Membership Inference Attack for Beluga Whales Discrimination ...
To efficiently monitor the growth and evolution of a particular wildlife population, one of the main fundamental challenges to address in animal ecology is the re-identification of individuals that have been previously encountered but also the discrimination between known and unknown individuals (th...
Main Authors: | , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2302.14769 https://arxiv.org/abs/2302.14769 |
id |
ftdatacite:10.48550/arxiv.2302.14769 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2302.14769 2023-05-15T15:41:44+02:00 Membership Inference Attack for Beluga Whales Discrimination ... Araújo, Voncarlos Marcelo Gambs, Sébastien Chion, Clément Michaud, Robert Schneider, Léo Lautraite, Hadrien 2023 https://dx.doi.org/10.48550/arxiv.2302.14769 https://arxiv.org/abs/2302.14769 unknown arXiv Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences Article article Preprint CreativeWork 2023 ftdatacite https://doi.org/10.48550/arxiv.2302.14769 2023-04-03T12:47:48Z To efficiently monitor the growth and evolution of a particular wildlife population, one of the main fundamental challenges to address in animal ecology is the re-identification of individuals that have been previously encountered but also the discrimination between known and unknown individuals (the so-called "open-set problem"), which is the first step to realize before re-identification. In particular, in this work, we are interested in the discrimination within digital photos of beluga whales, which are known to be among the most challenging marine species to discriminate due to their lack of distinctive features. To tackle this problem, we propose a novel approach based on the use of Membership Inference Attacks (MIAs), which are normally used to assess the privacy risks associated with releasing a particular machine learning model. More precisely, we demonstrate that the problem of discriminating between known and unknown individuals can be solved efficiently using state-of-the-art approaches for MIAs. ... : 15 pages ... Article in Journal/Newspaper Beluga Beluga* DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences Araújo, Voncarlos Marcelo Gambs, Sébastien Chion, Clément Michaud, Robert Schneider, Léo Lautraite, Hadrien Membership Inference Attack for Beluga Whales Discrimination ... |
topic_facet |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
description |
To efficiently monitor the growth and evolution of a particular wildlife population, one of the main fundamental challenges to address in animal ecology is the re-identification of individuals that have been previously encountered but also the discrimination between known and unknown individuals (the so-called "open-set problem"), which is the first step to realize before re-identification. In particular, in this work, we are interested in the discrimination within digital photos of beluga whales, which are known to be among the most challenging marine species to discriminate due to their lack of distinctive features. To tackle this problem, we propose a novel approach based on the use of Membership Inference Attacks (MIAs), which are normally used to assess the privacy risks associated with releasing a particular machine learning model. More precisely, we demonstrate that the problem of discriminating between known and unknown individuals can be solved efficiently using state-of-the-art approaches for MIAs. ... : 15 pages ... |
format |
Article in Journal/Newspaper |
author |
Araújo, Voncarlos Marcelo Gambs, Sébastien Chion, Clément Michaud, Robert Schneider, Léo Lautraite, Hadrien |
author_facet |
Araújo, Voncarlos Marcelo Gambs, Sébastien Chion, Clément Michaud, Robert Schneider, Léo Lautraite, Hadrien |
author_sort |
Araújo, Voncarlos Marcelo |
title |
Membership Inference Attack for Beluga Whales Discrimination ... |
title_short |
Membership Inference Attack for Beluga Whales Discrimination ... |
title_full |
Membership Inference Attack for Beluga Whales Discrimination ... |
title_fullStr |
Membership Inference Attack for Beluga Whales Discrimination ... |
title_full_unstemmed |
Membership Inference Attack for Beluga Whales Discrimination ... |
title_sort |
membership inference attack for beluga whales discrimination ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2302.14769 https://arxiv.org/abs/2302.14769 |
genre |
Beluga Beluga* |
genre_facet |
Beluga Beluga* |
op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_doi |
https://doi.org/10.48550/arxiv.2302.14769 |
_version_ |
1766374620831678464 |