检索结果-内蒙古大学图书馆

A deep learning deviation-based scheme to defend against false data injection attacks in power distribution systems

ELECTRIC POWER SYSTEMS RESEARCH 2025年 238卷

作者： Dehbozorgi, Mohammad Reza Rastegar, Mohammad Arani, Mohammadreza F. M. Shiraz Univ Sch Elect & Comp Engn Dept Power & Control Engn Shiraz Iran Toronto Metropolitan Univ Fac Engn & Architectural Sci Toronto ON Canada

Defending against false data injection attacks (FDIAs) in cyber-physical power systems is crucial. Detection in power distribution systems is complex due to load variations, uncertainties, and fewer meters. Defense strategies include model-driven and data-driven approaches, but model-based methods can trigger false alarms due to threshold setting issues. The current research proposes a novel data-driven method to address threshold setting issues in detecting and localizing FDIAs in power distribution systems. First, a dataset is created by recording estimated measurement values using an unscented Kalman filter and weighted least squares across various attack scenarios. These estimated measurements are then fed into a deep artificial neural network (ANN) for binary classification to detect attacks. The output, along with the estimated measurements, is used by another ANN to localize the corrupted meter zone. This deep learning-based approach improves threshold setting over the common chi-square method. Results show that the proposed deep learning method for FDIA detection and localization outperforms a recently proposed ensemble of shallow models. The area under the curve value increases by about 5% with lower training time. The approach is also effective against previously unseen attack strategies and different feeder topologies.

关键词： false data injection attacks Power distribution systems Unscented kalman filter Deviation-based fdia detection FDIA localization

来源：评论

学校读者我要写书评

暂无评论

Remote secure fusion estimation of cyber-physical systems under false data injection attacks

引用

AUTOMATICA 2025年 177卷

作者： Xing, Mengping Lu, Jianquan Liu, Yang Southeast Univ Sch Cyber Sci & Engn Nanjing 210096 Peoples R China Southeast Univ Dept Math Nanjing 210096 Peoples R China Zhejiang Normal Univ Key Lab Intelligent Educ Technol & Applicat Zhejia Jinhua 321004 Zhejiang Peoples R China Zhejiang Normal Univ Sch Math Sci Jinhua 321004 Peoples R China Zhejiang Normal Univ Hangzhou Sch Automat Hangzhou 311231 Peoples R China

This paper discusses the secure fusion estimation issue for cyber-physical systems subject to malicious attacks. Smart sensors equipped with computing modules transmit local posteriori estimations to remote fusion center through wireless communication channels. The transmission process is considered to be vulnerable to false data injection attacks. Therefore, to enhance the resilient of the estimator, protection and fusion strategies are collaboratively designed under cases where the attack information is unavailable or partially available. Noteworthy, instead of using innovation information from smart sensors, a set of auxiliary data transmitted along with local estimations is utilized for attack detection at the remote side. Then, according to the detection signal, the protector at each instant decides whether to drop the received estimations directly, and whether to take compensation measures. Further, the evolution and convergence results of fusion estimation covariance under different cases are analytically derived, and the comparisons of the convergence results are also theoretically deduced. Besides, most of existing achievements on fusion estimation are derived by utilizing local optimal Kalman filter, which implies that the fusion estimation may not be globally optimal and can be further improved. Thus, based on the analysis of steady-state and convergence of error covariance for Kalman filter, a novel iterative procedure for updating the local filter gains is proposed as the first attempt to further reduce fusion estimation error. Several examples including practical application in radar tracking and microgrids are finally provided to verify the derived results. (c) 2025 Published by Elsevier Ltd.

关键词： Cyber-physical systems Secure fusion estimation false data injection attacks Kalman filter Attack detection

来源：评论

学校读者我要写书评

暂无评论

Predictor-based event-triggered learning control of networked control systems with false data injection attacks and output delay

引用

APPLIED MATHEMATICS AND COMPUTATION 2025年 490卷

作者： Yang, Meng Zhai, Junyong Southeast Univ Sch Automat Key Lab Measurement & Control CSE Minist Educ Nanjing 210096 Jiangsu Peoples R China

