no code implementations • 21 Dec 2023 • Catherine F. Higham, Desmond J. Higham, Peter Grindrod
We provide a brief introduction to diffusion models for applied mathematicians and statisticians.
no code implementations • 28 Nov 2023 • Lucas Beerens, Desmond J. Higham
We develop and assess algorithms for both targeted and untargeted attacks.
no code implementations • 13 Sep 2023 • Alexander Bastounis, Alexander N. Gorban, Anders C. Hansen, Desmond J. Higham, Danil Prokhorov, Oliver Sutton, Ivan Y. Tyukin, Qinghua Zhou
We consider classical distribution-agnostic framework and algorithms minimising empirical risks and potentially subjected to some weights regularisation.
no code implementations • 7 Sep 2023 • Oliver J. Sutton, Qinghua Zhou, Ivan Y. Tyukin, Alexander N. Gorban, Alexander Bastounis, Desmond J. Higham
We introduce a simple generic and generalisable framework for which key behaviours observed in practical systems arise with high probability -- notably the simultaneous susceptibility of the (otherwise accurate) model to easily constructed adversarial attacks, and robustness to random perturbations of the input data.
no code implementations • 5 Sep 2023 • Stefano Di Giovacchino, Desmond J. Higham, Konstantinos Zygalakis
Stochastic optimization methods have been hugely successful in making large-scale optimization problems feasible when computing the full gradient is computationally prohibitive.
no code implementations • 29 Aug 2023 • Desmond J. Higham
Over the last decade, adversarial attack algorithms have revealed instabilities in deep learning tools.
no code implementations • 5 Jun 2023 • Lucas Beerens, Desmond J. Higham
We also study the use of a componentwise condition number to quantify vulnerability.
no code implementations • 26 Jun 2021 • Ivan Y. Tyukin, Desmond J. Higham, Alexander Bastounis, Eliyas Woldegeorgis, Alexander N. Gorban
Such a stealth attack could be conducted by a mischievous, corrupt or disgruntled member of a software development team.
1 code implementation • 15 Jan 2021 • Francesco Tudisco, Desmond J. Higham
Network scientists have shown that there is great value in studying pairwise interactions between components in a system.
Social and Information Networks Numerical Analysis Numerical Analysis Data Analysis, Statistics and Probability
no code implementations • 9 Apr 2020 • Ivan Y. Tyukin, Desmond J. Higham, Alexander N. Gorban
We show that in both cases, i. e., in the case of an attack based on adversarial examples and in the case of a stealth attack, the dimensionality of the AI's decision-making space is a major contributor to the AI's susceptibility.
1 code implementation • 25 Apr 2018 • Francesco Tudisco, Desmond J. Higham
We derive and analyse a new iterative algorithm for detecting network core--periphery structure.
Social and Information Networks Numerical Analysis Data Analysis, Statistics and Probability
2 code implementations • 17 Jan 2018 • Catherine F. Higham, Desmond J. Higham
This article provides a very brief introduction to the basic ideas that underlie deep learning from an applied mathematics perspective.