SUSAN: A Deep Learning based anomaly detection framework for sustainable industry

• Published in: Sustainable computing informatics and systems Vol. 37; p. 100842
• Main Authors: Gómez, Ángel Luis Perales, Maimó, Lorenzo Fernández, Celdrán, Alberto Huertas, Clemente, Félix J. García
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.01.2023
• Subjects: Anomaly detection; Deep learning; Industrial control systems; Machine learning; Sustainability; Deep learning; Industrial control systems; Sustainability; Anomaly detection; Machine learning
• ISSN: 2210-5379
• DOI: 10.1016/j.suscom.2022.100842

Nowadays, sustainability is the core of green technologies, being a critical aspect in many industries concerned with reducing carbon emissions and energy consumption optimization. While this concern increases, the number of cyberattacks causing sustainability issues in industries also grows. These cyberattacks impact industrial systems that control and monitor the right functioning of processes and systems. Furthermore, they are very specialized, requiring knowledge about the target industrial processes, and being undetectable for traditional cybersecurity solutions. To overcome this challenge, we present SUSAN, a Deep Learning-based framework, to build anomaly detectors that expose cyberattacks affecting the sustainability of industrial systems. SUSAN follows a modular and flexible design that allows the ensembling of several detectors to achieve more precise detections. To demonstrate the feasibility of SUSAN, we implemented the framework in a water treatment plant using the SWaT testbed. The experiments performed achieved the best recall rate (0.910) and acceptable precision (0.633), resulting in an F1-score of 0.747. Regarding individual cyberattacks that impact the system’s sustainability, our implementation detected all of them, and, concerning the related work, it achieved the most balanced results, with 0.64 as the worst recall rate. Finally, a false-positive rate of 0.000388 makes our solution feasible in real scenarios. •Anomaly Detection based on Deep Learning techniques improves the sustainability in the Industry.•Resource-consumption features help the model to discriminate between normal and abnormal behavior.•Autocorrelation and Fourier Transform help to extract higher-order features from industrial systems.•An Anomaly Detection Ensembler allows detecting different types of anomalies.