Analysis of Anomaly Detection Approaches Performed Through Deep Learning Methods in SCADA Systems

Altunay, Hakan Can; Albayrak, Zafer; Özalp, Ahmet Nusret; Çakmak, Muhammet

doi:10.1109/hora52670.2021.9461273

Cited by 21 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Atunay et al. [20] presented a comprehensive analysis of various deep learning models used for detecting anomalies in the SCADA systems. Typically, the IDS was mainly developed to minimize the cyber‐threats in the networking systems.…”

Section: Related Workmentioning

confidence: 99%

“…However, this framework has the limitations of inefficient detection, increased error outputs, and overfitting. Atunay et al [20] presented a comprehensive analysis of various deep learning models used for detecting anomalies in the SCADA systems. Typically, the IDS was mainly developed to minimize the cyber-threats in the networking systems.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A security model for smart grid SCADA systems using stochastic neural network

Rabie

Shitharth

Alghazzawi

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

Detection of cyber‐threats in the smart grid Supervisory Control and Data Acquisition (SCADA) is still remains one of the complex and essential processes need to be highly concentrated in present times. Typically, the SCADA is more prone to the security issues due to their environmental problems and vulnerabilities. Therefore, the proposed work intends to design a new detection approach by integrating the optimization and classification models for smart grid SCADA security. In this framework, the min‐max normalization is performed at first for noise removal and attributes arrangement. Here, the correlation estimation mechanism is mainly deployed to reduce the dimensionality of features by choosing the relevant features used for attack prediction. Moreover, the optimal features are selected by using the optimal solution provided by the Holistic Harris Hawks Optimization (H3O). Finally, the Perceptron Stochastic Neural Network (PSNN) is utilized to categorize the normal and attacking data flow in the network with minimal processing time and complexity. By using the combination of proposed H3O‐PSNN technique, the detection accuracy is improved up to 99% for all datasets used in this study, and also other measures such as precision to 99.2%, recall to 99%, f1‐score to 99.2% increased, when compared to the standard techniques.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A security model for smart grid SCADA systems using stochastic neural network

Rabie

Shitharth

Alghazzawi

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

show abstract

“…SCADA is a well-established computer-based automate system used to gather realtime data from remote or local equipment such as programmable logic controller, remote terminal unit (RTU), intelligent electronic devices (IED) and human machine interface (HMI), etc. [45]- [48]. Figure 4 explains the block diagram of SCADA architecture connected from operation center, energy management and distribution systems (EMS and DMS) through control room to the substation.…”

Section: Artificial Intelligence In Scada Intrusion Detectionmentioning

confidence: 99%

“…Over the last two decades, connecting SCADA networks to the internet has become essential due to performance and commercial needs. Hence, SCADA network's complexity and interconnectivity has increased [47]- [48]. SCADA networks are made to adopt Transmission control protocol/internet protocol and are accessible via internet and corporate networks, they are vulnerable to cyberattacks.…”

Section: Fig 4 Illustration Of Scada Infrastructurementioning

confidence: 99%

“…In this work, CNN serves as an intelligent real-time traffic monitoring system without intervening SCADA operations. The intrusion detection system proposed in [48] uses unsupervised learning in DL approaches to analyze the big data obtained from SCADA systems. In this work, several DL architectures such as CNN, LSTM, deep belief networks (DBN) and autoencoders (AE) are used to learn the features of SCADA system and prevents the malware attacks.…”

Section: Fig 4 Illustration Of Scada Infrastructurementioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence and its applications in Renewable Integrated Power Systems

E.R.¹,

Joy²,

Bansal³

et al. 2022

Preprint

View full text Add to dashboard Cite

Electric power system is undergoing major changes, due to large-scale integration of renewable energy, complicated network structure and increased energy demand. Developing autonomous systems, intelligent and digital communication technologies are becoming more and more urgent to modernize, strengthen and stabilize the power grid. Among several innovative efforts, artificial intelligence (AI) is becoming more popular due to its human like thinking logic, advanced wisdom, reasoning, learning capability and knowledge representation. AI approaches have demonstrated precise, faster and scalable outcomes, thus can be ideal to handle complex non-linear power systems. The recent technological developments in AI and hybrid techniques, makes it possible for solving large-scale complex power systems problems like control, planning, scheduling, prediction etc. This article has briefly discussed seven major areas, where AI has been used easily to handle constraints such as power system stability assessments, power system forecasting studies, power quality problems, optimization of generation scheduling, 5G network data communications, SCADA intrusion detection and transformer fault identification.

show abstract