This article is concerned with the predictor-based event-triggered learning control of networked control systems (NCSs) with false data injection attacks (FDIAs) and output delay. Firstly, by applying the prediction method, a new state observer including an output predictor is employed to get the estimation of delayed sampled-data output in the context of sampling. To improve the efficiency of limited networked resources, an intelligent periodic event-triggered scheme (PETS) is established, in which the triggered threshold can be optimized by the asynchronous advantage actor-critic (A3C) algorithm. Then, a predictor-based event-triggered learning control strategy is developed to handle the FDIAs occurring in the controller-to-actuator channel, and the neural network (NN) technique is introduced to approximate the false data. By applying the Lyapunov function, some sufficient conditions are given to guarantee the boundedness of the NCSs. At last, a simulation of a satellite system is given to confirm the superiorities of the presented predictor- based learning control strategy.

关键词： Networked control systems Intelligent periodic event-triggered scheme Neural networks false data injection attacks Output predictor

来源：评论

学校读者我要写书评

暂无评论

A two-stage recovery strategy against false data injection attacks in smart grids

引用

ELECTRIC POWER SYSTEMS RESEARCH 2025年 245卷

作者： Zhang, Guoqing Gao, Wengen Li, Yunfei An, Fang Anhui Polytech Univ Sch Elect Engn Wuhu 241000 Peoples R China

false data injection attacks (FDIAs) exploit vulnerabilities in the bad data identification mechanisms of power systems by tampering with measurement data. These attacks compromise state estimation, posing a critical threat to the safety and stability of power system operations. To enhance system resilience and enable rapid recovery after an attack, this paper proposes a novel two-stage recovery strategy specifically designed to address FDIAs. In the first stage, a detection method based on Normalized State Variable Residuals (NSVR) is introduced. By leveraging the distinct convergence behaviors of Weighted Least Squares (WLS) and the Extended Kalman Filter (EKF) under FDIAs, NSVR serves as an effective metric for detecting compromised measurements. The second stage employs a multi-step prediction compensation (MSPC) approach for attack correction. After identifying the attacked buses in the first stage, the prediction step of the EKF is utilized to compute the predicted values of the measurements. These predicted values are then selectively used to replace tampered measurements, reconstructing a set of corrected measurements for subsequent state estimation. Comprehensive simulation experiments were conducted on IEEE 14-bus and IEEE 30-bus test systems. The results confirm the efficacy of the proposed algorithm in accurately detecting FDIAs and achieving recovery of the power system.

关键词： false data injection attacks Smart grid Detection Correction State estimate

来源：评论

学校读者我要写书评

暂无评论

Nonlinear decoration-driven adaptive neural finite-time control for USVs with two rotatable thrusters under false data injection attacks and input saturation

引用

ISA TRANSACTIONS 2025年 158卷 97-109页

作者： Meng, Xiangfei Zhang, Guichen Han, Bing Shanghai Maritime Univ Merchant Marine Coll Shanghai 201306 Peoples R China Shanghai Ship & Shipping Res Inst Co Ltd Shanghai 200000 Peoples R China Minjiang Univ Coll Phys & Elect Informat Engn Fuzhou 350108 Peoples R China

This study explores the trajectory tracking control problem in unmanned surface vessels equipped with two rotatable thrusters in an adverse network environment beset by challenges, such as false data injection attacks (FDIAs) and input saturation. This study used the hyperbolic tangent function to provide a smooth transition for the control input, effectively avoiding the system oscillation and instability caused by sudden changes in the input signal. Next, the concept of stepwise reconstruction was used to handle the FDIAs faced by the kinematic and dynamic channels of the system. Under the backstepping framework, the exogenous disturbance bias caused by FDIAs in the kinematic channel was compensated using virtual adaptive technology. In the dynamic channel, the neural-based, high-speed disturbance compensation technology was used to correct the dynamic deviation caused by the composite uncertain dynamics composed of FDIAs and external disturbances. Finite-time technology was further introduced to propose an adaptive finite-time control scheme based on nonlinear decoration. The proposed control scheme was analyzed on the basis of Lyapunov stability theory. The results indicated that all signals in the closed-loop system are bounded. Finally, the effectiveness of the proposed control scheme was verified using simulations. The results revealed that the proposed control scheme enables unmanned surface vessels to track the reference trajectory, exhibiting satisfactory control performance under the constraints of FDIAs, input saturation, and uncertain internal and external dynamics.

