Alexander Schwankner M.Sc.

Research Area:

Alexander's research interests are in the area of the application of machine learning in IT security. He is particularly interested in the use of large language models and AI Agents and tries to apply them in the field of cyber security. He is also researching anomaly detection in networks, as well as 5G and 6G core network security.

He received his master's degree in IT security and his bachelor's degree in information systems from the Munich University of Applied Science. During his studies he worked as a IT-Security Consultant, Pentester and Software Developer at Protea Networks GmbH for about 4 years. Before his studies, he completed an apprenticeship as an IT specialist for software development at Telemotive AG. Afterwards, he worked as a software developer and team leader for software development as well as team leader for client software services at Telemotive AG for about 8 years.

Seminar/Bachelor/Master Thesis Topics:

Utilization of AI Agents for Automated Reconnaissance Phase in Penetration Testing: Recent advances in Artificial Intelligence (AI) and Machine Learning (ML) have enabled the development of autonomous agents that can perform various tasks with minimal human intervention. In the context of penetration testing, the reconnaissance phase is a critical step that involves gathering  information about the target system or network to identify potential vulnerabilities. This thesis explores the utilization of AI agents for automated reconnaissance phase in penetration testing.

Automated Attacks and Pentests on Computer Networks with Large Language Models: Recent research shows that large language models such as GPT-4 can be used not only for chat but also for generating code and commands. Therefore, this thesis evaluates the use of large language models for the automatic execution of attacks on computer networks. In doing so, the use of code interpreters and command lines is resorted to. To be able to implement this, you need to have knowledge in Linux, Python and Machine Learning.

Attack Detection in Computer Networks with Large Language Models: Large language models show their strengths in many areas and have become very capable of solving tasks other than chatting. Therefore, in this thesis you will investigate if and how large language models are able to detect attacks in computer networks.

Please approach me if you want to propose your own idea within my area of interest.