Christopher J. Anders

TL;DR: In this paper, the authors provide a timely overview of explainable AI, with a focus on 'post-hoc' explanations, explain its theoretical foundations, and put interpretability algorithms to a test both from a theory and comparative evaluation perspective using extensive simulations.

TL;DR: In this paper, the authors provide a timely overview of post hoc explanations and explain its theoretical foundations, and put interpretability algorithms to a test both from a theory and comparative evaluation perspective using extensive simulations, and demonstrate successful usage of XAI in a representative selection of application scenarios.

TL;DR: It is shown that explanations can be manipulated arbitrarily by applying visually hardly perceptible perturbations to the input that keep the network's output approximately constant, and theoretically this phenomenon can be related to certain geometrical properties of neural networks.

TL;DR: This work aims to provide a timely overview of this active emerging field of machine learning and explain its theoretical foundations, put interpretability algorithms to a test both from a theory and comparative evaluation perspective using extensive simulations, and outline best practice aspects.

TL;DR: In this paper, the authors show that explanations can be manipulated arbitrarily by applying visually hardly perceptible perturbations to the input that keep the network's output approximately constant, which is disconcerting for both trust and interpretability.