While deep neural networks have been very successfully employed in classification problems, their stability properties remain still unclear. In particular, the presence of adversarial examples has demonstrated that state-of-the-art networks are vulnerable to small perturbations in the data. This course serves as an introduction to adversarial attacks and defenses for deep neural nework algorithms.
1. Theory: in this course, we will discuss the trade-off between accuracy and stability of classification algorithms and study the state-of-the-art for robust image classification, adversarial attacks and adversarial training. 2. Practice: students will train and attack deep neural networks themselves, to get a hands-on experience.
Prerequisites / Notice
Courses on linear algebra, optimization and machine learning. Basic programming skills in Python, and experience with PyTorch or TensorFlow.
Performance assessment information (valid until the course unit is held again)