Skip to content

Instantly share code, notes, and snippets.

@stephenturner

stephenturner/ai-biosecurity-papers.md Secret

Created February 2, 2026 09:45
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save stephenturner/ff2aa3dc1ad148dc4c6ce6b2220cf1eb to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save stephenturner/ff2aa3dc1ad148dc4c6ce6b2220cf1eb to your computer and use it in GitHub Desktop.
Download ZIP
A few AIxBio / biosecurity papers
Raw
ai-biosecurity-papers.md

See also: Tacit Knowledge and Biosecurity at https://blog.stephenturner.us/p/tacit-knowledge-biosecurity-rand.

  1. Sarah R. Carter & Greg Butchello. A Framework for Managed Access to Biological AI Tools. https://www.nti.org/analysis/articles/a-framework-for-managed-access-to-biological-ai-tools/ (2026).
  2. Brent, R. & McKelvey, G. Contemporary Foundation AI Models Increase Biological Weapons Risk. https://www.rand.org/pubs/perspectives/PEA3853-1.html (2025).
  3. Dettman, J., Lathrop, E., Attal‐Juncqua, A., Nicotra, M. & Berke, A. Prioritizing Feasible and Impactful Actions to Enable Secure AI Development and Use in Biology. Biotech & Bioengineering bit.70132 (2026) doi:10.1002/bit.70132.
  4. Zhou, Y. et al. Benchmarking large language models on safety risks in scientific laboratories. Nat Mach Intell https://doi.org/10.1038/s42256-025-01152-1 (2026) doi:10.1038/s42256-025-01152-1.
  5. Mui, A. K. et al. Increasing Gene Synthesis Security Risk Awareness Through Global Engagement and Collaborative Exercise Development. Health Security 23, 449–455 (2025).
  6. Kolt, N. et al. Legal Alignment for Safe and Ethical AI. Preprint at https://doi.org/10.48550/arXiv.2601.04175 (2026).
  7. AI Security Institute. Frontier AI Trends Report. https://aisi.s3.eu-west-2.amazonaws.com/Frontier+AI+Trends+Report+-+AI+Security+Institute.pdf (2026).
  8. Gladue, D. P., O’Mahony, A., Gladue, D. P. & O’Mahony, A. CRISPR Treatments for AI-Designed Synthetic Viruses: Rapid Programmable Countermeasures for Emerging and Engineered Viruses. Viruses 17, (2025).
  9. Eskandar, K. Artificial intelligence and synthetic biology: biosecurity risks, dual-use concerns, and governance pathways. AI Ethics 6, 66 (2025).
  10. Beal, J. & Alexanian, T. Creating Enforceable Biosecurity Standards for Nucleic Acid Providers. Engineering Biology 9, e70003 (2025).
  11. Romero-Severson, E. O., Harvey, T., Generous, N. & Mach, P. M. Measuring skill-based uplift from AI in a real biological laboratory. Preprint at https://doi.org/10.48550/arXiv.2512.10960 (2025).
  12. Eskandar, K. Artificial intelligence and synthetic biology: biosecurity risks, dual-use concerns, and governance pathways. AI Ethics 6, 66 (2026).
  13. Okon, M. B. et al. From pandemics to preparedness: harnessing AI, CRISPR, and synthetic biology to counter biosecurity threats. Front Public Health 13, 1711344 (2025).
  14. Batalis, S. & Venkatram, V. Use all the tools of the trade: Building a foundation for the next era of biosecurity. Bulletin of the Atomic Scientists 81, 457–461 (2025).
  15. OpenAI. OpenAI O1 System Card. https://openai.com/index/openai-o1-system-card/ (2024).
  16. Taylor, J. et al. Auditing Games for Sandbagging. Preprint at https://doi.org/10.48550/arXiv.2512.07810 (2025).
  17. Committee on Assessing and Navigating Biosecurity Concerns and Benefits of Artificial Intelligence Use in the Life Sciences et al. The Age of AI in the Life Sciences: Benefits and Biosecurity Considerations. 28868 (National Academies Press, Washington, D.C., 2025). doi:10.17226/28868.
  18. Banerjee, A., Tam, E., Dang, C. & Martinez, D. SafeGenie: Erasing Dangerous Concepts from Biological Diffusion Models. in (2025).
  19. Braun, J. et al. Resisting RL Elicitation of Biosecurity Capabilities: Reasoning Models Exploration Hacking on WMDP. in (2025).
  20. O’Brien, K. et al. Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs. in (2025).
  21. Zhang, Z., Zhou, Z., Jin, R., Cong, L. & Wang, M. GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance. in (2025).
