Visible to the public Intrusion detection on robot cameras using spatio-temporal autoencoders: A self-driving car application

TitleIntrusion detection on robot cameras using spatio-temporal autoencoders: A self-driving car application
Publication TypeConference Paper
Year of Publication2020
AuthorsAmrouche, F., Lagraa, S., Frank, R., State, R.
Conference Name2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring)
Date PublishedMay 2020
ISBN Number978-1-7281-5207-3
KeywordsAutonomous automobiles, camera frames, camera vulnerabilities, Cameras, car application, decision making, decision-making process, embedded cameras, environment discovery, existing security breaches, Human Behavior, human factors, Image reconstruction, important fields, Intrusion detection, mobile robots, policy-based governance, pubcrawl, resilience, Resiliency, robot cameras, Robot Operating System, robot operating systems, Robot vision systems, robust solutions, ROS, security, security of data, self-driving cars industry, spatio-temporal autoencoders, suspicious frames, telecommunication security, Training, unsupervised anomaly detection tool

Robot Operating System (ROS) is becoming more and more important and is used widely by developers and researchers in various domains. One of the most important fields where it is being used is the self-driving cars industry. However, this framework is far from being totally secure, and the existing security breaches do not have robust solutions. In this paper we focus on the camera vulnerabilities, as it is often the most important source for the environment discovery and the decision-making process. We propose an unsupervised anomaly detection tool for detecting suspicious frames incoming from camera flows. Our solution is based on spatio-temporal autoencoders used to truthfully reconstruct the camera frames and detect abnormal ones by measuring the difference with the input. We test our approach on a real-word dataset, i.e. flows coming from embedded cameras of self-driving cars. Our solution outperforms the existing works on different scenarios.

Citation Keyamrouche_intrusion_2020