EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BP Neural Network–Based Kalman Filtering Method Under Multiple Cyberattacks

Zijing Li, Keting Huang, Gang Wang, Zhuowei Liang, Yun Zhou, Desheng Zheng, Yaoxin Duan

IET Signal Processing · 2026-01 · 2026 (1)

DOI: 10.1049/sil2/3335149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Signal Processing, online erschienen am 24.02.2026. Verfasst von Zijing Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a Kalman‐gain‐driven neural Kalman filtering (KF) defense framework, termed KFDBP, for secure state estimation in cyber–physical systems (CPSs) under denial‐of‐service (DoS), spoofing, and replay attacks. Unlike end‐to‐end neural filtering approaches such as KalmanNet that directly learn state estimators or implicitly approximate the Kalman gain using deep recurrent architectures, the proposed method employs a lightweight back‐propagation (BP) neural network to adaptively regulate the Kalman gain online, while strictly preserving the classical Kalman filter prediction–correction recursion. By formulating an innovation‐oriented Kalman gain learning objective, KFDBP explicitly addresses attack‐induced observation uncertainty and non‐Gaussian measurement corruption without requiring prior knowledge of attack timing, attack type, or attack probability during online estimation. The bounded gain regulation mechanism enhances estimation stability and interpretability, which are critical for safety‐sensitive CPS applications, while significantly reducing computational complexity compared with deep neural network–based filters. Extensive Monte Carlo simulations under single and hybrid attack scenarios demonstrate that KFDBP consistently achieves lower estimation error and improved robustness than the conventional Kalman filter and KalmanNet under different attack probabilities, making it suitable for real‐time and resource‐constrained CPS applications.

Förderung

  • Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education

Zitieren

APA

Li, Z., Huang, K., Wang, G., Liang, Z., Zhou, Y., Zheng, D., & Duan, Y. (2026). BP Neural Network–Based Kalman Filtering Method Under Multiple Cyberattacks. IET Signal Processing, 2026(1). https://doi.org/10.1049/sil2/3335149

Vancouver

Li Z, Huang K, Wang G, Liang Z, Zhou Y, Zheng D, et al. BP Neural Network–Based Kalman Filtering Method Under Multiple Cyberattacks. IET Signal Processing. 2026;2026(1). doi:10.1049/sil2/3335149

BibTeX
@article{Li2026,
  author = {Li, Zijing and Huang, Keting and Wang, Gang and Liang, Zhuowei and Zhou, Yun and Zheng, Desheng and Duan, Yaoxin},
  title = {BP Neural Network–Based Kalman Filtering Method Under Multiple Cyberattacks},
  journal = {IET Signal Processing},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1049/sil2/3335149}
}
Kostenlos starten →