Towards Modelling and Verification of Social Explainable AI

Damian Kurpiewski, Damian Kurpiewski, Wojciech Jamroga, Wojciech Jamroga, Teofil Sidoruk, Teofil Sidoruk

2023

Abstract

Social Explainable AI (SAI) is a new direction in artificial intelligence that emphasises decentralisation, transparency, social context, and focus on the human users. SAI research is still at an early stage. Consequently, it concentrates on delivering the intended functionalities, but largely ignores the possibility of unwelcome behaviours due to malicious or erroneous activity. We propose that, in order to capture the breadth of relevant aspects, one can use models and logics of strategic ability, that have been developed in multi-agent systems. Using the STV model checker, we take the first step towards the formal modelling and verification of SAI environments, in particular of their resistance to various types of attacks by compromised AI modules.

Paper Citation

in Harvard Style

Kurpiewski D., Jamroga W. and Sidoruk T. (2023). Towards Modelling and Verification of Social Explainable AI. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-623-1, pages 396-403. DOI: 10.5220/0011799900003393

in Bibtex Style

@conference{icaart23,
author={Damian Kurpiewski and Wojciech Jamroga and Teofil Sidoruk},
title={Towards Modelling and Verification of Social Explainable AI},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2023},
pages={396-403},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011799900003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Towards Modelling and Verification of Social Explainable AI
SN - 978-989-758-623-1
AU - Kurpiewski D.
AU - Jamroga W.
AU - Sidoruk T.
PY - 2023
SP - 396
EP - 403
DO - 10.5220/0011799900003393