新加坡共识提出AI安全三大研究方向，助力构建可信AI生态。
The Singapore Consensus on Global AI Safety Research Priorities
- 采用纵深防御模型，将AI安全分为开发、评估、控制三类挑战。
- 33国支持，整合全球科研力量聚焦可信AI系统建设。
- 适合政策制定者与AI安全研究人员参考，推动负责任创新。
快速提升的AI能力与自主性虽带来巨大变革潜力，但也引发关于如何确保AI安全（即可信、可靠、安全）的激烈讨论。构建可信生态系统至关重要——它能增强公众对AI的信心，为创新提供最大空间，同时避免负面反弹。2025年新加坡人工智能会议（SCAI）国际科学交流会旨在推动该领域研究，汇聚全球科学家，识别并整合AI安全研究优先事项。本报告基于由约书亚·本吉奥主持、33个国家支持的《国际AI安全报告》，采用纵深防御模型，将AI安全研究领域划分为三类：创建可信AI系统的挑战（开发）、评估其风险的挑战（评估），以及部署后监控与干预的挑战（控制）。
原文摘要 · Abstract (English)
Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy, reliable, and secure. Building a trusted ecosystem is therefore essential -- it helps people embrace AI with confidence and gives maximal space for innovation while avoiding backlash. The "2025 Singapore Conference on AI (SCAI): International Scientific Exchange on AI Safety" aimed to support research in this space by bringing together AI scientists across geographies to identify and synthesise research priorities in AI safety. This resulting report builds on the International AI Safety Report chaired by Yoshua Bengio and backed by 33 governments. By adopting a defence-in-depth model, this report organises AI safety research domains into three types: challenges with creating trustworthy AI systems (Development), challenges with evaluating their risks (Assessment), and challenges with monitoring and intervening after deployment (Control).
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。