Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915594501095424 |
|---|---|
| author | Zhang, Zaixi Chakraborty, Souradip Bedi, Amrit Singh Mathew, Emilin Saravanan, Varsha Cong, Le Velasquez, Alvaro Lin-Gibson, Sheng Blewett, Megan Hendrycs, Dan London, Alex John Zhong, Ellen Raphael, Ben Dieng, Adji Bousso Ma, Jian Xing, Eric Altman, Russ Church, George Wang, Mengdi |
| author_facet | Zhang, Zaixi Chakraborty, Souradip Bedi, Amrit Singh Mathew, Emilin Saravanan, Varsha Cong, Le Velasquez, Alvaro Lin-Gibson, Sheng Blewett, Megan Hendrycs, Dan London, Alex John Zhong, Ellen Raphael, Ben Dieng, Adji Bousso Ma, Jian Xing, Eric Altman, Russ Church, George Wang, Mengdi |
| contents | The rapid adoption of generative artificial intelligence (GenAI) in the biosciences is transforming biotechnology, medicine, and synthetic biology. Yet this advancement is intrinsically linked to new vulnerabilities, as GenAI lowers the barrier to misuse and introduces novel biosecurity threats, such as generating synthetic viral proteins or toxins. These dual-use risks are often overlooked, as existing safety guardrails remain fragile and can be circumvented through deceptive prompts or jailbreak techniques. In this Perspective, we first outline the current state of GenAI in the biosciences and emerging threat vectors ranging from jailbreak attacks and privacy risks to the dual-use challenges posed by autonomous AI agents. We then examine urgent gaps in regulation and oversight, drawing on insights from 130 expert interviews across academia, government, industry, and policy. A large majority ($\approx 76$\%) expressed concern over AI misuse in biology, and 74\% called for the development of new governance frameworks. Finally, we explore technical pathways to mitigation, advocating a multi-layered approach to GenAI safety. These defenses include rigorous data filtering, alignment with ethical principles during development, and real-time monitoring to block harmful requests. Together, these strategies provide a blueprint for embedding security throughout the GenAI lifecycle. As GenAI becomes integrated into the biosciences, safeguarding this frontier requires an immediate commitment to both adaptive governance and secure-by-design technologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15975 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity Zhang, Zaixi Chakraborty, Souradip Bedi, Amrit Singh Mathew, Emilin Saravanan, Varsha Cong, Le Velasquez, Alvaro Lin-Gibson, Sheng Blewett, Megan Hendrycs, Dan London, Alex John Zhong, Ellen Raphael, Ben Dieng, Adji Bousso Ma, Jian Xing, Eric Altman, Russ Church, George Wang, Mengdi Cryptography and Security Biomolecules The rapid adoption of generative artificial intelligence (GenAI) in the biosciences is transforming biotechnology, medicine, and synthetic biology. Yet this advancement is intrinsically linked to new vulnerabilities, as GenAI lowers the barrier to misuse and introduces novel biosecurity threats, such as generating synthetic viral proteins or toxins. These dual-use risks are often overlooked, as existing safety guardrails remain fragile and can be circumvented through deceptive prompts or jailbreak techniques. In this Perspective, we first outline the current state of GenAI in the biosciences and emerging threat vectors ranging from jailbreak attacks and privacy risks to the dual-use challenges posed by autonomous AI agents. We then examine urgent gaps in regulation and oversight, drawing on insights from 130 expert interviews across academia, government, industry, and policy. A large majority ($\approx 76$\%) expressed concern over AI misuse in biology, and 74\% called for the development of new governance frameworks. Finally, we explore technical pathways to mitigation, advocating a multi-layered approach to GenAI safety. These defenses include rigorous data filtering, alignment with ethical principles during development, and real-time monitoring to block harmful requests. Together, these strategies provide a blueprint for embedding security throughout the GenAI lifecycle. As GenAI becomes integrated into the biosciences, safeguarding this frontier requires an immediate commitment to both adaptive governance and secure-by-design technologies. |
| title | Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity |
| topic | Cryptography and Security Biomolecules |
| url | https://arxiv.org/abs/2510.15975 |