Impact of adversarial sparsity as an auxiliary metric in adversarial robustness
| dc.contributor.advisor | Швай, Надія | |
| dc.contributor.author | Кузьменко, Дмитро | |
| dc.date.accessioned | 2024-03-21T09:28:04Z | |
| dc.date.available | 2024-03-21T09:28:04Z | |
| dc.date.issued | 2023 | |
| dc.description.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. | uk_UA |
| dc.identifier.uri | https://ekmair.ukma.edu.ua/handle/123456789/28325 | |
| dc.language.iso | uk | uk_UA |
| dc.status | first published | uk_UA |
| dc.subject | CIFAR-10 | uk_UA |
| dc.subject | RobustBench | uk_UA |
| dc.subject | сomputer Vision tasks | uk_UA |
| dc.subject | Basic Iterative Method (BIM) | uk_UA |
| dc.subject | Projected Gradient Descent (PGD) | uk_UA |
| dc.subject | Fast Gradient Sign Method (FGSM) | uk_UA |
| dc.subject | master thesis | uk_UA |
| dc.title | Impact of adversarial sparsity as an auxiliary metric in adversarial robustness | uk_UA |
| dc.type | Other | uk_UA |
Files
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: