BioVeil MATRIX: Uncovering and categorizing vulnerabilities of agentic biological AI scientists
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914525892050944 |
|---|---|
| author | Provatas, Kimon Antonios Self, Avery Mouratidis, Ioannis Georgakopoulos-Soares, Ilias |
| author_facet | Provatas, Kimon Antonios Self, Avery Mouratidis, Ioannis Georgakopoulos-Soares, Ilias |
| contents | Agentic AI scientists equipped with domain-specific tools are rapidly entering scientific workflows across disciplines, with especially strong uptake in the life sciences where they can be used for literature synthesis, sequence analysis, and experimental planning support. While these systems accelerate biological research, they also introduce risks for dual-use applications that are not captured by current model-centric safety evaluations. We present evidence that current agentic AI scientists, including Biomni and K-Dense, are willing to assist with dual-use tasks that are blocked by base model safeguards. We also found that in a paired evaluation framework for biology and chemistry prompts involving Weapons of Mass Destruction proxies (WMDP), agentic scaffolding of Biomni increased the benchmark performance relative to the underlying standalone model, producing measurable capability uplift. We believe it is necessary to include additional safeguards in existing models and build future tools from the ground up with agentic vulnerabilities in mind. To systematically categorize broader risks, we introduce BioVeil MATRIX, a defensive taxonomy that maps AI-enabled biosecurity risks using 10 tactical categories (TA01--TA10) and 22 different techniques. We propose to use this taxonomy as a baseline for future AI scientist development and generate specialized benchmarks and protocols for red-teaming these vulnerabilities before public deployment. BioVeil MATRIX can be found at: https://bioveilmatrix.com/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00927 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BioVeil MATRIX: Uncovering and categorizing vulnerabilities of agentic biological AI scientists Provatas, Kimon Antonios Self, Avery Mouratidis, Ioannis Georgakopoulos-Soares, Ilias Other Quantitative Biology Agentic AI scientists equipped with domain-specific tools are rapidly entering scientific workflows across disciplines, with especially strong uptake in the life sciences where they can be used for literature synthesis, sequence analysis, and experimental planning support. While these systems accelerate biological research, they also introduce risks for dual-use applications that are not captured by current model-centric safety evaluations. We present evidence that current agentic AI scientists, including Biomni and K-Dense, are willing to assist with dual-use tasks that are blocked by base model safeguards. We also found that in a paired evaluation framework for biology and chemistry prompts involving Weapons of Mass Destruction proxies (WMDP), agentic scaffolding of Biomni increased the benchmark performance relative to the underlying standalone model, producing measurable capability uplift. We believe it is necessary to include additional safeguards in existing models and build future tools from the ground up with agentic vulnerabilities in mind. To systematically categorize broader risks, we introduce BioVeil MATRIX, a defensive taxonomy that maps AI-enabled biosecurity risks using 10 tactical categories (TA01--TA10) and 22 different techniques. We propose to use this taxonomy as a baseline for future AI scientist development and generate specialized benchmarks and protocols for red-teaming these vulnerabilities before public deployment. BioVeil MATRIX can be found at: https://bioveilmatrix.com/ |
| title | BioVeil MATRIX: Uncovering and categorizing vulnerabilities of agentic biological AI scientists |
| topic | Other Quantitative Biology |
| url | https://arxiv.org/abs/2605.00927 |