The course will provide an overview of state-of-the-art research on the trustworthiness of foundation models. The course material will comprise research papers covering three different perspectives: (a) red teaming and adversarial testing, focusing on the security aspects of foundation models, (b) fake content generation and watermarking, focusing on content authenticity, and (c) poisoning attacks and robust training, focusing on training-time robustness considerations. This course will familiarize participants with cutting-edge methods employed to assess or enhance the trustworthiness of foundation models.
The students will be asked to write reports on the papers assigned to them and present one of these papers. This course will additionally offer students hands-on experience with foundation models within the context of the topics discussed.
Course Staff
To reach us, please use the following email address: trustworthy-ai-s24-tutors@mpi-sws.org. Please use personal emails only for communication that is not related to this seminar.
Important Information
We will post the most important announcements below, but additional information may be communicated via email. Please check this website regularly for updates.
- The registration deadline is April 17th. Interested students should register through https://seminars.cs.uni-saarland.de/.
- The introductory session will take place on Tuesday April 30 at 9:00am. Location: Room 005 at MPI-SWS (Building E1 5).