关键词： false data injection attacks Input saturation Nonlinear decoration Rotatable thruster Virtual adaptive technology

来源：评论

学校读者我要写书评

暂无评论

Iterative learning resilient consensus of uncertain nonlinear multi-agent systems vulnerable to false data injection attacks

引用

INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE 2025年第1期56卷 157-169页

作者： Sun, Chang-Chun Li, Yuan-Xin Liaoning Univ Technol Coll Sci Jinzhou 121001 Liaoning Peoples R China

This work investigates the iterative learning resilient consensus of uncertain nonlinear high-order multi-agent systems (MASs) against false data injection (FDI) attacks. First, in order to reduce the impact of FDI attacks on the nonlinear MASs, a novel coordinate transformation technique is proposed, which is composed of the states after being attacked, and the Nussbaum gain technique is adopted to address the problem of unknown attack gains resulting from FDI attacks. Then, by employing compromised state variables, a fuzzy adaptive iterative learning resilient control method is presented based on the composite energy function, where unknown nonlinear functions are handled using fuzzy logic systems. The presented approach can guarantee that the outputs of all followers precisely track the leader in a limited time interval while ensuring that all closed-loop signals are bounded. Finally, a numerical simulation is provided to demonstrate the efficacy of the designed control strategy.

关键词： Uncertain nonlinear multi-agent systems iterative learning control Nussbaum gain technique false data injection attacks

来源：评论

学校读者我要写书评

暂无评论

Fault-tolerant bumpless transfer control for fuzzy switched delayed memristive neural networks subject to false data injection attacks

引用

CHAOS SOLITONS & FRACTALS 2025年 193卷

作者： Han, Xinyi Yu, Yongbin Wang, Xiangxiang Cai, Jingye Feng, Xiao Wang, Jingya Shi, Kaibo Zhong, Shouming Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu 610054 Sichuan Peoples R China Chengdu Univ Sch Elect Informat & Elect Engn Chengdu 610106 Sichuan Peoples R China Chengdu Univ Key Lab Pattern Recognit & Intelligent Informat Pr Chengdu 610106 Sichuan Peoples R China Univ Elect Sci & Technol China Sch Math Sci Chengdu 611731 Sichuan Peoples R China

This article investigates the fault-tolerant bumpless transfer (FTBT) control for fuzzy switched memristive neural networks (FSMNNs) with mixed time-varying delays and false data injection (FDI) attacks. First, the persistent dwell-time switching (PDTS) law is adopted to relax the switching frequency limitations. Next, through PDTS law and Takagi-Sugeno (T-S) fuzzy theory, the novel FSMNNs are developed considering non-ideal conditions such as mixed time-varying delays, actuator faults, and external disturbances, which improve the system reliability and align with the modeling requirement in complex situations. Meanwhile, two multiplicative variables and a stuck value are incorporated into actuator faults, capturing the dynamic evolution of fault states that are affected by practical factors. In addition, to cope with the bump phenomenon induced by switching signals and the control failures associated with actuator faults and FDI attacks, the fuzzy FTBT control scheme is employed by merely imposing bump constraints at switching instants, enhancing the flexibility of controller design. By means of Lyapunov-Krasovskii functions and inequality processing techniques, the novel conditions for the exponential stability and H infinity performance of systems are derived. Finally, the feasibility and effectiveness of the derived results are demonstrated by two simulation examples.

关键词： Switched memristive neural networks Persistent dwell-time switching Fault-tolerant bumpless transfer control Actuator faults false data injection attacks

来源：评论

学校读者我要写书评

暂无评论

Localization Detection of false data injection attacks in Novel Energy and Power Systems Based on Correlated Feature-Multi-Label Cascading Boosted Forests

ENGINEERING REPORTS

引用

ENGINEERING REPORTS 2025年第2期7卷

作者： Wang, Lei Li, Tong Geng, Hongbi Liu, Yang Chen, Jian Zhao, Hongwei State Grid Liaoning Elect Power Supply Co Ltd Shenyang Liaoning Peoples R China State Grid Liaoning Elect Power Res Inst Shenyang Liaoning Peoples R China

