Zobrazeno 1 - 4
of 4
pro vyhledávání: '"A��vodji, Ulrich"'
Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanation manipulation. In this paper, we investigate the capability of fairwashing attacks by analyzing their fidelity-unfairness tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::519f8ea59e321d9d84f89ad999eecdd0
http://arxiv.org/abs/2106.07504
http://arxiv.org/abs/2106.07504
Post-hoc explanation techniques refer to a posteriori methods that can be used to explain how black-box machine learning models produce their outcomes. Among post-hoc explanation techniques, counterfactual explanations are becoming one of the most po
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c61b63f6fc56ebd20ca1ee4f46ef4804
http://arxiv.org/abs/2009.01884
http://arxiv.org/abs/2009.01884
Recent works have demonstrated that machine learning models are vulnerable to model inversion attacks, which lead to the exposure of sensitive information contained in their training dataset. While some model inversion attacks have been developed in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::298bfcdea4b1385ef7b38bbfc2b35d7c
http://arxiv.org/abs/1909.11835
http://arxiv.org/abs/1909.11835
Autor:
A��vodji, Ulrich, Arai, Hiromi, Fortineau, Olivier, Gambs, S��bastien, Hara, Satoshi, Tapp, Alain
Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and generally complex -- produces its outcomes. Current approaches for solving this problem include model explanation, ou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe74799820fa17e4df8865ee0e058e8e
http://arxiv.org/abs/1901.09749
http://arxiv.org/abs/1901.09749