Scientists from TUD Dresden University of Technology (TUD), HAW Hamburg, Alpha Strike Labs GmbH and Traversals Analytics und Intelligence GmbH want to protect the Internet from AI attacks in the joint BMBF project "AI.Auto-Immune", which is funded with 3.79 million euros. The TUD is coordinating the project and is receiving 1.1 million euros in funding.

Artificial intelligence (AI) is ideal for collecting huge amounts of data, analyzing it and reacting on the basis of the knowledge gained. Attackers exploit these advantages to threaten IT systems. AI is therefore increasingly becoming a central component of cyber security.

Attackers can use sophisticated AI technologies not only to search for individual, known vulnerabilities in a targeted manner, but also to automatically explore the attack surface of IT infrastructures. In doing so, AI varies previous attack techniques and develops ways to circumvent automated protection mechanisms based on known signatures or patterns.

The joint project AI.Auto-Immune aims to protect the internet and its services from AI-based attacks. The scientists will work on new methods to evaluate communication data and network flows on the internet using AI algorithms in order to find vulnerabilities. The intelligent analysis of network services helps to identify patterns and emerging new threats at an early stage and adapt security measures accordingly. In this way, danger points can be predicted automatically and protection recommendations can be made for them, for example by the AI generating situation pictures of attack points for certain network areas such as internal company networks or critical infrastructures.

Matthias Wählisch, Chair of Distributed and Networked Systems at TU Dresden and network coordinator, is delighted with the project approval: "Strengthening the security of globally distributed and networked systems is enormously important and will be with us for the long term. We can only win the race against the attackers if we understand the limits of AI-based attacks on the one hand and use AI to react more flexibly and quickly to emerging threats on the other." His team, together with scientists from the Chair of Machine Learning for Computer Vision headed by Björn Andres, will focus on the topics of "Internet measurements and clustering methods for securing Internet services". In particular, the aim is to recognize conspicuous patterns in communication services even if they are previously unknown.

"AI.Auto-Immune is not only very important for further scientific successes against AI-based attacks on the Internet. The project is also of the utmost importance for our university as an institution and for Dresden as a science location," emphasizes TUD Rector Prof. Ursula Staudinger and thanks the university's participating researchers for their extraordinary commitment in this field.

AI.Auto-Immune is funded by the German government's research framework program on IT security "Digital. Secure. Sovereign." in the measure "Secure future technologies in a hyper-connected world: Artificial Intelligence".

Contact person:

Prof. Matthias Wählisch
Phone: +49 351 463-38261
E-mail