Data Leakage In Anonymization Methods Towards explainable machine learning
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20219069
- Paper/Info type
- Other International Conferences
- Pages
- 1-5(Total 5 p)
- Date of publication
- Sep 2021
- Publisher
- JSAE
- Language
- English
Detailed Information
Author(E) | 1) Martin Torstensson, 2) Felix Rosberg, 3) Boris Durán, 4) Cristofer Englund |
---|---|
Affiliation(E) | 1) RISE Research Institutes of Sweden, 2) Berge Consulting,Lindholmspiren 3A, 3) RISE Research Institutes of Sweden, 4) RISE Research Institutes of Sweden;Halmstad University |
Abstract(E) | Anonymization methods are one potential way of alleviating the risks of capturing personal information during data collections. The work presented here is based on one such method that, in turn, is based on generating images through machine learning to replace the original images. The chosen method merges both the original image and the generated one resulting in a risk of information from the original image leaking through to the final result. Here a possible approach to measure how much influence the original image has on the final product is presented . |