Impact of adversarial sparsity as an auxiliary metric in adversarial robustness
Loading...
Date
2023
Authors
Кузьменко, Дмитро
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The purpose of this research is to investigate adversarial sparsity in computer vision models and introduce a more efficient method for adversarial sparsity estimation. To fulfil this objective, the following tasks have been undertaken: To implement and evaluate an n-Ary search algorithm as an improvement over the conventional binary search method used in adversarial sparsity estimation. To benchmark and compare the performance of the proposed n-Ary search algorithm against the traditional binary search algorithm. To explore the implications of adversarial sparsity on the robustness of machine learning models.
Description
Keywords
CIFAR-10, RobustBench, сomputer Vision tasks, Basic Iterative Method (BIM), Projected Gradient Descent (PGD), Fast Gradient Sign Method (FGSM), master thesis