EUVIMEDDescubrir EUVIMED
Open access · CC BY 4.0

Discrete Unintentional Adversarial Perturbation Detection for DQN Traffic Signal Control

Haifeng Guo, Chengju Sun, Guanyu Zhu, Dongwei Xu, Tieming Chen, Akhylbek Kurishbayev, Duman Imanmadi

Electronics · 2026-10-29 · 15 (21) · 5014

DOI: 10.3390/electronics15215014 ↗

At a glance

Journal article in Electronics, published online on 2026-10-29. Written by Haifeng Guo and 6 co-authors. 53 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, “Pioneer” and “Leading Goose” R&D Program of Zhejiang, Zhejiang Provincial Natural Science Foundation of China.

ResumenDatos bibliográficosCiteRelated studies

Abstract (original language)

Anomalous traffic-state observations can affect deep Q-network (DQN) traffic signal control during training and inference. This study uses training-time backdoor poisoning to construct compromised DQN controllers and inference-time trigger activation to evaluate the resulting threat. We propose a Discrete Unintentional Adversarial Perturbation Detector (DUIAPD) for detecting trigger-bearing inputs to an already trained DQN. For each input, the detector generates discretized random perturbations, evaluates all perturbed input copies with the same fixed DQN, and measures action-wise Q-value variability. A normalized sensitivity score is compared with a threshold calibrated on clean reference inputs. No surrogate neural network is trained and no DQN parameters are updated during detection. At a single SUMO intersection with four actions, the reported results across 18 trigger configurations give true positive rates of 92.14–96.38% and false positive rates of 1.51–6.40%. These results support detection of the constructed trigger-bearing inputs under the evaluated conditions. General sensor-fault detection, transfer across intersections, real-time feasibility, and downstream closed-loop benefits remain to be validated.

Funding

  • National Natural Science Foundation of China
  • “Pioneer” and “Leading Goose” R&D Program of Zhejiang
  • Zhejiang Provincial Natural Science Foundation of China
  • Zhejiang University of Technology

Cite

APA

Guo, H., Sun, C., Zhu, G., Xu, D., Chen, T., Kurishbayev, A., & Imanmadi, D. (2026). Discrete Unintentional Adversarial Perturbation Detection for DQN Traffic Signal Control. Electronics, 15(21), 5014. https://doi.org/10.3390/electronics15215014

Vancouver

Guo H, Sun C, Zhu G, Xu D, Chen T, Kurishbayev A, et al. Discrete Unintentional Adversarial Perturbation Detection for DQN Traffic Signal Control. Electronics. 2026;15(21):5014. doi:10.3390/electronics15215014

BibTeX
@article{Guo2026,
  author = {Guo, Haifeng and Sun, Chengju and Zhu, Guanyu and Xu, Dongwei and Chen, Tieming and Kurishbayev, Akhylbek and Imanmadi, Duman},
  title = {Discrete Unintentional Adversarial Perturbation Detection for DQN Traffic Signal Control},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {21},
  pages = {5014},
  doi = {10.3390/electronics15215014}
}
Start for free →