Prioritizing High-Consequence Biological Capabilities in Evaluations of Artificial Intelligence Models

TL;DR

The paper discusses how lessons from life sciences dual-use research can inform the evaluation of AI models with biological capabilities, emphasizing the need to prioritize high-consequence biosafety and biosecurity risks before deployment.

Contribution

It proposes leveraging scientific experience in dual-use biological research to improve risk assessments of AI models with biological capabilities, focusing on high-consequence risks.

Findings

AI evaluations should prioritize high-consequence biological risks.

Lessons from life sciences can inform AI biosafety and biosecurity assessments.

Targeted evaluation methods are needed for biological AI capabilities.

Abstract

As a result of rapidly accelerating AI capabilities, over the past year, national governments and multinational bodies have announced efforts to address safety, security and ethics issues related to AI models. One high priority among these efforts is the mitigation of misuse of AI models. Many biologists have for decades sought to reduce the risks of scientific research that could lead, through accident or misuse, to high-consequence disease outbreaks. Scientists have carefully considered what types of life sciences research have the potential for both benefit and risk (dual-use), especially as scientific advances have accelerated our ability to engineer organisms and create novel variants of pathogens. Here we describe how previous experience and study by scientists and policy professionals of dual-use capabilities in the life sciences can inform risk evaluations of AI models with biological capabilities. We argue that AI model evaluations should prioritize addressing high-consequence risks (those that could cause large-scale harm to the public, such as pandemics), and that these risks should be evaluated prior to model deployment so as to allow potential biosafety and/or biosecurity measures. Scientists' experience with identifying and mitigating dual-use biological risks can help inform new approaches to evaluating biological AI models. Identifying which AI capabilities post the greatest biosecurity and biosafety concerns is necessary in order to establish targeted AI safety evaluation methods, secure these tools against accident and misuse, and avoid impeding immense potential benefits.