为端到端AI流程设计可密码验证的框架，保障可信与可审计。
A Framework for Cryptographic Verifiability of End-to-End AI Pipelines
- 提出全流程可验证框架，涵盖数据、训练、推理与删除
- 利用密码学证明实现生成内容的来源与正确性可验证
- 适合关注AI监管与防伪的开发者与政策制定者
人工智能在多行业深度集成，亟需透明、可信与可审计的机制。本文提出完整的可验证AI流程框架，识别关键组件，并分析现有密码学方法在数据获取、训练、推理及删除等阶段的可验证性贡献。该框架可通过附加密码学证明，使下游能验证AI生成内容的出处与正确性，从而应对虚假信息。研究强调需发展高效且可跨环节链接的密码工具，以支持端到端可验证AI技术的发展。
原文摘要 · Abstract (English)
The increasing integration of Artificial Intelligence across multiple industry sectors necessitates robust mechanisms for ensuring transparency, trust, and auditability of its development and deployment. This topic is particularly important in light of recent calls in various jurisdictions to introduce regulation and legislation on AI safety. In this paper, we propose a framework for complete verifiable AI pipelines, identifying key components and analyzing existing cryptographic approaches that contribute to verifiability across different stages of the AI lifecycle, from data sourcing to training, inference, and unlearning. This framework could be used to combat misinformation by providing cryptographic proofs alongside AI-generated assets to allow downstream verification of their provenance and correctness. Our findings underscore the importance of ongoing research to develop cryptographic tools that are not only efficient for isolated AI processes, but that are efficiently `linkable' across different processes within the AI pipeline, to support the development of end-to-end verifiable AI technologies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。