Slides and poster can also be found on the project page.
Due to German data protection laws, it is currently not possible to include the video directly, so please head over to YouTube using the link below!Watch on YouTube
In October this year, my work on relating adversarially robust generalization to flat minima in the (robust) loss surface with respect to weight perturbations was presented at ICCV’21. As oral presentation at ICCV’21, I recorded a 12 minute talk highlighting the main insights how (robust) flatness can avoid robust overfitting of adversarial training and improve robustness against adversarial examples. In this article, I want to share the recording.