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.

Attack and Fault Injection in Self-driving Agents on the Carla Simulator -- Experience Report / Niccolo Piazzesi; Massimo Hong; Andrea Ceccarelli. - ELETTRONICO. - (2021), pp. 210-225. ((Intervento presentato al convegno SAFECOMP [10.1007/978-3-030-83903-1_14].

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

Andrea Ceccarelli
2021

Abstract

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.
Computer Safety, Reliability, and Security
SAFECOMP
Niccolo Piazzesi; Massimo Hong; Andrea Ceccarelli
File in questo prodotto:
File Dimensione Formato  
safecomp-24 May - no track change.pdf

Accesso chiuso

Tipologia: Versione finale referata (Postprint, Accepted manuscript)
Licenza: DRM non definito
Dimensione 631.19 kB
Formato Adobe PDF
631.19 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2158/1243636
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact