arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.07039cs.AIcs.CRcs.CY
收藏

AI的协同缺陷披露:超越安全漏洞

Coordinated Flaw Disclosure for AI: Beyond Security Vulnerabilities

AI Village(AI村);Hugging Face

Sven Cattell, Avijit Ghosh, Lucie-Aimée Kaffee

AI总结:

针对AI算法缺陷披露缺乏结构化流程的问题,提出协同缺陷披露(CFD)框架,引入扩展模型卡、独立裁决小组等创新机制,以增强公众信任并改善AI问责制。

摘要:

人工智能(AI)领域的危害报告目前缺乏用于披露和处理算法缺陷的结构化流程,主要依赖于临时性方法。这与软件安全领域完善的协同漏洞披露(CVD)生态系统形成鲜明对比。尽管全球正在努力建立AI透明度与协作框架,但机器学习(ML)模型带来的独特挑战需要一种专门的方法。为弥补这一空白,我们提出实施一种针对ML和AI问题复杂性量身定制的协同缺陷披露(CFD)框架。本文回顾了ML披露实践的发展,从临时报告到新兴的参与式审计方法,并将其与网络安全规范进行了比较。我们的框架引入了扩展模型卡、动态范围扩展、独立裁决小组和自动化验证流程等创新。我们还概述了即将进行的CFD真实世界试点。我们认为CFD可以显著增强公众对AI系统的信任。通过平衡组织与社区利益,CFD旨在快速演进的技术环境中改善AI问责制。

英文摘要:

Harm reporting in Artificial Intelligence (AI) currently lacks a structured process for disclosing and addressing algorithmic flaws, relying largely on an ad-hoc approach. This contrasts sharply with the well-established Coordinated Vulnerability Disclosure (CVD) ecosystem in software security. While global efforts to establish frameworks for AI transparency and collaboration are underway, the unique challenges presented by machine learning (ML) models demand a specialized approach. To address this gap, we propose implementing a Coordinated Flaw Disclosure (CFD) framework tailored to the complexities of ML and AI issues. This paper reviews the evolution of ML disclosure practices, from ad hoc reporting to emerging participatory auditing methods, and compares them with cybersecurity norms. Our framework introduces innovations such as extended model cards, dynamic scope expansion, an independent adjudication panel, and an automated verification process. We also outline a forthcoming real-world pilot of CFD. We argue that CFD could significantly enhance public trust in AI systems. By balancing organizational and community interests, CFD aims to improve AI accountability in a rapidly evolving technological landscape.

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。

↑