IWCT 2020
Sat 24 Oct 2020 Porto, Portugal
co-located with ICST 2020

This short paper introduces an approach to producing explanations or justifications of decisions made by artificial intelligence and machine learning (AI/ML) systems, using methods derived from fault location in combinatorial testing. We use a conceptually simple scheme to make it easy to justify classification decisions: identifying combinations of features that are present in members of the identified class and absent or rare in non-members. The method has been implemented in a prototype tool, and examples of its application are given.

Sat 24 Oct

Displayed time zone: Lisbon change

14:20 - 15:10
Test Generation and Combinatorial Testing Applications SessionIWCT 2020 at Farfetch (D. Maria)
14:20
20m
Full-paper
An Automata-Based Generation Method for Combinatorial Sequence Testing of Finite State Machines
IWCT 2020
Andrea Bombarda University of Bergamo, Angelo Gargantini University of Bergamo
Link to publication DOI
14:40
10m
Short-paper
Combinatorial Methods for Explainable AI
IWCT 2020
Rick Kuhn Natl Institute of Standards & Technology, Raghu Kacker National Institute of Standards and Technology, Jeff Yu Lei University of Texas at Arlington, Dimitris Simos SBA Research
Link to publication DOI
14:50
20m
Full-paper
Generation of Invalid Test Inputs from Over-Constrained Test Models for Combinatorial Robustness Testing
IWCT 2020
Konrad Fögen RWTH Aachen University, Horst Lichter RWTH Aachen University
Link to publication DOI