Security of Deep Reinforcement Learning for Autonomous Driving: A Survey
IEEE Transactions on Intelligent Transportation Systems · 2026 · 1-18
DOI: 10.1109/tits.2026.3740283 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026. Verfasst von Ambra Demontis und 8 weiteren Autor:innen. Gefördert von: Project FAIR under the MUR NRRP.
Abstract (Originalsprache)
Reinforcement learning (RL) enables agents to learn optimal behaviors through interaction with their environment and has been increasingly deployed in safety-critical applications, including autonomous driving. Despite its promise, RL is susceptible to attacks designed either to compromise policy learning or to induce erroneous decisions by trained agents. Although the literature on RL security has grown rapidly and several surveys exist, existing categorizations often fall short in guiding the selection of appropriate defenses for specific systems. In this work, we present a comprehensive survey of 86 recent studies on RL security, addressing these limitations by systematically categorizing attacks and defenses according to defined threat models and single- versus multi-agent settings. Furthermore, we examine the relevance and applicability of state-of-the-art attacks and defense mechanisms within the context of autonomous driving, providing insights to inform the design of robust RL systems.
Förderung
- Project FAIR under the MUR NRRP
Zitieren
APA
Demontis, A., Gupta, S., Pintor, M., Demetrio, L., Grosse, K., Lin, H., Fang, C., Biggio, B., & Roli, F. (2026). Security of Deep Reinforcement Learning for Autonomous Driving: A Survey. IEEE Transactions on Intelligent Transportation Systems, 1-18. https://doi.org/10.1109/tits.2026.3740283
Vancouver
Demontis A, Gupta S, Pintor M, Demetrio L, Grosse K, Lin H, et al. Security of Deep Reinforcement Learning for Autonomous Driving: A Survey. IEEE Transactions on Intelligent Transportation Systems. 2026:1-18. doi:10.1109/tits.2026.3740283
BibTeX
@article{Demontis2026,
author = {Demontis, Ambra and Gupta, Srishti and Pintor, Maura and Demetrio, Luca and Grosse, Kathrin and Lin, Hsiao-Ying and Fang, Chengfang and Biggio, Battista and Roli, Fabio},
title = {Security of Deep Reinforcement Learning for Autonomous Driving: A Survey},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2026},
pages = {1--18},
doi = {10.1109/tits.2026.3740283}
}
EUVIMED