Edge security: AI-Driven Threat Detection in Industrial Control Systems

Immerse yourself in the forefront of industrial cybersecurity within Industrial Control Systems (ICS) and Edge-to-Cloud technology through our compelling BSc/MSc thesis project! Our research delves into the realm of anomaly detection, time series analysis, and artificial intelligence, aiming to fortify industrial operations against cyber threats.  Our focus is on using cutting-edge techniques such as edge detection, hierarchical learning, and multi-modal approaches to build a strong defense that covers everything from the edge of the system to the cloud. Join us in uncovering the secrets of cyber resilience in industrial settings, where each discovery brings us closer to a safer and more connected future.

Student Target Groups:

  • Students of ICE/Telematics;
  • Students of Computer Science;
  • Students of Software Engineering.

Thesis Type:

  • Master Thesis / Bachelor Thesis

Goal and Tasks:

The goal of this work is to investigate state-of-the-art hierarchical learning methods in an ICS environment, with a special focus on multi-modal approaches that should include fusion of different types of data, in order to detect anomalies originating from cyber intruders. First experiments should be done using publically available datasets and both centralised anomaly detection and edge detection, while later on more challenging data readings will be provided in the project, including different types of data. This work also includes investigation embedded AI possibilities in this type of environments.

  • Thorough literature research on the topic;
  • Select suitable anomaly detection methods;
  • Select suitable hierarchical learning method;
  • Select suitable multi-modal data fusion technique;
  • Design and conduct experiments to investigate the applicability of selected methods in such an environment;
  • Summarize the results in a written report, and prepare an oral presentation.

Recommended Prior Knowledge:

  • Programming skills in Python;
  • Prior experience with deep learning frameworks is desirable (preferably PyTorch).
  • Interest in the topic.


  • a.s.a.p.