BP Neural Network–Based Kalman Filtering Method Under Multiple Cyberattacks
Open Access
- 1 January 2026
- journal article
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 2026 (1)
Abstract
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.Keywords
Funding Information
- Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education (2022FF02)
This publication has 35 references indexed in Scilit:
- An innovative square root - untraced Kalman filtering strategy with full-parameter online identification for state of power evaluation of lithium-ion batteriesJournal of Energy Storage, 2024
- An accurate state-of-charge estimation of lithium-ion batteries based on improved particle swarm optimization-adaptive square root cubature kalman filterJournal of Power Sources, 2024
- Improving the transferability of adversarial examples through neighborhood attributionKnowledge-Based Systems, 2024
- A Resilient Distributed Kalman Filtering Under Bidirectional Stealthy AttackIEEE Signal Processing Letters, 2024
- Kalman Filter of Switching System Under Hybrid Cyber AttackIEEE Transactions on Automation Science and Engineering, 2023
- On Information Fusion in Optimal Linear FDI Attacks Against Remote State EstimationIEEE Transactions on Control of Network Systems, 2023
- Kalmannet: Data-Driven Kalman Filtering2021
- Intelligent Latency-Aware Virtual Network Embedding for Industrial Wireless NetworksIEEE Internet of Things Journal, 2019
- Optimal Linear Cyber-Attack on Remote State EstimationIEEE Transactions on Control of Network Systems, 2016
- Cyber–Physical Systems: A Perspective at the CentennialProceedings of the IEEE, 2012