263-2400-00L Reliable and Trustworthy Artificial Intelligence
| Semester | Autumn Semester 2024 |
| Lecturers | M. Vechev |
| Periodicity | yearly recurring course |
| Language of instruction | English |
| Abstract | Creating reliable, secure, robust, and fair machine learning models is a core challenge in artificial intelligence and one of fundamental importance. The goal of the course is to teach both the mathematical foundations of this new and emerging area as well as to introduce students to the latest and most exciting research in the space. | ||||||||||||||||||
| Learning objective | Upon completion of the course, the students should have mastered the underlying methods and be able to apply them to a variety of engineering and research problems. To facilitate deeper understanding, the course includes a group coding project where students will build a system based on the learned material. | ||||||||||||||||||
| Content | The course is split into 4 parts: Robustness of Machine Learning -------------------------------------------- - Adversarial attacks and defenses on deep learning models. - Automated certification of deep learning models (major trends: convex relaxations, branch-and-bound, randomized smoothing). - Certified training of deep neural networks (combining symbolic and continuous methods). Privacy of Machine Learning -------------------------------------- - Threat models (e.g., stealing data, poisoning, membership inference, etc.). - Attacking federated machine learning (across vision, natural language and tabular data). - Differential privacy for defending machine learning. - AI Regulations and checking model compliance. Fairness of Machine Learning --------------------------------------- - Introduction to fairness (motivation, definitions). - Enforcing individual fairness (for both vision and tabular data). - Enforcing group fairness (e.g., demographic parity, equalized odds). Robustness, Privacy and Fairness of Foundation Models --------------------------------------------------------------------------- - We discuss all previous topics, as well as programmability, in the context of latest foundation models (e.g., LLMs). More information here: https://www.sri.inf.ethz.ch/teaching/rtai24. | ||||||||||||||||||
| Prerequisites / Notice | While not a formal requirement, the course assumes familiarity with basics of machine learning (especially linear algebra, gradient descent, and neural networks as well as basic probability theory). These topics are usually covered in “Intro to ML” classes at most institutions (e.g., “Introduction to Machine Learning” at ETH). The coding project will utilize Python and PyTorch. Thus some programming experience in Python is expected. Students without prior knowledge of PyTorch are expected to acquire it early in the course by solving exercise sheets. | ||||||||||||||||||
Competencies |
|