Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

  • 类型:arxiv
  • 标识:2004.07213
  • 链接:https://arxiv.org/abs/2004.07213
  • 主题:agent
  • 主分类:risk
  • 形态:position
  • 被引:502
  • 被引来源:Semantic Scholar
  • S2被引:502
  • OpenAlex被引:297
  • 影响力被引:32
  • TLDR:This report suggests various steps that different stakeholders can take to improve the verifiability of claims made about AI systems and their associated development processes, with a focus on providing evidence about the safety, security, fairness, and privacy protection of AI systems.
  • OpenAlex ID:W4287552728
  • OpenAlex DOI:10.48550/arxiv.2004.07213
  • DOI:10.48550/arxiv.2004.07213
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/2004.07213
  • OpenAlex更新:2026-09-30
  • 待LLM分类:否
  • 成熟度:research
  • 场景:trustworthy AI、AI governance、verification
  • 标题中文:迈向可信的 AI 开发:支持可验证声明的机制
  • TLDR中文:本报告建议不同利益相关方可采取多种措施,提升关于 AI 系统及其相关开发流程声明的可验证性,重点是为 AI 系统的安全性、安保、公平性与隐私保护提供证据。
  • 来源文件:
  • [OpenAlex discover]
  • [S2 enrich]