The Operational Risks of AI in Large-Scale Biological Attacks: Results of a Red-Team Study

2024/01/01 by Christopher Mouton, Caleb Lucas, Ella Guest · 1 voice
Biochemistry, Genetics and Molecular Biology · #Bacillus and Francisella bacterial research

paper · pdf · doi:10.7249/rra2977-2

openalex publication_date 2024/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/06/11

Abstract

The authors of this report share final results of a study of potential risks of artificial intelligence (AI) in the context of biological weapon attacks. The authors sought to identify potential risks posed by AI misuse, generate policy insights to mitigate any risks, and contribute to responsible AI development. The findings indicate that using the existing generation of large language models did not measurably change the risk of such an attack.

Citations

• The WHO estimates of excess mortality associated with the COVID-19 pandemic

Discussions

• RAND Corporation report: The Operational Risks of AI in Large-Scale Biological Attacks: Results of a Red-Team Study doi.org/10.7249/RRA2... [bsky, 5 points, 0 comments]

Related

• Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools
• Contemporary AI foundation models increase biological weapons risk
• International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications
• Towards Risk Analysis of the Impact of AI on the Deliberate Biological Threat Landscape
• The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation