While deep neural networks have been very successfully employed in classification problems, their stability properties remain still unclear. In particular, the presence of so-called adversarial examples has demonstrated that state-of-the-art networks are extremely vulnerable to small perturbations in the data.
Lernziel
In this seminar, we will consider the state-of-the-art in adversarial attacks and defenses.
Voraussetzungen / Besonderes
Participants should already be familiar with the principles of deep neural networks. The course will also include programming that will require knowledge in using either PyTorch or Tensorflow.