Under the dual influence of power system transition to integrated energy and the evolution of cyberattack technology, a correlation feature-multilabel cascade boosted forest based false data injection attack localization and detection method is proposed for the new energy power system to accurately locate the attacked position of the power grid in response to the stealthy false data injection attack (FDIA). Considering the FDIA principle and characteristics of the new energy power system, as well as the fact that the new energy power system contains a large amount of measurement data and variable operation states, the proposed method enhances the fitting ability of multi-label cascade forests to complex power measurement data by incorporating the extreme gradient boosting algorithm to identify the anomalies of state quantities of each node of the system, and introduces the "correlation feature" algorithm to detect the original power measurement data. The "correlation feature" algorithm is introduced to extract highly informative features from the original power measurement data to enhance the generalization ability of the multi-label cascade forest, so as to obtain more accurate localization detection. Simulation tests are conducted in the IEEE-57 node system to verify the effectiveness of the proposed method, and compared with other methods, the proposed method has better accuracy, detection rate, sensitivity, and F1 score.

关键词： attack detection correlation characterization false data injection attacks multi-labeled cascade forests novel energy power systems

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Network-Based Approach for Detecting false data injection attacks on Voltage Stability

IEEE OPEN ACCESS JOURNAL OF POWER AND ENERGY

引用

IEEE OPEN ACCESS JOURNAL OF POWER AND ENERGY 2025年 12卷 12-23页

作者： Fahim, Shahriar Rahman Atat, Rachad Kececi, Cihat Takiddin, Abdulrahman Ismail, Muhammad Davis, Katherine R. Serpedin, Erchin Texas A&M Univ Elect & Comp Engn Dept College Stn TX 77843 USA Lebanese Amer Univ Dept Comp Sci & Math Beirut 03797751 Lebanon Florida State Univ Dept Elect & Comp Engn Tallahassee FL 32310 USA Tennessee Technol Univ Dept Comp Sci Cookeville TN 38505 USA

The integration of information and communication technologies into modern power systems has contributed to enhanced efficiency, controllability, and voltage regulation. Concurrently, these technologies expose power systems to cyberattacks, which could lead to voltage instability and significant damage. Traditional false data injection attacks (FDIAs) detectors are inadequate in addressing cyberattacks on voltage regulation since a) they overlook such attacks within power grids and b) primarily rely on static thresholds and simple anomaly detection techniques, which cannot capture the complex interplay between voltage stability, cyberattacks, and defensive actions. To address the aforementioned challenges, this paper develops an FDIA detection approach that considers data falsification attacks on voltage regulation and enhances the voltage stability index. A graph autoencoder-based detector that is able to identify cyberattacks targeting voltage regulation is proposed. A bi-level optimization approach is put forward to concurrently optimize the objectives of both attackers and defenders in the context of voltage regulation. The proposed detector underwent rigorous training and testing across different kinds of attacks, demonstrating enhanced generalization performance in all situations. Simulations were performed on the Iberian power system topology, featuring 486 buses. The proposed model achieves 98.11% average detection rate, which represents a significant enhancement of 10-25% compared to the cutting-edge detectors. This provides strong evidence for the effectiveness of proposed strategy in tackling cyberattacks on voltage regulation.

关键词： Power system stability Voltage control Stability criteria Detectors Computer crime Indexes Reactive power Autoencoders Voltage measurement Power grids Cybersecurity voltage regulation graph autoencoder voltage stability false data injection attacks bad data intrusion machine learning

来源：评论

学校读者我要写书评

暂无评论

Finite-time control of networked stochastic systems with disturbances and false data injection attacks

引用

TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL 2025年

作者： Sun, Yuexuan Wei, Xinjiang Zhang, Huifeng Hu, Xin Ludong Univ Sch Math & Stat Sci Yantai 264025 Peoples R China Taishan Univ Tai An Peoples R China

In this paper, networked stochastic systems (NSSs) subjected to disturbances and false data injection attacks (FDIAs) is studied, which have been extensively utilized in practical engineering. To fully utilize the disturbance information, a stochastic disturbance observer (SDO) is introduced to estimate the exogenous disturbance;since the state of the system is often unavailable under the FDIAs, an output observer is designed to obtain the estimation of the state. On these basis, the finite-time controller is constructed to compensate the disturbance and attenuate the FDIAs simultaneously, which can ensure the stability of the systems, and the convergence time can be restricted to a certain period of time. Finally, the effectiveness of the proposed scheme is verified by simulations.

关键词： Networked stochastic systems disturbance observer multiple disturbances finite-time control false data injection attacks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：