TU Darmstadt / ULB / TUprints

Lightweight Long Short-Term Memory Variational Auto-Encoder for Multivariate Time Series Anomaly Detection in Industrial Control Systems

Fährmann, Daniel ; Damer, Naser ; Kirchbuchner, Florian ; Kuijper, Arjan (2022):
Lightweight Long Short-Term Memory Variational Auto-Encoder for Multivariate Time Series Anomaly Detection in Industrial Control Systems. (Publisher's Version)
In: Sensors, 22 (8), MDPI, e-ISSN 1424-8220,
DOI: 10.26083/tuprints-00021287,
[Article]

[img] Text
sensors-22-02886-v2.pdf
Available under: CC BY 4.0 International - Creative Commons, Attribution.

Download (545kB)
Item Type: Article
Origin: Secondary publication DeepGreen
Status: Publisher's Version
Title: Lightweight Long Short-Term Memory Variational Auto-Encoder for Multivariate Time Series Anomaly Detection in Industrial Control Systems
Language: English
Abstract:

Heterogeneous cyberattacks against industrial control systems (ICSs) have had a strong impact on the physical world in recent decades. Connecting devices to the internet enables new attack surfaces for attackers. The intrusion of ICSs, such as the manipulation of industrial sensory or actuator data, can be the cause for anomalous ICS behaviors. This poses a threat to the infrastructure that is critical for the operation of a modern city. Nowadays, the best techniques for detecting anomalies in ICSs are based on machine learning and, more recently, deep learning. Cybersecurity in ICSs is still an emerging field, and industrial datasets that can be used to develop anomaly detection techniques are rare. In this paper, we propose an unsupervised deep learning methodology for anomaly detection in ICSs, specifically, a lightweight long short-term memory variational auto-encoder (LW-LSTM-VAE) architecture. We successfully demonstrate our solution under two ICS applications, namely, water purification and water distribution plants. Our proposed method proves to be efficient in detecting anomalies in these applications and improves upon reconstruction-based anomaly detection methods presented in previous work. For example, we successfully detected 82.16% of the anomalies in the scenario of the widely used Secure Water Treatment (SWaT) benchmark. The deep learning architecture we propose has the added advantage of being extremely lightweight.

Journal or Publication Title: Sensors
Volume of the journal: 22
Issue Number: 8
Publisher: MDPI
Collation: 23 Seiten
Uncontrolled Keywords: anomaly detection, pattern recognition, security
Classification DDC: 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik
Divisions: 20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Fraunhofer IGD
Date Deposited: 06 May 2022 11:08
Last Modified: 06 May 2022 11:08
DOI: 10.26083/tuprints-00021287
Corresponding Links:
URN: urn:nbn:de:tuda-tuprints-212876
SWORD Depositor: Deep Green
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/21287
PPN:
Export:
Actions (login required)
View Item View Item