# The Reality of AI and Biorisk

arXiv: https://arxiv.org/abs/2412.01946 · HTML: https://mlsanity.com/paper/2412.01946/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 76 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Builds on (most cited first, 7 of 7)

- [Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning](https://mlsanity.com/paper/2402.06619/) (2024)
- [On the Societal Impact of Open Foundation Models](https://mlsanity.com/paper/2403.07918/) (2024)
- [Open Problems in Technical AI Governance](https://mlsanity.com/paper/2407.14981/) (2024)
- [Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?](https://mlsanity.com/paper/2411.04118/) (2024)
- [Specialized Foundation Models Struggle to Beat Supervised Baselines](https://mlsanity.com/paper/2411.02796/) (2024)
- [On the Limitations of Compute Thresholds as a Governance Strategy](https://mlsanity.com/paper/2407.05694/) (2024)
- [Towards Responsible Governance of Biological Design Tools](https://mlsanity.com/paper/2311.15936/) (2023)

## Built on by (most cited first, 8 of 8)

- [AI Safety Should Prioritize the Future of Work](https://mlsanity.com/paper/2504.13959/) (2025)
- [Distinguishing Task-Specific and General-Purpose AI in Regulation](https://mlsanity.com/paper/2506.17347/) (2025)
- [GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models](https://mlsanity.com/paper/2505.10983/) (2025)
- [Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks](https://mlsanity.com/paper/2508.06411/) (2025)
- [Measuring Biological Capabilities and Risks of AI Agents](https://mlsanity.com/paper/2606.19899/) (2026)
- [The Case for ESM3 as a General-Purpose AI Model with Systemic Risk Under the EU AI Act](https://mlsanity.com/paper/2605.01611/) (2026)
- [Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety](https://mlsanity.com/paper/2607.05407/) (2026)
- [The Safeguard Worked. Is the LLM System Safer?](https://mlsanity.com/paper/2609.00519/) (2026)

## Abstract (arXiv)

To accurately and confidently answer the question 'could an AI model or system increase biorisk', it is necessary to have both a sound theoretical threat model for how AI models or systems could increase biorisk and a robust method for testing that threat model. This paper provides an analysis of existing available research surrounding two AI and biorisk threat models: 1) access to information and planning via large language models (LLMs), and 2) the use of AI-enabled biological tools (BTs) in synthesizing novel biological artifacts. We find that existing studies around AI-related biorisk are nascent, often speculative in nature, or limited in terms of their methodological maturity and transparency. The available literature suggests that current LLMs and BTs do not pose an immediate risk, and more work is needed to develop rigorous approaches to understanding how future models could increase biorisks. We end with recommendations about how empirical work can be expanded to more precisely target biorisk and ensure rigor and validity of findings.