Logo image
The operational risks of AI in large-scale biological attacks: results of a red-team study
Book

The operational risks of AI in large-scale biological attacks: results of a red-team study

Christopher A Mouton, Caleb Lucas, Ella Guest and RAND Global and Emerging Risks (Program)
Research report (Rand Corporation), RAND Corporation
2024

Abstract

Law and legislation Moral and ethical aspects
"The rapid advancement of artificial intelligence (AI) has far-reaching implications across multiple domains, including concern regarding the potential development of biological weapons. This potential application of AI raises particular concerns because it is accessible to nonstate actors and individuals. The speed at which AI technologies are evolving often surpasses the capacity of government regulatory oversight, leading to a potential gap in existing policies and regulations. In this report, the authors share final results of a study of the potential risks of using large language models (LLMs) in the context of biological weapon attacks. They conducted an expert exercise in which teams of researchers role-playing as malign nonstate actors were assigned to realistic scenarios and tasked with planning a biological attack; some teams had access to an LLM along with the internet, and others were provided only access to the internet. The authors sought to identify potential risks posed by LLM misuse, generate policy insights to mitigate any risks, and contribute to responsible LLM development. The findings indicate that using the existing generation of LLMs did not measurably change the operational risk of such an attack."-- Includes bibliographical references (pages 18-21).

Metrics

1 Record Views

Details

Logo image