摘要：人工智能正在横跨日益紧密的“从数字到物理”工作流，全面重塑生物学研究。通用大语言模型能够检索与整合前沿科研信息，支持实验规划和计算分析；生物基础模型（biological foundation models）能够预测、优化并生成蛋白质、基因及基因组尺度的序列；Agent 智能体系统能够自主协调多步骤科研任务；自动化实验室则已部分闭环了“设计-构建-测试-学习”（design-build-test-learn）全流程。这些技术有望极大造福医药、公共卫生和生物技术产业。然而，它们带来的生物安全风险不仅取决于 AI 本身具备何种能力，还取决于使用者本身、其实验技能与意图、其获取实验室器材与生物原材料的权限，以及现有的安全防护屏障。现有实证表明，AI 带来的能力跃升（uplift）客观存在，但目前主要局限于数字化任务而非物理操作任务。前沿系统在计算机模拟（in-silico）和筛查规避基准测试上已超越专家基线，而在受控的湿实验研究中，操作人员的隐性知识（tacit knowledge）和实际物理操作依然是难以跨越的实质性壁垒。本综述详述了利用 AI 工具可能引发的不同生物威胁路径，覆盖从信息搜集、生物设计，到原料采购、合成、测试、规模化放大乃至潜在释放的完整链路。我们进一步深入剖析了为何通用大模型的对齐（alignment）技术难以有效迁移至生物大模型，并探讨了模型可解释性在审计危险能力是否被真正剔除中的前沿应用。我们呼吁建立“纵深防御”（defense-in-depth）治理体系，在整个生物 AI 生态系统中将能力阈值与对等的安全责任相绑定，在防范高危后果风险的同时，全力护航 AI 的有益应用。

Abstract:Artificial intelligence is reshaping biological research across an increasingly connected digital-to-physical workflow. General-purpose large language models can retrieve and integrate scientific information, support experimental planning, and computational analysis; biological foundation models can predict, optimize, and generate proteins, genes, and genome-scale sequences; agentic systems can coordinate multistep research tasks; automated laboratories can partially close the design-build-test-learn cycle. These technologies could greatly benefit medicine, public health, and biotechnology. However, their biosecurity risk depends not only on what the AI can do, but also on who uses it, their expertise and intent, their access to laboratory tools and materials, and the safeguards in place. Current evidence shows that AI uplift exists but primarily affects digital rather than physical tasks. Frontier systems have exceeded expert baselines on in-silico, and screening-evasion benchmarks, whereas controlled wet-laboratory studies find that tacit knowledge and physical execution remain substantial barriers. This review describes the different biological threats from AI tool use, from information gathering and biological design to procurement, synthesis, testing, scale-up, and potential release. We further examine why alignment techniques for general-purpose models transfer poorly to biological ones, and the emerging role of interpretability in auditing whether hazardous capabilities are genuinely removed. We argue for defense-in-depth governance that links capability thresholds to proportionate responsibilities across the biological AI ecosystem, reducing high-consequence risk while preserving beneficial use.