  22. Liu, A. B. et al. ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity. in (2025).
  23. Wang, D. et al. Without Safeguards, AI-Biology Integration Risks Creating Future Pandemics. in (2025).
  24. OpenAI. Preparedness Framework. https://cdn.openai.com/pdf/18a02b5d-6b67-4cec-ab64-68cdfbddebcd/preparedness-framework-v2.pdf (2025).
  25. Endy, D. Biosecurity Really: A Strategy for Victory.
  26. Liu, Z., Dou, G., Tan, Z., Tian, Y. & Jiang, M. Towards Safer Large Language Models through Machine Unlearning. Preprint at https://doi.org/10.48550/arXiv.2402.10058 (2024).
  27. Nguyen, T. T. et al. A Survey of Machine Unlearning. ACM Trans. Intell. Syst. Technol. 16, 108:1-108:46 (2025).
  28. Anthropic. Activating AI Safety Level 3 protections. https://www.anthropic.com/news/activating-asl3-protections (2025).
  29. Tedeschi, S. et al. ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming. Preprint at https://doi.org/10.48550/arXiv.2404.08676 (2024).
  30. Mazeika, M. et al. HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal. Preprint at https://doi.org/10.48550/arXiv.2402.04249 (2024).
  31. Wang, Y. et al. MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark. Preprint at https://doi.org/10.48550/arXiv.2406.01574 (2024).
  32. Hendrycks, D. et al. Measuring Massive Multitask Language Understanding. Preprint at https://doi.org/10.48550/arXiv.2009.03300 (2021).
  33. Rein, D. et al. GPQA: A Graduate-Level Google-Proof Q&A Benchmark. Preprint at https://doi.org/10.48550/arXiv.2311.12022 (2023).
  34. Li, N. et al. The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning. Preprint at https://doi.org/10.48550/arXiv.2403.03218 (2024).
  35. Laurent, J. M. et al. LAB-Bench: Measuring Capabilities of Language Models for Biology Research. Preprint at https://doi.org/10.48550/arXiv.2407.10362 (2024).
  36. Ivanov, I. BioLP-bench: Measuring understanding of biological lab protocols by large language models. 2024.08.21.608694 Preprint at https://doi.org/10.1101/2024.08.21.608694 (2024).
  37. Rivera, S. & Mackelprang, R. Risk Mitigation for Biological Design Tools. https://ebrc.org/publications-risk-mitigation-for-biological-design-tools (2025) doi:10.25498/E4R10S.
  38. Tarangelo, J., Attal-Juncqua, A., Somani, E., Roberts, D. & Webster, K. Protecting Biological Materials and Services from Misuse: Opportunities for Access Monitoring and Control. https://www.rand.org/pubs/research_reports/RRA4067-1.html (2025).
  39. Ho, A. Do the biorisk evaluations of AI labs actually measure the risk of developing bioweapons? Epoch AI https://epoch.ai/gradient-updates/do-the-biorisk-evaluations-of-ai-labs-actually-measure-the-risk-of-developing-bioweapons (2025).
  40. Willis, H., Nicotra, M., Sperisen, B., Somani, E. & Willis, H. Living Framework and Guidelines for Information Disclosure in Biosecurity. Preprint at https://doi.org/10.20944/preprints202510.1427.v1 (2025).
  41. Zhang, Z. et al. Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity. Preprint at https://doi.org/10.48550/arXiv.2510.15975 (2025).
  42. Peppin, A. et al. The Reality of AI and Biorisk. Preprint at https://doi.org/10.48550/arXiv.2412.01946 (2025).
  43. Hattoh, G., Ayensu, J., Ofori, N. P., Eshun, S. & Akogo, D. Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio. Preprint at https://doi.org/10.48550/arXiv.2505.17154 (2025).
  44. Wheeler, N. E. Responsible AI in biotechnology: balancing discovery, innovation and biosecurity risks. Front Bioeng Biotechnol 13, 1537471 (2025).
  45. Forum, F. M. Issue Brief: Preliminary Taxonomy of AI-Bio Safety Evaluations. Frontier Model Forum https://www.frontiermodelforum.org/updates/issue-brief-preliminary-taxonomy-of-ai-bio-safety-evaluations/ (2024).
  46. Dev, S. et al. Toward Comprehensive Benchmarking of the Biological Knowledge of Frontier Large Language Models. https://www.rand.org/pubs/working_papers/WRA3797-1.html (2025).
  47. Lu, A. B. & Lewis, A. C. F. Governance strategies for biological AI: beyond the dual-use dilemma. Trends in Biotechnology S016777992500397X (2025) doi:10.1016/j.tibtech.2025.09.012.
  48. Titus, A. Shock Doctrine in the Life Sciences - When Fear Overwhelms Facts. SSRN Scholarly Paper at https://doi.org/10.2139/ssrn.5428795 (2025).
  49. Manheim, D., Williams, A., Aveggio, C. & Berke, A. Understanding the Theoretical Limits of AI-Enabled Pathogen Design: Insights from a Delphi Study. https://www.rand.org/pubs/research_reports/RRA4087-1.html (2025).
  50. Patel, A. J. et al. Physical Approaches to Civilian Biodefense: Identifying Potential Preparedness Measures for Challenging Biological Threats. https://www.rand.org/pubs/research_reports/RRA4036-1.html (2025).
  51. Dettman, J., Lathrop, E., Attal-Juncqua, A., Nicotra, M. & Berke, A. Prioritizing Feasible and Impactful Actions to Enable Secure Artificial Intelligence Development and Use in Biology. https://www.rand.org/pubs/working_papers/WRA4213-1.html (2025).
  52. Wittmann, B. J. et al. Strengthening nucleic acid biosecurity screening against generative protein design tools. Science 390, 82–87 (2025).
  53. Moulange, R. Defensive acceleration needs execution, not just good intentions. Securing the Interface https://richardmoulange.substack.com/p/defensive-acceleration-needs-execution (2025).
  54. Aveggio, C., Patel, A. J., Nevo, S. & Webster, K. Exploring the Offense-Defense Balance of Biology: Identifying and Describing High-Level Asymmetries. https://www.rand.org/pubs/perspectives/PEA4102-1.html (2025).
  55. Anthropic. Claude Sonnet 4.5 System Card. (2025).
  56. Attal-Juncqua, A. et al. Biosecurity Governance Across Uncertain Artificial Intelligence Futures: Perspectives from a Side Event on Biosecurity and Frontier AI at the 2025 AI Action Summit. https://www.rand.org/pubs/conf_proceedings/CFA4186-1.html (2025).
  57. Webster, T. et al. Global Risk Index for AI-Enabled Biological Tools. https://www.rand.org/pubs/external_publications/EP71093.html (2025) doi:10.71172/wjyw-6dyc.
  58. Pannu, J. et al. Dual-use capabilities of concern of biological AI models. PLOS Computational Biology 21, e1012975 (2025).
  59. Zhu, T. Mirror of the unknown: should research on mirror-image molecular biology be stopped? Nature 645, 588–591 (2025).
  60. Del Castello, B. & Willis, H. H. Assessing the Impacts of Technology Maturity and Diffusion on Malicious Biological Agent Development Capabilities: Demonstrating a Transparent, Repeatable Assessment Method. https://www.rand.org/pubs/research_reports/RRA3662-1.html (2025).
  61. Biodefense in the Age of Synthetic Biology. (National Academies Press, Washington, D.C., 2018). doi:10.17226/24890.
  62. Feldman, J. & Feldman, T. Resilient Biosecurity in the Era of AI-Enabled Bioweapons. Preprint at https://doi.org/10.48550/arXiv.2509.02610 (2025).
  63. Pannu, J. et al. Defining Hazardous Capabilities of Biological AI Models: Expert Convening to Inform Future Risk Assessment. https://www.rand.org/pubs/conf_proceedings/CFA3649-1.html (2025).
  64. Titus, A. Violet Teaming AI in the Life Sciences A Preprint. (2023). doi:10.5281/zenodo.8180396.
  65. Coltoff, E. C. & Davis, A. L. Emerging biotechnologies: Dual-use potential and strategies to prevent misuse. MIT Science Policy Review 6, (2025).
  66. National Security Commission on Emerging Biotechnology. Charting the Future of Biotechnology: An action plan for American security and prosperity. (2025).
  67. Drexel, B. & Withers, C. AI and the Evolution of Biological National Security Risks. https://www.cnas.org/publications/reports/ai-and-the-evolution-of-biological-national-security-risks (2025).
  68. Godbold, G. D. et al. The Case for Limiting “Sequences of Concern” to Those with Demonstrated Pathogenic Function. Applied Biosafety apb.2025.0015 (2025) doi:10.1089/apb.2025.0015.
  69. National Academies of Sciences, Engineering, and Medicine. The Age of AI in the Life Sciences: Benefits and Biosecurity Considerations. (2025).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment