The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in
Deep Learning

The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning

13 September 2023

Alexander Bastounis

Alexander N. Gorban

Anders C. Hansen

Danil Prokhorov

Oliver J. Sutton

ArXiv (abs)PDF HTML

Papers citing "The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning"

6 / 6 papers shown

Title
The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks Alexander Bastounis A. Hansen Verner Vlacic AAML OOD 74 28 0 13 Sep 2021
High-dimensional separability for one- and few-shot learning Alexander N. Gorban Bogdan Grechuk Evgeny M. Mirkes Sergey V. Stasenko I. Tyukin DRL 69 23 0 28 Jun 2021
Are adversarial examples inevitable? Ali Shafahi Wenjie Huang Christoph Studer Soheil Feizi Tom Goldstein SILM 64 283 0 06 Sep 2018
Stochastic Separation Theorems A. N. Gorban I. Tyukin 53 50 0 03 Mar 2017
Universal adversarial perturbations Seyed-Mohsen Moosavi-Dezfooli Alhussein Fawzi Omar Fawzi P. Frossard AAML 139 2,527 0 26 Oct 2016
Intriguing properties of neural networks Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna D. Erhan Ian Goodfellow Rob Fergus AAML 275 14,927 1 21 Dec 2013