Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

MediaEval 2019: concealed FGSM perturbations for privacy preservation

Linardos, Panagiotis, Little, Suzanne orcid logoORCID: 0000-0003-3281-3471 and McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477 (2019) MediaEval 2019: concealed FGSM perturbations for privacy preservation. In: MediaEval 2019 workshop, 27-29 Oct 2019, Sophia Antipolis, France.

Abstract
This work tackles the Pixel Privacy task put forth by MediaEval 2019. Our goal is to decrease the accuracy of a classification algorithm while preserving the original image quality. We use the fast gradient sign method, which normally has a corrupting influence on image appeal, and devise two methods to minimize the damage. The first approach uses a map that is a combination of salient and flat areas. Perturbations are more noticeable in these locations, and so are directed away from them. The second approach adds the gradient of an aesthetic algorithm to the gradient of the attacking algorithm to guide the perturbations towards a direction that preserves appeal. We make our code available at: https://git.io/JesXr
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:No
Subjects:Computer Science > Algorithms
Computer Science > Image processing
Computer Science > Machine learning
Engineering > Signal processing
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Published in: Working Notes Proceedings of the MediaEval 2019 Workshop. CEUR Workshop Proceedings 1(2670). CEUR-WS.
Publisher:CEUR-WS
Official URL:http://ceur-ws.org/Vol-2670/MediaEval_19_paper_11....
Copyright Information:© 2019 The Authors
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland (SFI) under grant number SFI/15/SIRG/3283 and SFI/12/RC/2289
ID Code:23779
Deposited On:25 Oct 2019 12:16 by Kevin Mcguinness . Last Modified 25 Jul 2022 12:17
Documents

Full text available as:

[thumbnail of MediaEval_2019___Pixel_Privacy.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
857kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record