DSTN Scholars
Start date : 01/06/2021
Issue :
The effects of the Internet of Things (IoT) are not going unnoticed, as they have turned our lives upside down, making it easier for people to work in all fields, including military, environmental, agricultural, medical, industrial and domestic. In fact
The fusion of IT (Information Technology) and OT (Operating Technology) in industrial power sector environments orchestrated by the IoT has enormously exposed critical infrastructures used at all operational stages (power generation, transmission and distribution) to critical cybersecurity risks (Stewart et al., 2017). This is compounded by the fact that PLCs and SCADA systems have not been designed to mitigate cyber attacks (Nicholson et al., 2012).
Current techniques of seeking and applying security patches from device suppliers and/or replacing units with security features are problematic, as patching and updating can result in control systems slowing down, rebooting and eventually shutting down (Ferrag et al., 2020; Zhang, Yang & Liao, 2016). There is a high cost in maintenance downtime and lost man-hours after each update, weakening the priority of availability over confidentiality and integrity in the CIA triad (AlGhazal & AlJubran, 2018). Current intrusion detection systems (IDSs) depend on the Purdue model, which are only capable of securing network boundaries. These IDSs alone are too weak to detect, deflect and deter new zero-day and MiTM attacks generated by intelligent techniques used by recent attackers (Hoque, Mukit & Bikas, 2012; Zarpelao et al., 2017).
The above problems are further compounded by an acute shortage of studies, models and testbeds that model attacks on SCADA systems in the power sector using bio-inspiration. There is a need to develop a multi-layered intelligent technique inspired by biological mechanisms and driven by machine learning algorithms to ensure better intrusion detection and protection of critical assets in the power sector. The above information reveals the importance of an in-depth study.