Auto-Encoding Robot State Against Sensor Spoofing Attacks

In robotic systems, the physical world is highly coupled with cyberspace. New threats affect cyber-physical systems as they rely on several sensors to perform critical operations. The most sensitive targets are their location systems, where spoofing attacks can force robots to behave incorrectly. In this paper, we propose a novel anomaly detection approach for sensor spoofing attacks, based on an auto-encoder architecture. After initial training, the detection algorithm works directly on the compressed data by computing the reconstruction errors. We focus on spoofing attacks on Light Detection and Ranging (LiDAR) systems. We tested our anomaly detection approach against several types of spoofing attacks comparing four different compression rates for the auto-encoder. Our approach has a 99% True Positive rate and a 10% False Negative rate for the 83% compression rate. However, a compression rate of 41% could handle almost all of the same attacks while using half the data.

[1]  Khalil M. Ahmad Yousef,et al.  Analyzing Cyber-Physical Threats on Robotic Platforms † , 2018, Sensors.

[2]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[3]  Yong Haur Tay,et al.  Abnormal Event Detection in Videos using Spatiotemporal Autoencoder , 2017, ISNN.

[4]  R. M. Suresh Babu,et al.  Indigenous Mobile Robot for Surveillance and Mapping , 2019 .

[5]  Enrique Soriano,et al.  Quantitative analysis of security in distributed robotic frameworks , 2018, Robotics Auton. Syst..

[6]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[7]  김종영.  구글 TensorFlow 소개 , 2015 .

[8]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[9]  Peng Liu,et al.  Exploiting Physical Dynamics to Detect Actuator and Sensor Attacks in Mobile Robots , 2017, ArXiv.

[10]  Diane J. Cook,et al.  Robot-enabled support of daily activities in smart home environments , 2019, Cognitive Systems Research.

[11]  Hao Wu,et al.  Controlling UAVs with Sensor Input Spoofing Attacks , 2016, WOOT.

[12]  Jonathan Petit,et al.  Remote Attacks on Automated Vehicles Sensors : Experiments on Camera and LiDAR , 2015 .

[13]  Prateek Kapoor,et al.  Detecting and Mitigating Spoofing Attack Against an Automotive Radar , 2018, 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall).

[14]  Chen Yan.  Can You Trust Autonomous Vehicles : Contactless Attacks against Sensors of Self-driving Vehicle , 2016 .

[15]  Andreas E. Savakis,et al.  Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks , 2016, ArXiv.

[16]  Sean Rivera,et al.  ROS-Defender: SDN-Based Security Policy Enforcement for Robotic Applications , 2019, 2019 IEEE Security and Privacy Workshops (SPW).

[17]  Shayok Mukhopadhyay,et al.  Autonomous robotic exploration based on multiple rapidly-exploring randomized trees , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[18]  Neminath Hubballi,et al.  An event based technique for detecting spoofed IP packets , 2017, J. Inf. Secur. Appl..

[19]  Sean Rivera,et al.  ROSploit: Cybersecurity Tool for ROS , 2019, 2019 Third IEEE International Conference on Robotic Computing (IRC).

[20]  Yongdae Kim,et al.  The Frog-Boiling Attack: Limitations of Anomaly Detection for Secure Network Coordinate Systems , 2009, SecureComm.

[21]  Yongdae Kim,et al.  Illusion and Dazzle: Adversarial Optical Channel Exploits Against Lidars for Automotive Applications , 2017, CHES.