Representation of Trustworthiness Components in AI Systems: A Formalized Approach Considering Interconnections and Overlap

Скорочена інформація про документ
dc.contributor.authorManziuk, Eduard
dc.contributor.authorBarmak, Oleksandr
dc.contributor.authorRadiuk, Pavlo
dc.contributor.authorKuznetsov, Vladislav
dc.contributor.authorKrak, Iurii
dc.date.accessioned2024-10-30T18:38:36Z
dc.date.available2024-10-30T18:38:36Z
dc.date.issued2024-10-05
dc.description.abstractThe study addresses the problem of integrating trustworthiness components into artificial intelligence (AI) systems. A new method is proposed to determine the interdependence and intersection of concepts in the field of trustworthy AI. The approach provides a structured way to assess the interconnections and overlaps between different trustworthiness concepts, offering a more complete understanding of their complex interaction. A method for assessing the degree of coincidence between different trustworthiness components is proposed, which allows for a more accurate analysis of their interconnections. The results of experimental studies have shown the level of interconnection between the concepts, with an average level of overlap of about 67%. A formal model for integrating trustworthiness components into AI systems has also been developed. This model provides a framework for evaluating the actions of an AI agent against several trustworthiness criteria simultaneously. The approach takes into account different contexts and scenarios, providing a more robust and flexible assessment of trustworthy AI. By bridging the gap between theoretical concepts and practical implementation, this work contributes to the development of trustworthy AI systems. The proposed work also provides a more structured and formalized approach to understanding and implementing trustworthy AI. Furthermore, this research aims to contribute to the development of AI systems that are built on ethical principles and societal values.
dc.identifier.citationRepresentation of trustworthiness components in AI systems: A formalized approach considering interconnections and overlap / E. Manziuk et al. 4th International Workshop of IT-professionals on Artificial Intelligence 2024 (ProfIT AI 2024) : CEUR-Workshop Proceedings, Cambridge, MA, USA, 25–27 September 2024 / ed. by D. Chumachenko et al. Vol. 3777. CEUR-WS.org, Aachen, 2024. P. 405–417. URL: https://ceur-ws.org/Vol-3777/paper25.pdf
dc.identifier.issn1613–0073
dc.identifier.urihttps://elar.khmnu.edu.ua/handle/123456789/16951
dc.language.isoen
dc.subjecttrustworthy AI
dc.subjectconcept interdependence
dc.subjectformal modeling trustworthiness
dc.subjectethical AI
dc.subjectreliability assessment
dc.subjecttrustworthiness integration
dc.subjectartificial intelligence ethics
dc.subjectAI safety
dc.titleRepresentation of Trustworthiness Components in AI Systems: A Formalized Approach Considering Interconnections and Overlap
dc.typeТези доповідей
Файли
Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
Manziuk_Representation-of-Trustworthiness.pdf
Розмір:
1.32 MB
Формат:
Adobe Portable Document Format
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Назва:
license.txt
Розмір:
4.26 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити
Зібрання
Кафедра комп’ютерних наук