arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.05765cs.AIcs.LO
收藏

规范时逻辑在AI伦理形式验证中的应用

Deontic Temporal Logic for Formal Verification of AI Ethics

International Institute of Information Technology - Bangalore(国际信息技术研究所-班加罗尔)

Priya T. V., Shrisha Rao

AI总结:

本文提出基于规范逻辑的AI伦理形式化方法,用于验证AI系统在公平性和可解释性方面的伦理行为,通过自动定理证明器验证实际系统是否满足伦理要求。

摘要:

确保人工智能系统在日益普及和影响力增强的情况下表现出道德行为是一个全球性的重要问题。在AI伦理中使用形式方法是一种可能的关键方法,用于指定和验证AI系统的道德行为。本文提出基于规范逻辑的形式化方法,用于定义和评估AI系统的道德行为,重点是系统级规范,为这一重要目标做出贡献。它引入了公理和定理来捕捉与公平性和可解释性相关的伦理要求。形式化过程中加入了时间运算符,以在时间上推理AI系统的道德行为。作者通过评估现实中的COMPAS和贷款预测AI系统的伦理来评估该形式化的有效性。通过将COMPAS和贷款预测系统的各种伦理属性编码为规范逻辑公式,允许使用自动定理证明器验证这些系统是否满足定义的属性。形式验证揭示了这两个系统未能满足某些关键的公平性和非歧视性伦理属性,展示了所提出形式化方法在识别现实AI应用中的潜在伦理问题方面的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