Skip to Content.
Sympa Menu

fizinfo - [Fizinfo] USZ FSI IP seminar: Márk Jelasity, 07. 02. 2024. 3:00 pm, Budó auditorium &/ online + link

fizinfo AT lists.kfki.hu

Subject: ELFT HÍRADÓ

List archive

[Fizinfo] USZ FSI IP seminar: Márk Jelasity, 07. 02. 2024. 3:00 pm, Budó auditorium &/ online + link


Chronological Thread 
  • From: mcsete AT physx.u-szeged.hu
  • To: fizinfo AT lists.kfki.hu
  • Subject: [Fizinfo] USZ FSI IP seminar: Márk Jelasity, 07. 02. 2024. 3:00 pm, Budó auditorium &/ online + link
  • Date: Mon, 05 Feb 2024 17:30:59 +0100
  • Authentication-results: smtp012.wigner.hu (amavisd-new); dkim=pass (2048-bit key) header.d=physx.u-szeged.hu


Seminar

Speaker: Prof. Márk Jelasity
Department of Algorithms and AI
University of Szeged

Date: 07, February (Wednesday) 2024, 3:00 pm
Location: USZ FSI IP, Budó auditorium & online
https://join.skype.com/Kq14BLX30ftv

Title:
Adversarial Robustness of Deep Neural Networks

Deep neural networks (DNNs) are the foundations of AI systems, yet they are known to have several vulnerabilities that are unsolved to this day. A particularly interesting vulnerability is that it is possible to construct inputs to these networks that are extremely close to natural inputs (eg. invisible perturbations to images) yet result in completely unexpected behaviour. This adversarial behaviour can even be designed in advance. In the talk I will give several examples of this problem, and I will also present some of our own results in the area. I will briefly touch on the formal verification of neural networks from the point of view of adversarial robustness, and I will also discuss some applications like attacking semantic image segmentation networks and attacking entire ensembles of models.

Everyone is welcome to attend.

Dr. Mária Csete


----------------------------------------------------------------
This message was sent using IMP, the Internet Messaging Program.

Attachment: pngIhV6Gy6rM1.png
Description: PNG image



  • [Fizinfo] USZ FSI IP seminar: Márk Jelasity, 07. 02. 2024. 3:00 pm, Budó auditorium &/ online + link, mcsete, 02/05/2024

Archive powered by MHonArc 2.6.19+.

Top of Page