We offer a number of courses each semester that revolve around machine learning and security. These include lectures on learning algorithms in security systems and adversarial machine learning as well as our labs where people can experiment with attacks and malicious code. Teaching is fun for us and so we have been able to even win awards for our lectures and practical courses.
This lab is a hands-on course that explores machine learning in computer security. Students design and develop intelligent systems for security problems such as attack detection, malware clustering, and vulnerability discovery. The developed systems are trained and evaluated on real-world data, providing insight into their strengths and weaknesses in practice. The lab is a continuation of the lecture "Machine Learning for Computer Security" and thus knowledge from that course is expected.
This project explores how large language modules, such as ChatGPT, can be used for steganography. Students will form a red team (attackers) and a blue team (defenders). The red team will develop techniques to hide secret messages in generated texts, while the blue team will develop methods to detect these messages. The color of the teams will change after some time. The project is aimed at Master students. A good understanding of language models and strong programming skills are required.
This block seminar explores attacks on explainable artificial intelligence (XAI). We will examine different explanation methods and learn about attacks that can manipulate explanations at inference and training time. We also take a look at privacy leaks of XAI and corresponding inference attacks. The seminar is intended for Master students. A basic understanding of machine learning is strongly recommended.
In this block seminar, we will look at unusual ways in which an attacker can obtain secret information. We examine various physical side channels through which information can escape from a computer, such as acoustic, optical, and electromagnetic leaks. We also examine the security and privacy implications of the attacks and discuss appropriate defenses. The seminar is aimed at Bachelor students. No prior knowledge of side channels is required, but a strong interest is assumed.
Are you looking for an exciting topic for your Bachelor or Master thesis? We offer research-oriented thesis topics on machine learning and security, which we design together with the students. Contact Prof. Rieck by email and ask for further details. Please include the result of
(23**42)%2248 in the subject line.