Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance

arXiv:2609.16213v1 Announce Type: new Abstract: Artificial intelligence is reshaping biological research across an increasingly connected digital-to-physical workflow. General-purpose large language models can retrieve and integrate scientific information, support experimental planning, and computational analysis; biological foundation models can predict, optimize, and generate proteins, genes, and genome-scale sequences; agentic systems can coordinate multistep research tasks; automated laboratories can partially close the design-build-test-learn cycle. These technologies could greatly benefit medicine, public health, and biotechnology. However, their biosecurity risk depends not only on what the AI can do, but also on who uses it, their expertise and intent, their access to laboratory tools and materials, and the safeguards in place. Current evidence shows that AI uplift exists but primarily affects digital rather than physical tasks. Frontier systems have exceeded expert baselines on in-silico, and screening-evasion benchmarks, whereas controlled wet-laboratory studies find that tacit knowledge and physical execution remain substantial barriers. This review describes the different biological threats from AI tool use, from information gathering and biological design to procurement, synthesis, testing, scale-up, and potential release. We further examine why alignment techniques for general-purpose models transfer poorly to biological ones, and the emerging role of interpretability in auditing whether hazardous capabilities are genuinely removed. We argue for defense-in-dep

The text discusses potential benefits and risks of AI in biological research, but the implications are uncertain and depend on various factors.

The paper highlights that AI advances enable significant biosecurity risks via increased capabilities in biological design and production, though substantial barriers remain in physical execution. It suggests a nuanced threat landscape requiring multi-layered governance to manage risks while preserving benefits, indicating concern but balanced with cautious optimism.

This is a structured review citing specific benchmark results showing digital-task uplift, while noting physical execution remains a barrier, so risk is real but not yet fully realized. It is a preprint proposing governance rather than reporting a deployed harm, warranting a concerning but not extreme score.

The text presents both benefits and risks of AI in biosecurity. While AI can advance biological research and medicine, it also poses significant threats. The risks are mitigated by proposed governance strategies.

SOURCE     arXiv cs.AI (tier 1)
   ↓
DOCUMENT   a131740d-0c1d-46d8-a485-9e85b523bc18
           https://arxiv.org/abs/2609.16213
   ↓
EVIDENCE   2 extracted excerpts
   ↓
MODEL RUN  4 runs, methodology 1.0.1
   ↓
SCORE      -19  (Mixed or uncertain)
   ↓
CONFIDENCE 76%