Trust modelling and verification using Event-B
Trust modelling and verification using Event-B
Trust is a crucial component in collaborative multiagent systems (MAS) involving humans and autonomous AI agents. Rather than assuming trust based on past system behaviours, it is important to formally verify trust by modelling the current state and capabilities of agents. We argue for verifying actual trust relations based on agents' abilities to deliver intended outcomes in specific contexts. To enable reasoning about different notions of trust, we propose using the refinement-based formal method Event-B. Refinement allows progressively introducing new aspects of trust - from abstract to concrete models incorporating knowledge and runtime states. We demonstrate modelling three trust concepts and verifying associated trust properties in MAS. The formal, correctness-by-construction approach allows to deduce guarantees about trustworthy autonomy in human-AI partnerships. Overall, our contribution facilitates rigorous verification of trust in multiagent systems.
Trust, multiagent systems, Trustworthy Autonomous Systems, Citizen-Centric AI Systems, Event-B
Salehi Fathabadi, Asieh
b799ee35-4032-4e7c-b4b2-34109af8aa75
Yazdanpanah, Vahid
28f82058-5e51-4f56-be14-191ab5767d56
15 November 2023
Salehi Fathabadi, Asieh
b799ee35-4032-4e7c-b4b2-34109af8aa75
Yazdanpanah, Vahid
28f82058-5e51-4f56-be14-191ab5767d56
Salehi Fathabadi, Asieh and Yazdanpanah, Vahid
(2023)
Trust modelling and verification using Event-B.
<br/>Fifth Workshop on Formal Methods for Autonomous Systems<br/>, , Leiden, Netherlands.
15 - 16 Nov 2023.
7 pp
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Trust is a crucial component in collaborative multiagent systems (MAS) involving humans and autonomous AI agents. Rather than assuming trust based on past system behaviours, it is important to formally verify trust by modelling the current state and capabilities of agents. We argue for verifying actual trust relations based on agents' abilities to deliver intended outcomes in specific contexts. To enable reasoning about different notions of trust, we propose using the refinement-based formal method Event-B. Refinement allows progressively introducing new aspects of trust - from abstract to concrete models incorporating knowledge and runtime states. We demonstrate modelling three trust concepts and verifying associated trust properties in MAS. The formal, correctness-by-construction approach allows to deduce guarantees about trustworthy autonomy in human-AI partnerships. Overall, our contribution facilitates rigorous verification of trust in multiagent systems.
Text
FMAS2023_UoS
- Version of Record
More information
Accepted/In Press date: 2023
Published date: 15 November 2023
Venue - Dates:
<br/>Fifth Workshop on Formal Methods for Autonomous Systems<br/>, , Leiden, Netherlands, 2023-11-15 - 2023-11-16
Keywords:
Trust, multiagent systems, Trustworthy Autonomous Systems, Citizen-Centric AI Systems, Event-B
Identifiers
Local EPrints ID: 482874
URI: http://eprints.soton.ac.uk/id/eprint/482874
PURE UUID: 85bbde51-87fe-420f-9c0b-ec0cea5bde4c
Catalogue record
Date deposited: 16 Oct 2023 16:37
Last modified: 18 Mar 2024 03:57
Export record
Contributors
Author:
Asieh Salehi Fathabadi
Author:
Vahid Yazdanpanah
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics