Research Group
Machine Learning
and Security
and Security
View from our building over Berlin.
We offer different Bachelor and Master courses that revolve around machine learning and computer security. Following is a list of all courses offered in the summer term 2024.
MLSEC — Machine Learning for Computer Security
This integrated lecture is concerned with using machine learning in computer security. Many tasks in security, such as the analysis of malicious software or the discovery of vulnerabilities, rest on manual work. Methods from machine learning can help accelerate this process and make security systems more intelligent. The lecture explores different approaches for constructing such learning-based security systems.
This lab is a hands-on, entry-level course that explores the security analysis of systems. It provides an introduction to practical system security and serves a preparation for later advanced security labs. This includes developing strategies and tools for security analysis as well as investigating the security of real-world systems. In each unit of the lab, a different system is analyzed, ranging from Android applications to network hosts.
SEGA — Security Playground for Generative Agents
This project deals with the development of a security playground for generative agents. The agents are small characters that autonomously move through the playground and talk with each other. They are controlled by large language models, such as ChatGPT. The user can instruct the agents and simulate different attacks with them. The students develop the playground and the agents in teams. The project is aimed at Master students. A good understanding of web technology and good programming skills are required.
STEMO — Steganography with Language Models
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.
PASIL — Privacy and Security in Learning
This block seminar focuses on privacy and security in machine learning. We will examine recent attacks on learning algorithms and discuss their impact on practical privacy and security. We will also look at possible defenses and countermeasures to protect learning algorithms and the underlying data. The seminar is intended for Master students.
MOPS — Mobile Privacy and Security
This block seminar deals with the security and privacy of mobile devices. We will discuss different concepts for analyzing and detecting security threats, such as attacks and malicious software. Futhermore, we will explore defense strategies suitable for mobile environments. The seminar is intended for Bachelor students. A good understanding of computer security is required.
Are you looking for an exciting topic for your Bachelor or Master thesis? Simply contact Prof. Rieck. Note that we do not have a list of "off the shelf" topics. Instead, we try to find interesting thesis topics together with the students that align with our current research.