Adversarial robustness and attacks in Deep Learning Керівни

Швай, НадіяКузьменко, Дмитро2024-04-112024-04-112022https://ekmair.ukma.edu.ua/handle/123456789/28873The 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).ukLocal LipschitznessCarlini-WagnerSelf-COnsistent Robust ErrorScale and std hyperparameters in Jitterмагістерська роботаAdversarial robustness and attacks in Deep Learning КерівниOther