Адаптивні методи анонімізаціх даних
| dc.contributor.advisor | Швай, Надія | |
| dc.contributor.author | Ронська, Дарина | |
| dc.date.accessioned | 2022-01-17T21:34:24Z | |
| dc.date.available | 2022-01-17T21:34:24Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | Sometimes it is impossible to use the original image and only anonymized version of it is available (e.g., faces of the people or plate numbers on cars are blurred). In other words, we can use only edited version of the original image. Sometimes the class of the edited image is different from original one and we want to avoid this. This work is about gradient method which allows to get the class predicted for unchanged image for the one with blurred sensitive part by applying small changes in the edited area only. | uk_UA |
| dc.identifier.uri | https://ekmair.ukma.edu.ua/handle/123456789/22288 | |
| dc.language.iso | en | uk_UA |
| dc.status | first published | uk_UA |
| dc.subject | адаптивні методи | uk_UA |
| dc.subject | анонімізація даних | uk_UA |
| dc.subject | магістерська робота | uk_UA |
| dc.title | Адаптивні методи анонімізаціх даних | uk_UA |
| dc.type | Other | uk_UA |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Ronska_Adaptyvni_metody_anonimizatsikh_danykh.pdf
- Size:
- 1.18 MB
- Format:
- Adobe Portable Document Format
- Description:
- магістерська робота
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 7.54 KB
- Format:
- Item-specific license agreed upon to submission
- Description: