Adversarial robustness and attacks in Deep Learning

dc.contributor.advisor	Швай, Надія
dc.contributor.author	Кузьменко, Дмитро
dc.date.accessioned	2024-04-11T12:45:58Z
dc.date.available	2024-04-11T12:45:58Z
dc.date.issued	2022
dc.description.abstract	The theoretical underpinnings for this field involve the notions of robustness and astuteness, local Lipschitzness, r-separability of datasets, robustness-accuracy tradeoff, and L-inf distance. This work will cover all the preliminaries, explain the choice of CIFAR-10 with L-inf metric space and eps=8/255 as a main dataset for the task, make use of already well-known attacks and defenses, introduce new ones, and try different ensembles on the 3 most robust models available on the benchmark – Adversarial Weight Perturbation, Augmentations and weight averaging, and Self-COnsistent Robust Error (SCORE-based model).	uk_UA
dc.identifier.uri	https://ekmair.ukma.edu.ua/handle/123456789/28873
dc.language.iso	uk	uk_UA
dc.relation.organisation	НаУКМА	uk_UA
dc.status	first published	uk_UA
dc.subject	Local Lipschitzness	uk_UA
dc.subject	Carlini-Wagner	uk_UA
dc.subject	Self-COnsistent Robust Error	uk_UA
dc.subject	Scale and std hyperparameters in Jitter	uk_UA
dc.subject	магістерська робота	uk_UA
dc.title	Adversarial robustness and attacks in Deep Learning	uk_UA
dc.type	Other	uk_UA

Now showing 1 - 2 of 2

Now showing 1 - 1 of 1