Start Over

Detecting Potential Local Adversarial Examples for Human-Interpretable Defense

Authors :: Christophe Marsala
Xavier Renard
Marie-Jeanne Lesot
Thibault Laugel
Marcin Detyniecki
Learning, Fuzzy and Intelligent systems (LFI)
LIP6
Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)
Source :: ECML PKDD 2018 Workshops ISBN: 9783030134525, Nemesis/UrbReas/SoGood/IWAISe/GDM@PKDD/ECML, Workshop on Recent Advances in Adversarial Learning (Nemesis) of the European Conference on Machine Learning and Principles of Practice of Knowledge Discovery in Databases (ECML-PKDD), Workshop on Recent Advances in Adversarial Learning (Nemesis) of the European Conference on Machine Learning and Principles of Practice of Knowledge Discovery in Databases (ECML-PKDD), Sep 2018, Dublin, Ireland
Publication Year :: 2019
Publisher :: Springer International Publishing, 2019.
Abstract: Machine learning models are increasingly used in the industry to make decisions such as credit insurance approval. Some people may be tempted to manipulate specific variables, such as the age or the salary, in order to get better chances of approval. In this ongoing work, we propose to discuss, with a first proposition, the issue of detecting a potential local adversarial example on classical tabular data by providing to a human expert the locally critical features for the classifier's decision, in order to control the provided information and avoid a fraud.<br />presented at 2018 ECML/PKDD Workshop on Recent Advances in Adversarial Machine Learning (Nemesis 2018), Dublin, Ireland

Details

ISBN :: 978-3-030-13452-5
ISBNs :: 9783030134525
Database :: OpenAIRE
Journal :: ECML PKDD 2018 Workshops ISBN: 9783030134525, Nemesis/UrbReas/SoGood/IWAISe/GDM@PKDD/ECML, Workshop on Recent Advances in Adversarial Learning (Nemesis) of the European Conference on Machine Learning and Principles of Practice of Knowledge Discovery in Databases (ECML-PKDD), Workshop on Recent Advances in Adversarial Learning (Nemesis) of the European Conference on Machine Learning and Principles of Practice of Knowledge Discovery in Databases (ECML-PKDD), Sep 2018, Dublin, Ireland
Accession number :: edsair.doi.dedup.....d488b7e06298d9b96ea586837983b22b
Full Text :: https://doi.org/10.1007/978-3-030-13453-2_4