Abstract

Supervisory control and data acquisition (SCADA) systems monitor and control the critical infrastructures (CI) such as power generation, smart grids, oil–gas pipelines, wastewater management, and nuclear power plant. Due to the drastic increase in cyber attacks, maintaining SCADA systems has become a complex task. Difficulty in securing the SCADA has gained the attention of researchers in designing a robust intrusion detection system (IDS). However, existing machine-learning and statistical approaches fail to detect the cyber physical attacks with high detection rate. This paper presents a sine-cosine optimization based recurrent neural network (SCO-RNN) to detect the cyber physical attacks against SCADA systems and the performance of the proposed SCO-RNN was validated using the Secure Water Treatment (SWaT) dataset in terms of accuracy and detection rate.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call