AML — Adversarial Machine Learning

This integrated lecture is concerned with adversarial machine learning. It explores various attacks on learning algorithms, including white-box and black-box adversarial examples, poisoning, backdoors, membership inference, and model extraction. It also examines the security and privacy implications of these attacks and discusses defensive strategies, ranging from threat modeling to integrated countermeasures.

   Course Website    Module 41117 Type: Lecture Audience: Master

SMARTLAB — Smart Security Lab

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.

   Course Website    Module 41116 Type: Lab course Audience: Master

MONSOON — LLM-based Network Scanning

This project explores the use of large language models (LLMs) for automated vulnerability detection. Participants will extend Google’s Tsunami network scanner using LLM-generated plugins. The course involves experimenting with LLMs to translate vulnerability reports into scanner logic, evaluating the quality and reliability of generated plugins, and designing improvements. The overall goal is to assess the feasibility of LLM-driven network scanning and to gain hands-on experience at AI in security.

   Course Website    Module 41102 Type: Project Audience: Master

RAID — Reproducing AI Attacks and Defense

This project puts recent AI research to the test. Participants will re-implement current attack and defense techniques that utilize machine learning, evaluate their capabilities, and design improvements. Possible techniques include attacks and defenses for large language models and computer vision systems. The overall goal is to learn about the state of the art in AI security and reproduce results where possible.

   Course Website    Module 41102 Type: Project Audience: Master

CARE — Code Analysis and Reverse Engineering

This block seminar is concerned with the analysis and reverse engineering of code. We will cover different techniques for program analysis of source code and binary code. In addition, we will look at concepts for understanding unknown software, reverse engineering its functionality, and discovering security vulnerabilities. The seminar is intended for Master students.

   Course Website    Module 41104 Type: Seminar Audience: Master

SEPA — Security and Privacy of AI

This block seminar focuses on security and privacy in artificial intelligence and machine learning. We will examine recent attacks on learning algorithms and discuss their impact on practical security and privacy. We will also look at possible defenses and countermeasures to protect learning algorithms and the underlying data. The seminar is intended for Bachelor students.

   Course Website    Module 41103 Type: Seminar Audience: Bachelor