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 Data might be outdated or incorrect.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 16:02:04
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
- DR
Examination
- Type
- ungraded semester performance
Registration & Places
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
-
Doctorate Mathematics (More Information at: )
-
Subject Specialisation (The list of courses (together with the allocated credit points) eligible for doctoral students is published each semester in the newsletter of the ZGSM.)
-
Graduate School (Official website of the Zurich Graduate School in Mathematics:)
-
-