG M, MA Z Y, et al. Review on development of key technology for autonomous vehicle[J]. Journal of Fuzhou University (Natural Science Edition), 2021, 49(5): 691-703. [2] 郑振华, 刘其朋. 基于视觉特征提取的强化学习自动驾驶系统[J]. 复杂系统与复杂性科学, 2020,17(4): 30-37. ZHENG Z H, LIU Q P. Autonomous driving systems trained by reinforcement learning with visual features extraction[J]. Complexity Systems and Complexity Science, 2020, 17(4): 30-37. [3] HAMID U Z A, PUSHKIN K, ZAMZURI H, et al. Current collision mitigation technologies for advanced driver assistance systems-a survey[J]. Perintis eJournal, 2016, 6(2): 78-90. [4] SHEEHAN B, MURPHY F, MULLINS M, et al. Connected and autonomous vehicles: a cyber-risk classification framework[J]. Transportation Research Part A, 2019, 124: 523-536. [5] PARKINSON S, WARD P, WILSON K, et al. Cyber threats facing autonomous and connected vehicles: future challenges[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(11): 2898-2915. [6] PETIT J, SHLADOVER S E. Potential cyberattacks on automated vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2): 546-556. [7] 冯敏健, 张辉, 巨志扬, 等. 基于LGSVL/Apollo的网络延迟攻击下自动驾驶车辆定位估算[J]. 汽车安全与节能学报, 2021, 12(1): 62-69. FENG M J, ZHANG H, JU Z Y, et al. Localization estimation algorithm under cyber delay attack for autonomous vehicle based on LGSVL/Apollo[J]. Journal of Automotive Safety and Energy, 2021, 12(1): 62-69. [8] 李慧云, 邵翠萍, 陈贝章, 等. 基于矩阵补全的无人车感知系统的攻击防御技术[J]. 集成技术, 2020, 9(5): 1-14. LI H Y, SHAO C P, CHEN B Z, et al. Attack defense technology of unmanned vehicle perception system based on matrix completion[J]. Journal of Integration Technology, 2020, 9(5):1-14. [9] 叶斌, 葛万成. 基于对抗补丁的交通标牌攻击[J]. 通信技术, 2021, 54(3): 664-671. YE B, GE W C. Traffic sign attack based on adversarial patch[J]. Communications Technology, 2021, 54(3): 664-671. [10] 陈晋音, 陈治清, 郑海斌, 等. 基于PSO的路牌识别模型黑盒对抗攻击方法[J]. 软件学报, 2020, 31(9): 2785-2801. CHEN J Y, CHEN Y Q, ZHENG H B, et al. Black-box physical attack against road sign recognition model via PSO[J]. Journal of Software, 2020, 31(9): 2785-2801. [11] KONG J, PFEIFFER M, SCHILDBACH G, et al. Kinematic and dynamic vehicle models for autonomous driving control design[C]// 2015 IEEE Intelligent Vehicles Symposium. Seoul, Korea: IEEE, 2015: 1094-1099. [12] AGUERO C E, KOENIG N, CHEN I, et al. Inside the virtual robotics challenge: simulating real-time robotic disaster response[J]. IEEE Transactions on Automation Science and Engineering, 2015, 12(2): 494-506. [13] KATO S, TAKEUCHI E, ISHIGURO Y, et al. An open approach to autonomous vehicles[J]. IEEE Micro, 2015, 35(6): 60-68. [14] QUIGLEY M, GERKEY B P, CONLEY K, et al. ROS: an open-source robot operating system[C]// 2009 ICRA Workshop on Open Source Software. Kobe, Japan: IEEE, 2009: 5. [15] BIBER P, STRABER W. The normal distributions transform: a new approach to laser scan matching[C]// 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Las Vegas, USA: IEEE, 2003: 2743-2748. [16] KRAVCHIK M, SHABTAI A. Detecting cyber attacks in industrial control systems using convolutional neural networks[C]// 2018 ACM Workshop on Cyber-Physical Systems Security and Privacy. Toronto, Canada: ACM, 2018: 72-83. [17] SHIN J, BAEK Y, EUN Y, et al. Intelligent sensor attack detection and identification for automotive cyber-physical systems[C]// 2017 IEEE Symposium Series on Computational Intelligence (SSCI). Hawaii, USA: IEEE, 2017: 3380-3387. [18] 闻佳, 王宏君, 邓佳, 等. 基于深度学习的异常事件检测[J]. 电子学报, 2020, 48(2): 308-313. WEN J, WANG H J, DENG J, et al. Abnormal event detection based on deep learning[J]. Acta Electronica Sinica, 2020, 48(2): 308-313.
