Susceptibility of Autonomous Driving Agents to Learning-Based Action-Space Attacks

Yuting Wu, Xin Lou, Pengfei Zhou, Rui Tan, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Intelligent vehicles with increasing complexity face cybersecurity threats. This paper studies action-space attacks on autonomous driving agents that make decisions using either a traditional modular processing pipeline or the recently proposed end-to-end driving model obtained via deep reinforcement learning (DRL). Such attacks alter the actuation signal and pose direct risks to the vehicle's state. We formulate the attack construction as a DRL problem based on the input from either an extra camera or inertial measurement unit deployed. The attacks are designed to lurk until a safety-critical moment arises and cause a side collision upon activation. We analyze the behavioral differences between two driving agents when subjected to action-space attacks and demonstrate the superior resilience of the modular processing pipeline. We further investigate the performance and limitations of two enhancement methods, i.e., adversarial training through fine-tuning and progressive neural networks. The result offers valuable insights into vehicle safety from the viewpoints of both the assailant and the defender and informs the future design of autonomous driving systems.

Original languageEnglish (US)
Title of host publicationProceedings - 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops Volume, DSN-W 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages76-83
Number of pages8
ISBN (Electronic)9798350325430
DOIs
StatePublished - 2023
Event53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops Volume, DSN-W 2023 - Porto, Portugal
Duration: Jun 27 2023Jun 30 2023

Publication series

NameProceedings - 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops Volume, DSN-W 2023

Conference

Conference53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops Volume, DSN-W 2023
Country/TerritoryPortugal
CityPorto
Period6/27/236/30/23

Keywords

  • Action-space attack
  • Autonomous driving
  • Cybersecurity
  • Reinforcement learning

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Software
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Susceptibility of Autonomous Driving Agents to Learning-Based Action-Space Attacks'. Together they form a unique fingerprint.

Cite this