Autoencoder Based Anomaly Detection for SCADA Networks

Sajid Nazir, Shushma Patel, Dilip Patel

Source Title: International Journal of Artificial Intelligence and Machine Learning (IJAIML)11(2)

ISSN: 2642-1577|EISSN: 2642-1585|EISBN13: 9781799864110|DOI: 10.4018/IJAIML.20210701.oa6

MLA

Nazir, Sajid, et al. "Autoencoder Based Anomaly Detection for SCADA Networks." IJAIML vol.11, no.2 2021: pp.83-99. http://doi.org/10.4018/IJAIML.20210701.oa6

APA

Nazir, S., Patel, S., & Patel, D. (2021). Autoencoder Based Anomaly Detection for SCADA Networks. International Journal of Artificial Intelligence and Machine Learning (IJAIML), 11(2), 83-99. http://doi.org/10.4018/IJAIML.20210701.oa6

Chicago

Nazir, Sajid, Shushma Patel, and Dilip Patel. "Autoencoder Based Anomaly Detection for SCADA Networks," International Journal of Artificial Intelligence and Machine Learning (IJAIML) 11, no.2: 83-99. http://doi.org/10.4018/IJAIML.20210701.oa6

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

Supervisory control and data acquisition (SCADA) systems are industrial control systems that are used to monitor critical infrastructures such as airports, transport, health, and public services of national importance. These are cyber physical systems, which are increasingly integrated with networks and internet of things devices. However, this results in a larger attack surface for cyber threats, making it important to identify and thwart cyber-attacks by detecting anomalous network traffic patterns. Compared to other techniques, as well as detecting known attack patterns, machine learning can also detect new and evolving threats. Autoencoders are a type of neural network that generates a compressed representation of its input data and through reconstruction loss of inputs can help identify anomalous data. This paper proposes the use of autoencoders for unsupervised anomaly-based intrusion detection using an appropriate differentiating threshold from the loss distribution and demonstrate improvements in results compared to other techniques for SCADA gas pipeline dataset.