Enhanced SCADA IDS Security by Using MSOM Hybrid Unsupervised Algorithm

Enhanced SCADA IDS Security by Using MSOM Hybrid Unsupervised Algorithm

Sangeetha K., Shitharth S., Gouse Baig Mohammed
DOI: 10.4018/IJWLTT.20220301.oa2
Article PDF Download
Open access articles are freely available for download

Abstract

In Self-Organizing Maps (SOM) are unsupervised neural networks that cluster high dimensional data and transform complex inputs into easily understandable inputs. To find the closest distance and weight factor, it maps high dimensional input space to low dimensional input space. The Closest node to data point is denoted as a neuron. It classifies the input data based on these neurons. The reduction of dimensionality and grid clustering using neurons makes to observe similarities between the data. In our proposed Mutated Self Organizing Maps (MSOM) approach, we have two intentions. One is to eliminate the learning rate and to decrease the neighborhood size and the next one is to find out the outliers in the network. The first one is by calculating the median distance (MD) between each node with its neighbor nodes. Then those median values are compared with one another. In case, if any of the MD values significantly varies from the rest then it is declared as anomaly nodes. In the second phase, we find out the quantization error (QE) in each instance from the cluster center.
Article Preview
Top

1.Introduction

Supervisory control and data acquisition system are such an integral part of the latest automation industries. This receives data from various sources like sensors, RTU (Remote Terminal Units) and smart meters. The major tasks performed by SCADA (Rakas et al., 2020; Tamy et al., n.d.) is to monitor the connected data fetching sources. SCADA systems are mainly used to control and monitoring purposes in various industrial applications. It can be used for a small office building to monitor environmental conditions also used to monitor complex conditions in a nuclear power plant SCADA (Ferrag et al., 2020; Khan et al., 2019; Waagsnes & Ulltveit-Moe, n.d.) . To protect control systems, systems are evaluated before being deployed in production. So the operators have a good understanding of what types of vulnerability those systems may be introducing into their environment. One of the challenges of control systems is that many of them have been developed in an environment that works very well in operations, but they don’t have all of the cybersecurity safeguards built into them (Shitharth et al., 2021; Suaboot et al., 2020). Sensor nodes which sense physical phenomenon that occur around them. These sensor nodes are majorly used for medical purposes, agriculture, industrial purposes, and so on. SCADA system uses wired or wireless sensor networks to transport the data from the master station. SCADA systems mainly use wireless sensor networks due to their frequent changing topology nature and the possibility of reconfiguration of networks. Using the wireless sensor networks this information or data is transmitted through a router, firewall, and switches. The first layer of protection is a router. The router should be configured with a VPN tunnel on the router side. Firewalls in control systems are used to protect unauthorized access (Priyanga et al., 2019; Teixeira et al., 2018). Data should be encrypted, to increase the level of information security, while accessing information through the internet. Various security threats (Gao et al., n.d.; Gao et al., 2020; Shitharth & Winston, 2016) are evolving every day like unauthorized access to the control software, virus infection and one more major threat is intruders sending malicious packets to host devices. By sending these packets anyone can control the SCADA devices.

Complete Article List

Search this Journal:
Reset
Volume 19: 1 Issue (2024)
Volume 18: 2 Issues (2023)
Volume 17: 8 Issues (2022)
Volume 16: 6 Issues (2021)
Volume 15: 4 Issues (2020)
Volume 14: 4 Issues (2019)
Volume 13: 4 Issues (2018)
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing