VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

401-4660-70L 4 Credits BSC , MSC D-MATH

Robustness of Deep Neural Networks

Lecturers & Examiners: Dr. Rima Alaifari
Number of participants limited to 40
VVZ CR n/a

Last Updated: 2026-02-05 15:34:40

Abstract

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.

Objective

In this seminar, we will consider the state-of-the-art in adversarial attacks and defenses.

General Information

Language
English
Levels
BSC , MSC

Examination

Type
ungraded semester performance

Registration & Places

Limited places (Special selection)
Signup Start
01.08.2020
Signup End
11.09.2020
Priority: Registration for the course unit is only possible for the primary target group

Course Components

Type Title Time & Place Hours
seminar Robustness of Deep Neural Networks
The lecturers will communicate the exact lesson times of ONLINE courses.
  • Mon 14:00-16:00 (ON LI NE)
2 h weekly

Offered In

  • Mathematics Bachelor
    • Seminars (This semester, many seminars have a waiting list with special selection procedure. If no other criteria apply, a definitive registration will be granted first of all to students who haven't got another seminar registration. Here is the best procedure for dealing with two waiting lists: first choose your preferred seminar and afterwards choose an alternative seminar.)
  • Mathematics Master
    • Seminars and Semester Papers
      • Seminars (This semester, many seminars have a waiting list with special selection procedure. If no other criteria apply, a definitive registration will be granted first of all to students who haven't got another seminar registration. Here is the best procedure for dealing with two waiting lists: first choose your preferred seminar and afterwards choose an alternative seminar.)