paperAugust 2026Unreviewed

BioFirewall: A genome-writing-native governance layer for design-stage biosecurity screening of agentic AI

Anees Ahmed Mahaboob Ali, R. Delhibabu, Everette Jacob Remington Nelson

Abstract

Background. Artificial-intelligence design tools now plan genome-scale edits, and agentic systems execute those plans with progressively less human oversight. Biosecurity controls are limited to two points: refusal guardrails at the foundation model and sequence-identity screening at the synthesiser. The design stage between them, where the plan is specified, remains governed by recommendations rather than any deployed system. Results. We present BioFirewall, a rule-governed middleware that inte

Cite

@misc{ali2026biofirewall,
  title = {{BioFirewall: A genome-writing-native governance layer for design-stage biosecurity screening of agentic AI}},
  author = {Anees Ahmed Mahaboob Ali and R. Delhibabu and Everette Jacob Remington Nelson},
  year = {2026},
  month = aug,
  eprint = {2608.20413},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/cf5903b5d8af40fba5e21a2fefdfd4e634dd0f81}
}