Das Frühjahrssemester 2021 findet grundsätzlich online statt. Neue Präsenzelemente ab 26. April werden von den Dozierenden mitgeteilt.

401-3620-19L  Student Seminar in Statistics: Adversarial and Robust Machine Learning

SemesterFrühjahrssemester 2019
DozierendeP. L. Bühlmann, M. H. Maathuis, N. Meinshausen, S. van de Geer
Periodizitätjedes Semester wiederkehrende Veranstaltung
LehrspracheEnglisch
KommentarMaximale Teilnehmerzahl: 22

Hauptsächlich für Studierende der Bachelor- und Master-Studiengänge Mathematik, welche nach der einführenden Lerneinheit 401-2604-00L Wahrscheinlichkeit und Statistik (Probability and Statistics) mindestens ein Kernfach oder Wahlfach in Statistik besucht haben. Das Seminar wird auch für Studierende der Master-Studiengänge Statistik bzw. Data Science angeboten.


KurzbeschreibungAs statistical and machine learning models are increasingly employed in many real-world applications it becomes more important to understand the vulnerabilities and robustness properties of these models.
In the first part of this seminar, we will study papers relating to adversarial examples. In the second part of the course, we will review other types of distribution shifts.
LernzielAfter this seminar, you should know
- properties of adversarial examples
- some attacks and defenses
- some concepts from robust optimization and distributional robustness
- other distribution shifts that can fool machine learning models in general and neural networks in particular
InhaltAs statistical and machine learning models are increasingly employed in many real-world applications it becomes more important to understand the vulnerabilities and robustness properties of these models. In the first part of this seminar, we will study papers relating to adversarial examples, covering their properties, various attacks and defenses. In the second part of the course, we will review other types of distribution shifts, posing significant challenges for state-of-the-art machine learning models. Some parts of the seminar will be devoted to implementing these methods in python.
Voraussetzungen / BesonderesWe require at least one course in statistics or machine learning and basic knowledge in computer programming. Some background knowledge in deep learning is helpful but not strictly required.
Topics will be assigned during the first meeting.