Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models

TL;DR

This paper introduces BioRiskEval, a framework for assessing the robustness of bio-foundation models against dual-use risks, revealing that current data filtering practices are insufficient to prevent malicious use.

Contribution

The paper presents BioRiskEval, a novel evaluation framework that uncovers limitations of current filtering methods and highlights the need for more robust safety strategies for open-weight bio models.

Findings

Filtering practices may not prevent knowledge recovery via fine-tuning

Dual-use signals are present in pretrained representations

Simple probing can elicit malicious capabilities

Abstract

Open-weight bio-foundation models present a dual-use dilemma. While holding great promise for accelerating scientific research and drug development, they could also enable bad actors to develop more deadly bioweapons. To mitigate the risk posed by these models, current approaches focus on filtering biohazardous data during pre-training. However, the effectiveness of such an approach remains unclear, particularly against determined actors who might fine-tune these models for malicious use. To address this gap, we propose BioRiskEval, a framework to evaluate the robustness of procedures that are intended to reduce the dual-use capabilities of bio-foundation models. BioRiskEval assesses models' virus understanding through three lenses, including sequence modeling, mutational effects prediction, and virulence prediction. Our results show that current filtering practices may not be particularly effective: Excluded knowledge can be rapidly recovered in some cases via fine-tuning, and exhibits broader generalizability in sequence modeling. Furthermore, dual-use signals may already reside in the pretrained representations, and can be elicited via simple linear probing. These findings highlight the challenges of data filtering as a standalone procedure, underscoring the need for further research into robust safety and security strategies for open-weight bio-foundation models.