Real-Time Detection of False Data Injection Attacks in Smart Grid: A Deep Learning-Based Intelligent Mechanism

By Youbiao He, Gihan J. Mendis, Jin Wei. 2017

651 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

In Electrical and Electronic Engineering

Citations in the corpus

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, neutral): “[107] proposed a Conditional DBN to extract FDI attack features from the historical data of smart grids, and use these features for attack detection in realtime.”
Online False Data Injection Attack Detection With Wavelet Transform and Deep Neural Networks (2018, methodology): “Variants of DNN have been employed recently in solving many power system operation problems; see [24] and [38] for examples.”
Artificial Intelligence Techniques in Smart Grid: A Survey (2021, methodology): “Unsupervised neural networks—such as restricted Boltzmann machine, autoencoder, and variational autoencoder—are applied to anomaly detection [39,40], stability assessment [41], load forecasting [42–44], and so on.”
On-Line Building Energy Optimization Using Deep Reinforcement Learning (2017, background): “Possible benefits of deep learning methods in terms of superior accuracy start to be investigated also for other types of signals in smart grids, such as wind forecast [32], as well as for event detection (classification) problem [33].”
A Review on Digital Twin Technology in Smart Grid, Transportation System and Smart City: Challenges and Future (2023, background): “In [75], the authors suggested a semi-supervised learning approach based on adversarial AE for detecting FDIAs distribution”
A Survey of Deep Learning Methods for Cyber Security (2019, methodology): “To address this issue, He et al. [172] developed a real-time FDI detection algorithm using an extended DBN composed of RBMs that utilize Conditional Gaussian-Bernoulli RBMs (CGBRBMs), which they call a Conditional Deep Belief Network (CDBN) with four hidden layers.”
A Survey on the Detection Algorithms for False Data Injection Attacks in Smart Grids (2020, methodology): “This method was utilized in detecting FDIA in [117], [118].”
Detection of False Data Injection Attacks in Smart Grid: A Secure Federated Deep Learning Approach (2022, methodology): “And many studies on methods for DC state estimation have subsequently emerged, such as DC FDIA detection by Kalman filtering [8], network theory [9], [10], and machine learning [11].”
Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks (2019, background): “traffic offloading [330], resource allocation [331], attack detection [332], just to name a few.”
Machine Learning-Based Network Vulnerability Analysis of Industrial Internet of Things (2019, methodology): “[21] used conditional deep belief network (CDBN) to detect attacks in smart grids.”
Quo vadis artificial intelligence? (2022, background): “To deal with highly complex problems and discover insights from extensive data collections, deep structures are necessary [65–67].”
Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study (2020, methodology): “The IEEE 300-bus power test system has been used for multiple works related to cyber-attack classiﬁcation [38], [53], [58].”
A systems and control perspective of CPS security (2019, background): “Applications of Neural Networks (NNs) and Baysian learning are studied for anomaly detection in the context of security in the presence of attacks [202]–[206].”
Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey (2019, background): “For speciﬁc application scenarios, such as cloud computing [82,83], IoT [84–86], and smart grids [87,88], domain knowledge can be used to provide the environmental characteristics that are helpful in data collection and data preprocessing.”
Distributed Blockchain-Based Data Protection Framework for Modern Power Systems Against Cyber Attacks (2019, background): “against cyber-attacks based on existing centralized data communication and storage mechanisms [18], [19].”