VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Robustness of Deep Neural Networks
Last Updated: 2026-02-05 16:02:14
Abstract
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.
Objective
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.
General Information
- Language
- English
- Levels
- MSC
Examination
- Type
- graded semester performance
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| lecture with exercise | Robustness of Deep Neural Networks |
|
2 h weekly |
| independent project | Robustness of Deep Neural Networks | No time listed | 1 h weekly |
Offered In
-
-
Electives (For the Master's degree in Applied Mathematics the following additional condition (not manifest in myStudies) must be obeyed: At least 15 of the required 28 credits from core courses and electives must be acquired in areas of applied mathematics and further application-oriented fields.)
-
-