Winter 2025/2026

Instructor: Adam Dziedzic

Contact: adam.dziedzic@cispa.de

Lectures: Wednesday 14:00-16:00, CISPA C0 building (on campus)

Exercise Sessions: Roles rotate weekly (Presenters, Questioners, Observers). Check description for detail.

CMS

Description

Deploying machine learning in real-world systems necessitates methods to ensure trustworthy AI. This course explores research at the intersection of machine learning, privacy, and security. This course provides a comprehensive overview of techniques to build robust and trustworthy machine learning models, focusing on neural networks. We will examine seminal work on privacy-preserving machine learning methods. Our primary focus will be on Large Language Models (LLMs) and Diffusion Models (DMs). Throughout the course, we will discuss outstanding challenges and future research directions to make machine learning more robust, private, and trustworthy.

Class Structure: In every class, we will discuss two papers. At the beginning of the semester, students will be assigned roles that will rotate every week:

1. The Presenters: Two students. Each presents a paper and takes the lead in answering questions.
2. The Questioners: Responsible for preparing a list of questions. Questions must be prepared during the preceding week and sent to the class by 5 pm Monday.
3. The Observers: Take notes on a shared document during discussion capturing major take-away points and resolve unresolved questions.

Assignments

The seminar incorporates project work to foster research skills and creativity. Students select papers aligning with their interests, present them, and design a project with the potential to evolve into a scientific publication. Each student writes a comprehensive report detailing their findings and includes code to validate their results.

• Weekly Questions: Turn in at least 1 question per paper each week when acting as a Questioner.
• Seminar Paper / Project Report: Comprehensive report detailing project findings and code (submitted at the end of the semester).
• Project Presentations: Two 10-minute presentation sessions to showcase project progress and innovations at the end of the semester.

Feedback

Online Communication and feedback are handled via Discord. Please ask the instructor for the link to the server via email.

Course Staff

• Adam Dziedzic (Instructor)