Machine Learning – The Results Are Not the only Thing that Matters! What About Security, Explainability and Fairness?
Authors:
- Michał ChoraśMichał Choraś
- Marek PawlickiMPMarek Pawlicki
- Damian PuchalskiDPDamian Puchalski
- Rafał KozikRKRafał Kozik
- 15 June 2020
- book chapter
- Published by Springer Nature
- Vol. 12140, 615-628
Abstract
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.Keywords
This publication has 13 references indexed in Scilit:
- Machine Learning Interpretability: A Survey on Methods and MetricsElectronics, 2019
- Towards Complementary Explanations Using Deep Neural Networks2018
- Perturbation-Based Explanations of Prediction Models2018
- Fairness definitions explained2018
- Explainable artificial intelligence: A survey2018
- SoK: Security and Privacy in Machine Learning2018
- Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization2017
- Fairness Beyond Disparate Treatment & Disparate Impact2017
- PATTERN RECOGNITION SYSTEMS UNDER ATTACK: DESIGN ISSUES AND RESEARCH CHALLENGESInternational Journal of Pattern Recognition and Artificial Intelligence, 2014
- Secure Machine Learning, a Brief Overview2011