A Classy Multifacet Clustering and Fused Optimization Based Classification Methodologies for SCADA Security

Detecting intrusions from the supervisory control and data acquisition (SCADA) systems is one of the most essential and challenging processes in recent times. Most of the conventional works aim to develop an efficient intrusion detection system (IDS) framework for increasing the security of SCADA ag...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energies (Basel) 2022-05, Vol.15 (10), p.3624
Hauptverfasser: Khadidos, Alaa, Manoharan, Hariprasath, Selvarajan, Shitharth, Khadidos, Adil, Alyoubi, Khaled, Yafoz, Ayman
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Detecting intrusions from the supervisory control and data acquisition (SCADA) systems is one of the most essential and challenging processes in recent times. Most of the conventional works aim to develop an efficient intrusion detection system (IDS) framework for increasing the security of SCADA against networking attacks. Nonetheless, it faces the problems of complexity in classification, requiring more time for training and testing, as well as increased misprediction results and error outputs. Hence, this research work intends to develop a novel IDS framework by implementing a combination of methodologies, such as clustering, optimization, and classification. The most popular and extensively utilized SCADA attacking datasets are taken for this system’s proposed IDS framework implementation and validation. The main contribution of this work is to accurately detect the intrusions from the given SCADA datasets with minimized computational operations and increased accuracy of classification. Additionally the proposed work aims to develop a simple and efficient classification technique for improving the security of SCADA systems. Initially, the dataset preprocessing and clustering processes were performed using the multifacet data clustering model (MDCM) in order to simplify the classification process. Then, the hybrid gradient descent spider monkey optimization (GDSMO) mechanism is implemented for selecting the optimal parameters from the clustered datasets, based on the global best solution. The main purpose of using the optimization methodology is to train the classifier with the optimized features to increase accuracy and reduce processing time. Moreover, the deep sequential long short term memory (DS-LSTM) is employed to identify the intrusions from the clustered datasets with efficient data model training. Finally, the proposed optimization-based classification methodology’s performance and results are validated and compared using various evaluation metrics.
ISSN:1996-1073
1996-1073
DOI:10.3390/en15103624