Data-Driven False Data-Injection Attack Design and Detection in Cyber-Physical Systems

Zhao, Zhengen; Huang, Yi-Min; Zhen, Ziyang; Li, Yuzhe

doi:10.1109/tcyb.2020.2969320

Cited by 60 publications

(20 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stealth attack design on a quantized networked control system has been solved in [14]. On the other hand, attempts on attack detection include centralized (and decentralized as well) schemes for noiseless systems [15], coding of sensor output along with χ 2 detector [16], comparing the sensor observations with those coming from from a few known safe sensors [17], the attack detection and secure estimation schemes based on innovation vectors in [18], data driven design and detection of FDI [19], neural network based detection of FDI [20], quickest detection of time-varying false data injection attacks in dynamic linear regression models [21], FDI detection in linear parameter varying CPS [22], Gaussian mixture model based detection and secure state estimation [23], and quickest detection of FDI using Markov decision process formulation [24]. Attempts on attack-resilient state estimation include: [25] for bounded noise, [26]- [28] for adaptive filter design using stochastic approximation, [29] that uses sparsity models to characterize the switching location attack in a noiseless linear system and state recovery constraints for various attack modes.…”

Section: A Related Literaturementioning

confidence: 99%

Design of False Data Injection Attack on Distributed Process Estimation

Moulik

Chattopadhyay

Mitra

et al. 2022

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Section: A Related Literaturementioning

confidence: 99%

Design of False Data Injection Attack on Distributed Process Estimation

Moulik

Chattopadhyay

Mitra

et al. 2022

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

“…Khojasteh et al [26] investigated a learning-based attack method to estimate the dynamics of a system through a nonlinear Gaussian process-based learning algorithm that attacked the control policy. Zhao et al [27] used subspace recognition technology to propose an attack method based on wrong data injection. The target of the attack was the state estimation error, and the coding matrix was used to detect the attack.…”

Section: Related Workmentioning

confidence: 99%

Research on a PSO-H-SVM-Based Intrusion Detection Method for Industrial Robotic Arms

2022

View full text Add to dashboard Cite

The automation and intelligence of industrial manufacturing is the core of the fourth industrial revolution, and robotic arms and proprietary networked information systems are an integral part of this vision. However, with the benefits come risks that have been overlooked, and robotic arms have become a heavily attacked area. In order to improve the security of the robotic arm system, this paper proposes an intrusion detection method based on a state classification model. The closure operation process of the robotic arm is divided into five consecutive states, while a support vector machine based on the particle swarm optimization algorithm (PSO-H-SVM) classifies the operation state of the robotic arm. In the detection process, the classifier predicts the operation state of the robotic arm in real time, and the detection method determines whether the state transfer meets the logical requirements, and then determines whether the intrusion occurs. In addition, a response mechanism is proposed on the basis of the intrusion detection system to make protection measures for the robotic arm system. Finally, a physical experiment platform was built to test the intrusion detection method. The results showed that the classification accuracy of the PSO-H-SVM algorithm reached 96.02%, and the detection accuracy of the intrusion detection method reached 90%, which verified the effectiveness and reliability of the intrusion detection method.

show abstract

“…Remark From the viewpoint of defender, the attack detection for the proposed stealthy multiplicative attacks may be realized by designing appropriate coding matrices, 33,34 to make the gap metric between the coded signal subspace and the primary signal subspace larger than the stealthiness index.…”

Section: Optimized Stealthy Multiplicative Attack Designmentioning

confidence: 99%

Stealthy multiplicative attacks against cyber‐physical systems: A gap metric approach

Zhao

et al. 2022

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

In this article, a stealthy multiplicative attack design scheme for cyber‐physical systems equipped with parity space based detector is proposed, with the aid of gap metric method. First, a novel stealthiness index defined by the gap metric is presented for multiplicative attacks, and the security analysis issue of parity space based detector is formulated. Then, the attack subspace satisfying the stealthiness constraint is constructed, and the subspace rotation is applied to parameterize the multiplicative attacks. Moreover, a joint optimization method is presented to design the stealthy multiplicative attacks. Finally, simulations on a flight vehicle demonstrate the effectiveness of the proposed methods.

show abstract

Data-Driven False Data-Injection Attack Design and Detection in Cyber-Physical Systems

Cited by 60 publications

References 38 publications

Design of False Data Injection Attack on Distributed Process Estimation

Design of False Data Injection Attack on Distributed Process Estimation

Research on a PSO-H-SVM-Based Intrusion Detection Method for Industrial Robotic Arms

Stealthy multiplicative attacks against cyber‐physical systems: A gap metric approach

Contact Info

Product

Resources

About