发表机构
Institute for Artificial Intelligence, Peking University; The Hong Kong University of Science and Technology (Guangzhou)（北京大学人工智能研究院; 香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对大语言模型生物安全评估盲区，构建SPIKE-Bench评估框架，发现多数模型易生成毒素序列，提出BioSafe-Guard分类器降低功能风险并开源相关资源。
AI 中文摘要
大语言模型（LLMs）正在推动生物学研究加速发展，但这一能力同时带来了关键的生物安全威胁：协助蛋白质工程的模型同样可能被提示生成预测的毒素样序列，从而降低生物误用的门槛。然而，当前的安全评估仅针对自然语言，无法判断模型生成的氨基酸序列是生物学胡话还是计算风险信号。为解决这一评估盲区，我们推出SPIKE-Bench，将7个功能类别下的631个精心整理的毒素设计提示，与SPIKE漏斗（一个通过合规性、生物学合理性和预测毒性三个阶段过滤输出的协议）相结合，生成阶段级诊断结果和聚合的功能感知指标：功能危害率（FHR）。对32个LLMs的审计显示，大多数模型会自由遵从毒素设计请求；FHR主要由生物生成能力而非安全对齐驱动，达到50.7%；弃权（不执行）率无法预测功能风险。作为缓解的第一步，我们提供BioSafe-Guard，一个领域专用分类器，在保留良性效用的同时大幅降低预测功能风险。我们在该httpsURL发布SPIKE-Bench和BioSafe-Guard，以支持对LLMs更严格的生物安全评估。
英文摘要
Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat: models that assist in protein engineering can equally be prompted to generate predicted toxin-like sequences, potentially lowering the barrier to biological misuse. Current safety evaluations, however, operate in natural language and cannot determine whether a model-generated amino acid sequence is biological gibberish or a computational risk signal. To address this evaluation blind spot, we introduce SPIKE-Bench, coupling 631 curated toxin-design prompts across seven functional categories with the SPIKE funnel, a three-stage protocol that filters output through compliance, biological plausibility, and predicted toxicity, producing stage-level diagnostics and an aggregate function-aware metric: the Functional Harmfulness Rate (FHR). An audit of 32 LLMs reveals that most models freely comply with toxin-design requests; FHR is driven primarily by biological generation capability rather than safety alignment, reaching 50.7%; and Refusal Rate fails to predict functional risk. As a first step toward mitigation, we provide BioSafe-Guard, a domain-specialized classifier that substantially reduces predicted functional risk while preserving benign utility. We release SPIKE-Bench and BioSafe-Guard at https://github.com/PKU-Alignment/SPIKE-Bench to support more rigorous biosecurity evaluation of LLMs.
CommentsAccepted to COLM 2026. 40 pages, 9 figures
