AI-based Network Assessment, Policy Definition, and Enforcement of Security in Complex Networks (WINTERMUTE, funded by BMBF)
|Partner||genua GmbH (Kirchheim bei München) |
acsplus GmbH (Berlin)
IsarNet Software Solutions GmbH (München)
|Funded period||April 2020 - March 2023|
|Researcher||Prof. Dr. Tobias Hoßfeld |
Dr. Michael Seufert
Nicholas Gray M. Sc.
Katharina Dietz M. Sc.
As a result of current trends towards device automation, such as Internet of Things and Industry 4.0, network administrators have to manage more and more complex communication systems. These systems are a popular target for potential attackers, since sensitive data is exchanged and the communication has to meet strict time constraints. Thus, it is an essential task to secure the ongoing communication appropriately.
This project aims to ensure safe communication with the help of Artificial Intelligence (AI) and Machine Learning (ML) under two main aspects: privacy and usability. While the preservation of secure communication is important, a violation of privacy has to be prevented. Additionally, the goal is to provide a user-friendly solution, since current approaches only emphasize the intrusion detection aspect of the problem, and thus, make it difficult to be incorporated without highly specialised experts. Nevertheless, the goal of this project is not to replace human IT experts, but rather to support these specialists in their decision making by providing an assessment of the current network situation.
genua GmbH is an IT-specialist based in Kirchheim (Munich) and operates as project coordinator. Besides University of Würzburg, other academic partners such as University of Bamberg and University of Bremen are involved. Furthermore, industrial partners also take an important role in the project, namely acs plus GmbH (Berlin) und IsarNet Software Solutions GmbH (Munich). This grants both the relevancy to practice and the incorporation of recent scientific research. The main focus of University of Würzburg is the analysis of adequate data sources, the extraction of this data, and the evaluation of different ML approaches to process the extracted information.