Ensuring ethical behavior in Artificial Intelligence (AI) systems amidst their increasing ubiquity and influence is a major concern the world over. The use of formal methods in AI ethics is a possible crucial approach for specifying and verifying the ethical behavior of AI systems. This paper proposes a formalization based on deontic logic to define and evaluate the ethical behavior of AI systems, focusing on system-level specifications, contributing to this important goal. It introduces axioms and theorems to capture ethical requirements related to fairness and explainability. The formalization incorporates temporal operators to reason about the ethical behavior of AI systems over time. The authors evaluate the effectiveness of this formalization by assessing the ethics of the real-world COMPAS and loan prediction AI systems. Various ethical properties of the COMPAS and loan prediction systems are encoded using deontic logical formulas, allowing the use of an automated theorem prover to verify whether these systems satisfy the defined properties. The formal verification reveals that both systems fail to fulfill certain key ethical properties related to fairness and non-discrimination, demonstrating the effectiveness of the proposed formalization in identifying potential ethical issues in real-world AI applications.
Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment
German Research Center for Artificial Intelligence(德国人工智能研究中心);Center for European Research in Trusted AI (CERTAIN)(可信AI欧洲研究中心);Saarland Informatics Campus(萨尔州信息学校区);Computer Science Department, TU Darmstadt(图宾根大学计算机科学系)
Toward Robust Legal Text Formalization into Defeasible Deontic Logic using LLMs
TU Wien(维也纳技术大学);AIT Austrian Institute of Technology(奥地利技术研究所);School of Engineering and Technology(工程与技术学院);Artificial Intelligence and Cyber Futures Institute(人工智能与未来网络研究院)
Action Languages Based Actual Causality for Computational Ethics: a Sound and Complete Implementation in ASP
Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);National Institute of Informatics(国立信息学研究所);École Normale Supérieure(巴黎高等师范学院);Université PSL(巴黎文理研究大学);Collège de France(法兰西公学院)
From Ethical Declarations to Provable Independence: An Ontology-Driven Optimal-Transport Framework for Certifiably Fair AI Systems
Senior Scientist, Trustworthy AI, Luxembourg Institute of Science \& Technology, Maison de l'innovation 5, L-4362, Luxembourg Chief Investment Risk Strategist for Sovereign Institutions Founder, RsRL, Jumeirah Beach Residence (JBR), P.O.Box 29215, Dubai, United Arab Emirates
Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping
Koguan School of Law, China Institute for Smart Justice, School of Computer Science, Shanghai Jiao Tong University(柯 guar 法学院、中国智能正义研究院、计算机科学学院、上海交通大学)
fEDM+: A Risk-Based Fuzzy Ethical Decision Making Framework with Principle-Level Explainability and Pluralistic Validation
Dept. of Informatics, University of Bari ``Aldo Moro'', Bari, Italy(信息学院,巴里阿尔多·莫罗大学);Centro Interdipartimentale di Logica e Applicazioni (CILA), University of Bari ``Aldo Moro'', Bari, Italy(逻辑与应用跨部门中心(CILA),巴里阿尔多·莫罗大学)
A Fuzzy Approach to the Specification, Verification and Validation of Risk-Based Ethical Decision Making Models
Dept. of Informatics, University of Bari ``Aldo Moro'', Bari, Italy(信息学院,巴勒莫大学,意大利);Centro Interdipartimentale di Logica e Applicazioni (CILA), University of Bari ``Aldo Moro'', Bari, Italy(逻辑与应用研究中心(CILA),巴勒莫大学,意大利)
Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving
Chair of Econometrics and Statistics Corresponding author esp. in the Transport Sector(计量经济学与统计学教授职位(交通运输领域特别对应作者));Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)(可扩展数据与人工智能研究中心(ScaDS.AI))