# Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools

arXiv: https://arxiv.org/abs/2306.13952 · HTML: https://mlsanity.com/paper/2306.13952/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2023.

## Built on by (most cited first, 30 of 45)

- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [Large Language Model Unlearning via Embedding-Corrupted Prompts](https://mlsanity.com/paper/2406.07933/) (2024)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [Language Models Resist Alignment: Evidence From Data Compression](https://mlsanity.com/paper/2406.06144/) (2024)
- [Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective](https://mlsanity.com/paper/2407.16997/) (2024)
- [Probing the limitations of multimodal language models for chemistry and materials research](https://mlsanity.com/paper/2411.16955/) (2024)
- [Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives](https://mlsanity.com/paper/2311.09227/) (2023)
- [Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark](https://mlsanity.com/paper/2504.16137/) (2025)
- [Mapping the Ethics of Generative AI: A Comprehensive Scoping Review](https://mlsanity.com/paper/2402.08323/) (2024)
- [SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks](https://mlsanity.com/paper/2410.03769/) (2024)
- [Controlling risks of AI in chemical science with agents](https://mlsanity.com/paper/2312.06632/) (2023)
- [UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs](https://mlsanity.com/paper/2410.17050/) (2024)
- [Training Compute Thresholds: Features and Functions in AI Regulation](https://mlsanity.com/paper/2405.10799/) (2024)
- [Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework](https://mlsanity.com/paper/2311.14711/) (2023)
- [Distillation Robustifies Unlearning](https://mlsanity.com/paper/2506.06278/) (2025)
- [Prioritizing High-Consequence Biological Capabilities in Evaluations of Artificial Intelligence Models](https://mlsanity.com/paper/2407.13059/) (2024)
- [The Necessity of AI Audit Standards Boards](https://mlsanity.com/paper/2404.13060/) (2024)
- [Improving LLM Unlearning Robustness via Random Perturbations](https://mlsanity.com/paper/2501.19202/) (2025)
- [Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility](https://mlsanity.com/paper/2507.11630/) (2025)
- [Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception](https://mlsanity.com/paper/2510.23853/) (2025)
- [DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning](https://mlsanity.com/paper/2511.05784/) (2025)
- [Measuring Mid-2025 LLM-Assistance on Novice Performance in Biology](https://mlsanity.com/paper/2602.16703/) (2026)
- [Towards Responsible Governance of Biological Design Tools](https://mlsanity.com/paper/2311.15936/) (2023)
- [LLM Unlearning Without an Expert Curated Dataset](https://mlsanity.com/paper/2508.06595/) (2025)
- [Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation](https://mlsanity.com/paper/2503.04299/) (2025)
- [Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling](https://mlsanity.com/paper/2503.10093/) (2025)
- [CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models](https://mlsanity.com/paper/2406.04752/) (2024)

## Abstract (arXiv)

As advancements in artificial intelligence (AI) propel progress in the life sciences, they may also enable the weaponisation and misuse of biological agents. This article differentiates two classes of AI tools that could pose such biosecurity risks: large language models (LLMs) and biological design tools (BDTs). LLMs, such as GPT-4 and its successors, might provide dual-use information and thus remove some barriers encountered by historical biological weapons efforts. As LLMs are turned into multi-modal lab assistants and autonomous science tools, this will increase their ability to support non-experts in performing laboratory work. Thus, LLMs may in particular lower barriers to biological misuse. In contrast, BDTs will expand the capabilities of sophisticated actors. Concretely, BDTs may enable the creation of pandemic pathogens substantially worse than anything seen to date and could enable forms of more predictable and targeted biological weapons. In combination, the convergence of LLMs and BDTs could raise the ceiling of harm from biological agents and could make them broadly accessible. A range of interventions would help to manage risks. Independent pre-release evaluations could help understand the capabilities of models and the effectiveness of safeguards. Options for differentiated access to such tools should be carefully weighed with the benefits of openly releasing systems. Lastly, essential for mitigating risks will be universal and enhanced screening of gene synthesis products.