Detecting Dynamic Attacks in Smart Grids Using Reservoir Computing: A Spiking Delayed Feedback Reservoir Based Approach

Hamedani, Kian; Liu, Lingjia; Hu, Shiyan; Ashdown, Jonathan; Wu, Jinsong; Yi, Yang

doi:10.1109/tetci.2019.2902845

Cited by 31 publications

(19 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], the authors proposed detecting dynamic attacks in smart grids using a spiking delay feedback reservoir-based computing. The proposed attack detection approach implemented a spike in neural network for dynamic detection of attacks but it has major limitation of learning the data, which affects the accuracy of the approach.…”

Section: Related Workmentioning

confidence: 99%

Blockchain-Based SQKD and IDS in Edge Enabled Smart Grid Network

Alkhiari¹,

Mishra²,

Alshehri³

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Smart Grid is a power grid that improves flexibility, reliability, and efficiency through smart meters. Due to extensive data exchange over the Internet, the smart grid faces many security challenges that have led to data loss, data compromise, and high power consumption. Moreover, the lack of hardware protection and physical attacks reduce the overall performance of the smart grid network. We proposed the BLIDSE model (Blockchain-based secure quantum key distribution and Intrusion Detection System in Edge Enables Smart Grid Network) to address these issues. The proposed model includes five phases: The first phase is blockchain-based secure user authentication, where all smart meters are first registered in the blockchain, and then the blockchain generates a secret key. The blockchain verifies the user ID and the secret key during authentication matches the one authorized to access the network. The secret key is shared during transmission through secure quantum key distribution (SQKD). The second phase is the lightweight data encryption, for which we use a lightweight symmetric encryption algorithm, named Camellia. The third phase is the multi-constraint-based edge selection; the data are transmitted to the control center through the edge server, which is also authenticated by blockchain to enhance the security during the data transmission. We proposed a perfect matching algorithm for selecting the optimal edge. The fourth phase is a dual intrusion detection system which acts as a firewall used to drop irrelevant packets, and data packets are classified into normal, physical errors and attacks, which is done by Double Deep Q Network (DDQN). The last phase is optimal user privacy management. In this phase, smart meter updates and revocations are done, for which we proposed Forensic based Investigation Optimization (FBI), which improves the security of the smart grid network. The simulation is performed using network simulator NS3.26, which evaluates the performance in terms of computational complexity, accuracy, false detection, and false alarm rate. The proposed BLIDSE

show abstract

Section: Related Workmentioning

confidence: 99%

Blockchain-Based SQKD and IDS in Edge Enabled Smart Grid Network

Alkhiari¹,

Mishra²,

Alshehri³

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Different data-based techniques, e.g., deep learning methods, can then be employed to recognize the behavior features of attacks and thus achieve attack detection. However, these methods usually face a heavy computational burden to train a fully connected network [38], [39].…”

Section: Related Workmentioning

confidence: 99%

Cyberattack Detection for Converter-Based Distributed dc Microgrids: Observer-Based Approaches

Tan

Xie

Guerrero

et al. 2022

EEE Ind. Electron. Mag.

View full text Add to dashboard Cite

show abstract

“…5) Model free detection scheme: Model free-based detection approached have also been introduced for monitoring attacks in CPSs [31]- [33], [70]- [76]. These solutions generally rely on machine learning or statistical mechanisms to infer a model for the system under inspection directly from data.…”

Section: B Attack Detection Designmentioning

confidence: 99%

“…In order to reduce the difficulties of training neural networks, the reservoir computing method is widely adopted in the literature. For example, in [75] and [76], a reservoir computing-based method was proposed by Hamedani to detect single attacks and stealth attacks, respectively.…”

Section: B Attack Detection Designmentioning

confidence: 99%

Brief Survey on Attack Detection Methods for Cyber-Physical Systems

Tan

Guerrero

Xie

et al. 2020

IEEE Systems Journal

137

View full text Add to dashboard Cite

In recent years, Cyber-Physical Systems (CPSs) have attracted intense attention due to their potential applications in many areas. However, the strong reliance on communication networks makes CPSs vulnerable to intentional cyber-attacks. Therefore, a great number of attack detection methods have been proposed to enforce security of CPSs. In this paper, various false data injection attack detection methods presented for CPSs are investigated and reviewed. According to the knowledge of control information, the controllers of CPSs are categorized as centralized and distributed controllers. Existing centralized attack detection approaches are discussed in terms of (i) linear time-invariant systems, (ii) actuator and sensor attacks, (iii) nonlinear systems and (iv) systems with noise. Furthermore, the development of distributed attack detection is reviewed according to different decoupling methods. Some challenges and future research directions in the context of attack detection approaches are provided.

show abstract

Detecting Dynamic Attacks in Smart Grids Using Reservoir Computing: A Spiking Delayed Feedback Reservoir Based Approach

Cited by 31 publications

References 26 publications

Blockchain-Based SQKD and IDS in Edge Enabled Smart Grid Network

Blockchain-Based SQKD and IDS in Edge Enabled Smart Grid Network

Cyberattack Detection for Converter-Based Distributed dc Microgrids: Observer-Based Approaches

Brief Survey on Attack Detection Methods for Cyber-Physical Systems

Contact Info

Product

Resources

About