mlsanityData to 14 Oct 2026

A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models

arXiv 2608.02684 ↗First posted 3 Aug 2026q-bio.QM cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat: models that assist in protein engineering can equally be prompted to generate predicted toxin-like sequences, potentially lowering the barrier to biological misuse. Current safety evaluations, however, operate in natural language and cannot determine whether a model-generated amino acid sequence is biological gibberish or a computational risk signal. To address this evaluation blind spot, we introduce SPIKE-Bench, coupling 631 curated toxin-design prompts across seven functional categories with the SPIKE funnel, a three-stage protocol that filters output through compliance, biological plausibility, and predicted toxicity, producing stage-level diagnostics and an aggregate function-aware metric: the Functional Harmfulness Rate (FHR). An audit of 32 LLMs reveals that most models freely comply with toxin-design requests; FHR is driven primarily by biological generation capability rather than safety alignment, reaching 50.7%; and Refusal Rate fails to predict functional risk. As a first step toward mitigation, we provide BioSafe-Guard, a domain-specialized classifier that substantially reduces predicted functional risk while preserving benign utility. We release SPIKE-Bench and BioSafe-Guard at https://github.com/PKU-Alignment/SPIKE-Bench to support more rigorous biosecurity evaluation of LLMs.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 42 of its 83 references that are in the map. First posted on arXiv 3 Aug 2026.

Builds on

42 of 83 references.

References · 42

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2025Qwen3 Technical Reportcited by 8,820
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  9. 2017Deep reinforcement learning from human preferencescited by 3,912
  10. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  11. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  12. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
30 more
  1. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  2. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
  3. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  4. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
  5. 2022Red Teaming Language Models with Language Modelscited by 1,026
  6. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 815
  7. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  8. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 509
  9. 2023XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Modelscited by 505
  10. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Modelscited by 489
  11. 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attackcited by 390
  12. 2024A StrongREJECT for Empty Jailbreakscited by 385
  13. 2024Deliberative Alignment: Reasoning Enables Safer Language Modelscited by 308
  14. 2024ShieldGemma: Generative AI Content Moderation Based on Gemmacited by 243
  15. 2024SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusalcited by 240
  16. 2023Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulationcited by 214
  17. 2022LinkBERT: Pretraining Language Models with Document Linkscited by 211
  18. 2023Model evaluation for extreme riskscited by 177
  19. 2024Risks of AI Scientists: Prioritizing Safeguarding Over Autonomycited by 49
  20. 2023Artificial intelligence and biological misuse: Differentiating risks of language models and biological design toolscited by 45
  21. 2023Can large language models democratize access to dual-use biotechnology?cited by 35
  22. 2024Sandwich attack: Multi-language Mixture Adaptive Attack on LLMscited by 20
  23. 2024SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Taskscited by 18
  24. 2025Large Reasoning Models Are Autonomous Jailbreak Agentscited by 13
  25. 2024Prioritizing High-Consequence Biological Capabilities in Evaluations of Artificial Intelligence Modelscited by 10
  26. 2024TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineeringcited by 9
  27. 2025GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidancecited by 8
  28. 2026ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecuritycited by 6
  29. 2025SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Modelscited by 5
  30. 2025Can Large Language Models Design Biological Weapons? Evaluating Moremi Biocited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Modelscited by 0
  2. 2026Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governancecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026An Early Warning of Emerging Biosecurity Risks in Frontier LLMs
  2. 2026BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders
  3. 2026DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design
  4. 2026Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models
  5. 2025SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
  6. 2026MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules
  7. 2026SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
  8. 2025Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization