The Brent Group
AboutThe problem
Research
People

Publications

Publications

Refereed and institutional publications

  1. Brent, R., McKelvey, T. G., Jr., and Matheny, J. (2024). The New Bioweapons: How Synthetic Biology Could Destabilize the World. Foreign Affairs, vol. 103, no. 5.
  2. Barkan, C. O., Rodriguez, C., Chowdhury, S., Zhang, L.-A., and Brent, R. (2026). Restricting AI Agent Use of Biological Tools: Exploring the Feasibility of Software Barriers. RAND Corporation, RR-A5000-1.
  3. Williams, A. E., Del Castello, B., Lee, J., Roberts, D., Tarangelo, J. P., Atanda, J., Colman-Lerner, A., Gerold, J., and Brent, R. (2026). Developing a risk-scoring tool for artificial intelligence-enabled biological design. RAND Corporation, RR-A4490-1.
  4. Brent, R., and McKelvey, T. G., Jr. (2025). Contemporary Foundation AI Models Increase Biological Weapons Risk. RAND Corporation, Expert Insights PE-A3853-1. Preprint at arXiv:2506.13798.
  5. Brent, R. (2005). In the valley of the shadow of death. Draft prepared for a National Academy of Sciences committee. MIT Synthetic Biology archive, DSpace.

Preprints

  1. Brent, R., and Colman-Lerner, A. (2026). A break-glass plan for biological security: bibliometric analysis of methods for building virus-length recombinant DNA constructions identifies advanced DNA polymerases as key reagents and suggests additional controls that might be imposed in response to triggering biological incidents. Preprints.org.
  2. Air, A., Reworr, Kotov, N., Volkov, D., Steidley, J., and Ladish, J. (2026). Language Models Can Autonomously Hack and Self-Replicate. arXiv:2605.06760.
  3. Reworr and Volkov, D. (2024). LLM Agent Honeypot: Monitoring AI Hacking Agents. arXiv:2410.13919.
  4. Volkov, D. (2024). Badllama 3: removing safety finetuning from Llama 3 in minutes. arXiv:2407.01376.
  5. Krupkina, E., and Volkov, D. (2024). BadGPT-4o: stripping safety finetuning from GPT models. arXiv:2412.05346.

Reports and commentary

  1. Palisade Research (2024). End-to-end autonomous AI hacking.
  2. Volkov, D., et al. (2025). Biollama. Palisade Research.
  3. Williams, A. E., et al. — explainer and future work. Posts on LinkedIn.