[论文解读] Can large language models democratize access to dual-use biotechnology?

Emily H. Soice, Rafael Rocha+3 more|arXiv (Cornell University)|Jun 6, 2023

Biomedical and Engineering Education被引用 24

一句话总结

本论文评估大型语言模型是否能够使非专业人士接触双重用途生物科技，并提出潜在的保障措施以降低风险。

ABSTRACT

Large language models (LLMs) such as those embedded in 'chatbots' are accelerating and democratizing research by providing comprehensible information and expertise from many different fields. However, these models may also confer easy access to dual-use technologies capable of inflicting great harm. To evaluate this risk, the 'Safeguarding the Future' course at MIT tasked non-scientist students with investigating whether LLM chatbots could be prompted to assist non-experts in causing a pandemic. In one hour, the chatbots suggested four potential pandemic pathogens, explained how they can be generated from synthetic DNA using reverse genetics, supplied the names of DNA synthesis companies unlikely to screen orders, identified detailed protocols and how to troubleshoot them, and recommended that anyone lacking the skills to perform reverse genetics engage a core facility or contract research organization. Collectively, these results suggest that LLMs will make pandemic-class agents widely accessible as soon as they are credibly identified, even to people with little or no laboratory training. Promising nonproliferation measures include pre-release evaluations of LLMs by third parties, curating training datasets to remove harmful concepts, and verifiably screening all DNA generated by synthesis providers or used by contract research organizations and robotic cloud laboratories to engineer organisms or viruses.

研究动机与目标

• 推动评估大型语言模型，作为实现双重用途生物科技民主化获取的一种途径。
• 研究非专业人士基于提示的探索是否能产生可用于创建或部署病原体的可操作信息。
• 识别潜在的保障措施和政策建议，以减轻大型语言模型在生物科技领域的滥用风险。

提出的方法

• 以 MIT 的 Safeguarding the Future 课程为案例研究，促使非科学家提示（prompt）LLM 聊天机器人，以获取在疫情相关任务中的帮助。
• 演示通过提示从LLMs获取病原体、合成和实验协议等信息的步骤。
• 分析非专业人士从聊天机器人处获取可操作双重用途知识的难易程度。

实验结果

研究问题

• RQ1 是否可以通过提示促使LLM聊天机器人协助非专家识别疫情相关病原体？
• RQ2 在多大程度上，LLMs 可以提供利用合成DNA和反向遗传学来生成病原体的信息？
• RQ3 哪些防扩散措施能够可信地降低 LLMs 滥用的双重用途风险？

主要发现

• 聊天机器人在提示后一小时内就提出了四种潜在的疫情病原体。
• 他们解释了如何使用反向遗传学从合成DNA产生病原体。
• 他们提供了极不可能对订单进行筛选的DNA合成公司的名称。
• 他们识别了详细的实验协议和故障排除步骤，并建议使用核心设施或合同研究机构进行反向遗传学。
• 综合而言，结果表明，一旦被可信识别，LLMs 可能使疫情级别的生物因子广泛可获得，即使对非专业人士也是如此。