BioVeil MATRIX: Uncovering and categorizing vulnerabilities of agentic biological AI scientists

Kimon Antonios Provatas, Avery Self, Ioannis Mouratidis, Ilias Georgakopoulos-Soares

Abstract

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,

Categories

Cite This Resource

@article{llmsec202600191,
  title = {BioVeil MATRIX: Uncovering and categorizing vulnerabilities of agentic biological AI scientists},
  author = {Kimon Antonios Provatas and Avery Self and Ioannis Mouratidis and Ilias Georgakopoulos-Soares},
  year = {2026},
  url = {https://arxiv.org/abs/2605.00927},
}