Machine Learning – The Results Are Not the only Thing that Matters! What About Security, Explainability and Fairness?

Recent advances in machine learning (ML) and the surge in computational power have opened the way to the proliferation of ML and Artificial Intelligence (AI) in many domains and applications. Still, apart from achieving good accuracy and results, there are many challenges that need to be discussed i...

Descripción completa

Detalles Bibliográficos
Autores principales: Choraś, Michał, Pawlicki, Marek, Puchalski, Damian, Kozik, Rafał
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7303684/
http://dx.doi.org/10.1007/978-3-030-50423-6_46
_version_ 1783548112595320832
author Choraś, Michał
Pawlicki, Marek
Puchalski, Damian
Kozik, Rafał
author_facet Choraś, Michał
Pawlicki, Marek
Puchalski, Damian
Kozik, Rafał
author_sort Choraś, Michał
collection PubMed
description Recent advances in machine learning (ML) and the surge in computational power have opened the way to the proliferation of ML and Artificial Intelligence (AI) in many domains and applications. Still, apart from achieving good accuracy and results, there are many challenges that need to be discussed in order to effectively apply ML algorithms in critical applications for the good of societies. The aspects that can hinder practical and trustful ML and AI are: lack of security of ML algorithms as well as lack of fairness and explainability. In this paper we discuss those aspects and provide current state of the art analysis of the relevant works in the mentioned domains.
format Online
Article
Text
id pubmed-7303684
institution National Center for Biotechnology Information
language English
publishDate 2020
record_format MEDLINE/PubMed
spelling pubmed-73036842020-06-19 Machine Learning – The Results Are Not the only Thing that Matters! What About Security, Explainability and Fairness? Choraś, Michał Pawlicki, Marek Puchalski, Damian Kozik, Rafał Computational Science – ICCS 2020 Article Recent advances in machine learning (ML) and the surge in computational power have opened the way to the proliferation of ML and Artificial Intelligence (AI) in many domains and applications. Still, apart from achieving good accuracy and results, there are many challenges that need to be discussed in order to effectively apply ML algorithms in critical applications for the good of societies. The aspects that can hinder practical and trustful ML and AI are: lack of security of ML algorithms as well as lack of fairness and explainability. In this paper we discuss those aspects and provide current state of the art analysis of the relevant works in the mentioned domains. 2020-05-23 /pmc/articles/PMC7303684/ http://dx.doi.org/10.1007/978-3-030-50423-6_46 Text en © Springer Nature Switzerland AG 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Article
Choraś, Michał
Pawlicki, Marek
Puchalski, Damian
Kozik, Rafał
Machine Learning – The Results Are Not the only Thing that Matters! What About Security, Explainability and Fairness?
title Machine Learning – The Results Are Not the only Thing that Matters! What About Security, Explainability and Fairness?
title_full Machine Learning – The Results Are Not the only Thing that Matters! What About Security, Explainability and Fairness?
title_fullStr Machine Learning – The Results Are Not the only Thing that Matters! What About Security, Explainability and Fairness?
title_full_unstemmed Machine Learning – The Results Are Not the only Thing that Matters! What About Security, Explainability and Fairness?
title_short Machine Learning – The Results Are Not the only Thing that Matters! What About Security, Explainability and Fairness?
title_sort machine learning – the results are not the only thing that matters! what about security, explainability and fairness?
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7303684/
http://dx.doi.org/10.1007/978-3-030-50423-6_46
work_keys_str_mv AT chorasmichał machinelearningtheresultsarenottheonlythingthatmatterswhataboutsecurityexplainabilityandfairness
AT pawlickimarek machinelearningtheresultsarenottheonlythingthatmatterswhataboutsecurityexplainabilityandfairness
AT puchalskidamian machinelearningtheresultsarenottheonlythingthatmatterswhataboutsecurityexplainabilityandfairness
AT kozikrafał machinelearningtheresultsarenottheonlythingthatmatterswhataboutsecurityexplainabilityandfairness

Ejemplares similares