Attack and Fault Injection in Self-driving Agents on the Carla Simulator – Experience Report

Autor:	Niccolò Piazzesi, Andrea Ceccarelli, Massimo Hong
Rok vydání:	2021
Předmět:	Adversarial system Software Automotive systems Self driving business.industry Computer science Driving simulator Automotive industry Experience report Fault injection business Simulation
Zdroj:	Lecture Notes in Computer Science ISBN: 9783030839024 SAFECOMP
DOI:	10.1007/978-3-030-83903-1_14
Popis:	Machine Learning applications are acknowledged at the foundation of autonomous driving, because they are the enabling technology for most driving tasks. However, the inclusion of trained agents in automotive systems exposes the vehicle to novel attacks and faults, that can result in safety threats to the driving tasks. In this paper we report our experimental campaign on the injection of adversarial attacks and software faults in a self-driving agent running in a driving simulator. We show that adversarial attacks and faults injected in the trained agent can lead to erroneous decisions and severely jeopardize safety. The paper shows a feasible and easily-reproducible approach based on open source simulator and tools, and the results clearly motivate the need of both protective measures and extensive testing campaigns.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::cd3b2b419645d303c3972a48f6938772 https://doi.org/10.1007/978-3-030-83903-1_14 Zobrazit plný text záznamu