CISPA
Browse
s12083-022-01434-0.pdf (1.75 MB)

Backdoor attacks against deep reinforcement learning based traffic signal control systems

Download (1.75 MB)
journal contribution
posted on 2024-03-22, 14:36 authored by Heng Zhang, Jun Gu, Zhikun Zhang, Linkang Du, Yongmin Zhang, Yan Ren, Jian Zhang, Hongran Li
To improve the efficiency of the traffic signal control and alleviate traffic congestion, many researchers focus on applying deep reinforcement learning (DRL) for traffic signal control systems (TSCS). The TSCS consider all the vehicles’ waiting time around the intersection and decrease them so as to alleviate the traffic congestion. However, it has been confirmed that the DRL model is vulnerable to backdoor attacks. In this paper, we propose the first backdoor attack against DRL based TSCS. We define a special drive behavior as malicious input (called trigger). Once the trigger is activated via an attacker, the TSCS will only take into waiting time for the attacker’s vehicle at the intersection. Our empirical experiments show that our proposed backdoor attacks are effective with negligible impact on TSCS’s normal operation.

History

Primary Research Area

  • Trustworthy Information Processing

Journal

Peer-to-Peer Networking and Applications

Volume

16

Page Range

466-474

Publisher

Springer Nature

Open Access Type

  • Not Open Access

Sub Type

  • Article

BibTeX

@article{Zhang:Gu:Zhang:Du:Zhang:Ren:Zhang:Li:2023, title = "Backdoor attacks against deep reinforcement learning based traffic signal control systems", author = "Zhang, Heng" AND "Gu, Jun" AND "Zhang, Zhikun" AND "Du, Linkang" AND "Zhang, Yongmin" AND "Ren, Yan" AND "Zhang, Jian" AND "Li, Hongran", year = 2023, month = 1, journal = "Peer-to-Peer Networking and Applications", number = "1", pages = "466--474", publisher = "Springer Nature", issn = "1936-6442", doi = "10.1007/s12083-022-01434-0" }

Usage metrics

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC