Investigation of the evaluation techniques and tools used for model-specific XAI models

Bachelor Thesis (2022)
Author(s)

Tanguy Marbot (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

C. Lal – Mentor (TU Delft - Cyber Security)

Mauro Conti – Mentor (TU Delft - Cyber Security)

Joana P. Gonçalves – Graduation committee member (TU Delft - Pattern Recognition and Bioinformatics)

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2022 Tanguy Marbot
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 Tanguy Marbot
Graduation Date
24-06-2022
Awarding Institution
Delft University of Technology
Project
['CSE3000 Research Project']
Programme
['Computer Science and Engineering']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The spread of AI techniques has lead to its presence in critical situations, with increasing performance that can compromise on its understanding. Users with no prior AI knowledge rely on these techniques such as doctors or recruiters with a need for transparency and comprehensibility of the mechanisms. The advent of Explainable Artificial Intelligence techniques responds to such issues with a diversity that has lead to the construction of a taxonomy for this domain. Notably, there is a distinction between model-specific and model-agnostic techniques. Rightly operational XAI technique should go through an evaluation process. In this paper, we investigate the different available tools and metrics for the evaluation of XAI techniques to then assess the evaluation quality of five state-of-the-art model specific techniques: TCAV, SIDU, ACE, Net2Vec and Concept Analysis with ILP. It has been concluded that despite broad existing literature on evaluation methods, there is a lack of exhaustive assessment of criteria and a lack of standardization in regards of the evaluation of these model-specific- techniques.

Files

License info not available