An Early Warning of Emerging Biosecurity Risks in Frontier LLMs

• URL: http://arxiv.org/abs/2607.18056v1
• Date: Mon, 20 Jul 2026 15:26:23 GMT
• Title: An Early Warning of Emerging Biosecurity Risks in Frontier LLMs
• Abstract summary: We develop Intern-BioBreaker, a specialized bio-red-teaming model, together with an integrated computational-to-physical framework.<n>Within this framework, Intern-BioBreaker generates targeted jailbreak prompts to test whether aligned models can be induced to provide operational guidance.<n>Our evaluation reveals a concerning gap between text-level safeguards and the risks posed by capable scientific models.
• Score: 62.01705276160883
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the biological risks of frontier models, we develop Intern-BioBreaker, a specialized bio-red-teaming model, together with an integrated computational-to-physical framework that couples model-level stress testing with wet-lab validation. Within this framework, Intern-BioBreaker generates targeted jailbreak prompts to test whether aligned models can be induced to provide operational guidance for safety-sensitive biological tasks or produce sequence-level outputs with potentially harmful properties. Selected sequence outputs are then carried forward for DNA synthesis, host expression, and orthogonal protein verification to assess whether model-generated designs can yield the intended biological products. Our evaluation reveals a concerning gap between text-level safeguards and the risks posed by capable scientific models: (i) Intern-BioBreaker outperforms baseline attack models and reveals widespread bio-risk jailbreak vulnerabilities across both open-weight and proprietary frontier LLMs, with several targets reaching near-saturated or 100% task-level attack success rate (ASR); (ii) in sequence-level case studies, GPT-5.5 can be induced to generate modified viral candidate sequences with pathogenic potential; the corresponding translated proteins may exhibit even stronger receptor-binding affinity and thus enhanced infection potential; and (iii) end-to-end verification shows that selected model-generated biological designs are not merely textual artifacts, but can be physically realized under controlled experimental settings. These findings underscore the need for stronger biological red-teaming, nucleic acid synthesis screening, and safety mechanisms that keep pace with model capabilities.

Related papers

• A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models [24.33428502712115]
  Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat.<n>Current safety evaluations operate in natural language and cannot determine whether a model-generated amino acid sequence is biological gibberish.<n>We release SPIKE-Bench and BioSafe-Guard to support more rigorous biosecurity evaluation of LLMs.
  arXiv  Detail & Related papers  (2026-08-03T03:51:19Z)
• MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules [60.55214893687032]
  MolSafeEval is a benchmark dedicated to evaluating and analyzing the safety risks of molecular generation.<n>It integrates heterogeneous safety knowledge - ranging from toxicological databases to hazard rules - into a structured molecular safety knowledge graph.<n>By systematically revealing the safety vulnerabilities of current generative approaches, MolSafeEval offers a new lens for benchmarking molecular models.
  arXiv  Detail & Related papers  (2026-07-01T05:33:51Z)
• Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization [85.4863852505905]
  We introduce unsupervised reward optimization of protein language models (PLMs)<n>Our key insight is that task-agnostic rewards, which combine intrinsic model uncertainty with semantic consistency informed by protein representation models, exhibit strong correlation with controllability measures across base models and temperature regimes.<n>Our framework provides a scalable pathway toward controllable biomolecular design in settings where labeled preferences or experimental feedback are scarce or unavailable.
  arXiv  Detail & Related papers  (2026-06-17T11:42:01Z)
• ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks [86.89727311669937]
  We introduce ViroBench, the first comprehensive and large-scale benchmark specifically designed for nucleotide foundation models (NFMs)<n>ViroBench evaluates models across two critical dimensions: biological understanding and latent biosecurity risk, covering 18 diverse scenarios within 4 task types.<n>ViroBench provides interpretable, diagnostic evaluations and a reproducible measurement framework for future research on viral nucleotide foundation models.
  arXiv  Detail & Related papers  (2026-05-25T03:31:46Z)
• Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models I: The Task-Query Architecture [0.38186458149494623]
  This paper describes the first component of a novel Biothreat Benchmark Generation (BBG) Framework.<n>The BBG approach is designed to help model developers and evaluators reliably measure and assess the biosecurity risk uplift and general harm potential of existing and future AI models.<n>As a pilot, the BBG is first being developed to address bacterial biological threats only.
  arXiv  Detail & Related papers  (2025-12-09T00:16:44Z)
• Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models [24.414900360499548]
  Open-weight bio-foundation models could enable bad actors to develop more deadly bioweapons.<n>Current approaches focus on filtering biohazardous data during pre-training.<n>BioRiskEval is a framework to evaluate the robustness of procedures intended to reduce the dual-use capabilities of bio-foundation models.
  arXiv  Detail & Related papers  (2025-10-31T17:00:20Z)
• Resilient Biosecurity in the Era of AI-Enabled Bioweapons [0.0]
  Existing biosafety measures rely on sequence alignment and protein-protein interaction prediction to detect dangerous outputs.<n>We evaluate the performance of three leading PPI prediction tools: AlphaFold 3, AF3Complex, and SpatialPPIv2.<n>None of the tools successfully identify any of the four experimentally validated SARS-CoV-2 mutants with confirmed binding.
  arXiv  Detail & Related papers  (2025-08-30T18:09:04Z)
• Conditional Chemical Language Models are Versatile Tools in Drug Discovery [0.0]
  We present SAFE-T, a chemical modeling framework that conditions on biological context to prioritize molecules.<n>It supports principled scoring of molecules across tasks such as virtual screening, drug-target interaction prediction, and activity cliff detection.<n>It consistently achieves performance comparable to or better than existing approaches.
  arXiv  Detail & Related papers  (2025-07-14T13:42:39Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments [112.25067497985447]
  We introduce BioDiscoveryAgent, an agent that designs new experiments, reasons about their outcomes, and efficiently navigates the hypothesis space to reach desired solutions.<n>BioDiscoveryAgent can uniquely design new experiments without the need to train a machine learning model.<n>It achieves an average of 21% improvement in predicting relevant genetic perturbations across six datasets.
  arXiv  Detail & Related papers  (2024-05-27T19:57:17Z)
• Biomanufacturing Harvest Optimization with Small Data [3.8447683272775586]
  We introduce a model to characterize the accumulation of the protein and impurity levels in the fermentation process. A common challenge in the industry is the availability of only a very limited amount of data. We study the harvesting decision for a fermentation process (i.e., when to stop the fermentation and collect the production reward) under model risk.
  arXiv  Detail & Related papers  (2021-01-11T07:47:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.