Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio

• URL: http://arxiv.org/abs/2505.17154v1
• Date: Thu, 22 May 2025 11:27:50 GMT
• Title: Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio
• Authors: Gertrude Hattoh, Jeremiah Ayensu, Nyarko Prince Ofori, Solomon Eshun, Darlington Akogo,
• Abstract summary: Our study generated 1020 novel toxic proteins and 5,000 toxic small molecules.<n>In-depth computational toxicity assessments revealed that all the proteins scored high in toxicity.<n>Our findings underscore the critical need for robust governance and technical safeguards to balance rapid biotechnological innovation with biosecurity imperatives.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Advances in AI, particularly LLMs, have dramatically shortened drug discovery cycles by up to 40% and improved molecular target identification. However, these innovations also raise dual-use concerns by enabling the design of toxic compounds. Prompting Moremi Bio Agent without the safety guardrails to specifically design novel toxic substances, our study generated 1020 novel toxic proteins and 5,000 toxic small molecules. In-depth computational toxicity assessments revealed that all the proteins scored high in toxicity, with several closely matching known toxins such as ricin, diphtheria toxin, and disintegrin-based snake venom proteins. Some of these novel agents showed similarities with other several known toxic agents including disintegrin eristostatin, metalloproteinase, disintegrin triflavin, snake venom metalloproteinase, corynebacterium ulcerans toxin. Through quantitative risk assessments and scenario analyses, we identify dual-use capabilities in current LLM-enabled biodesign pipelines and propose multi-layered mitigation strategies. The findings from this toxicity assessment challenge claims that large language models (LLMs) are incapable of designing bioweapons. This reinforces concerns about the potential misuse of LLMs in biodesign, posing a significant threat to research and development (R&D). The accessibility of such technology to individuals with limited technical expertise raises serious biosecurity risks. Our findings underscore the critical need for robust governance and technical safeguards to balance rapid biotechnological innovation with biosecurity imperatives.

Related papers

• SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification [11.083274646861312]
  Multimodal large language models (MLLMs) enable multimodal generation but inherit toxic, biased, and NSFW signals from pretraining corpora.<n>We propose SGM, a white-box neuron-level multimodal intervention that acts like safety glasses for toxic neurons.
  arXiv  Detail & Related papers  (2025-12-17T03:31:36Z)
• Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective [104.09817371557476]
  Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks.<n>Their potential to generate harmful content has raised serious safety concerns.<n>We introduce three novel multi-label benchmarks for toxicity detection.
  arXiv  Detail & Related papers  (2025-10-16T06:50:33Z)
• 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)
• Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification? [19.700175505235876]
  ToxiMol is the first benchmark task for general-purpose Multimodal Large Language Models (MLLMs) focused on molecular toxicity repair.<n>We construct a standardized dataset covering 11 primary tasks and 560 representative toxic molecules spanning diverse mechanisms and granularities.
  arXiv  Detail & Related papers  (2025-06-12T17:25:53Z)
• Towards an AI co-scientist [48.11351101913404]
  We introduce an AI co-scientist, a multi-agent system built on Gemini 2.0.<n>The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses.<n>The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method.
  arXiv  Detail & Related papers  (2025-02-26T06:17:13Z)
• MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks [104.50239783909063]
  Multimodal large language models with Retrieval Augmented Generation (RAG) have significantly advanced tasks such as multimodal question answering.<n>This reliance on external knowledge poses a critical yet underexplored safety risk: knowledge poisoning attacks.<n>We propose MM-PoisonRAG, the first framework to systematically design knowledge poisoning in multimodal RAG.
  arXiv  Detail & Related papers  (2025-02-25T04:23:59Z)
• Pesti-Gen: Unleashing a Generative Molecule Approach for Toxicity Aware Pesticide Design [0.0]
  Climate change has reduced crop resilience and pesticide efficacy, making reliance on synthetic pesticides inevitable.<n>We propose Pesti-Gen, a novel generative model based on variational auto-encoders to generate pesticide candidates with optimized properties.<n>Pesti-Gen achieves approximately 68% structural validity in generating new molecular structures.
  arXiv  Detail & Related papers  (2025-01-24T13:00:54Z)
• BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction [65.93303145891628]
  BatGPT-Chem is a large language model with 15 billion parameters, tailored for enhanced retrosynthesis prediction. Our model captures a broad spectrum of chemical knowledge, enabling precise prediction of reaction conditions. This development empowers chemists to adeptly address novel compounds, potentially expediting the innovation cycle in drug manufacturing and materials science.
  arXiv  Detail & Related papers  (2024-08-19T05:17:40Z)
• Machine Learning Applied to the Detection of Mycotoxin in Food: A Review [0.0]
  Mycotoxins pose significant threats to global food safety and public health. Traditional lab analysis methods for mycotoxin detection can be time-consuming. Machine learning (ML) methods have gained popularity for use in the detection of mycotoxins.
  arXiv  Detail & Related papers  (2024-04-23T14:13:31Z)
• Detoxifying Large Language Models via Knowledge Editing [57.0669577257301]
  This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs) We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts. We conduct experiments with several knowledge editing approaches, indicating that knowledge editing has the potential to detoxify LLMs with a limited impact on general performance efficiently.
  arXiv  Detail & Related papers  (2024-03-21T15:18:30Z)
• Unveiling the Implicit Toxicity in Large Language Models [77.90933074675543]
  The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. We show that LLMs can generate diverse implicit toxic outputs that are exceptionally difficult to detect via simply zero-shot prompting. We propose a reinforcement learning (RL) based attacking method to further induce the implicit toxicity in LLMs.
  arXiv  Detail & Related papers  (2023-11-29T06:42:36Z)
• Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools [0.0]
  This article differentiates two classes of AI tools that could pose such biosecurity risks: large language models (LLMs) and biological design tools (BDTs)
  arXiv  Detail & Related papers  (2023-06-24T12:48:49Z)
• Toxicity Detection in Drug Candidates using Simplified Molecular-Input Line-Entry System [0.0]
  The need for analysis of toxicity in new drug candidates and the requirement of doing it fast have asked the consideration of scientists. This paper goes for the study of simplified Molecular Input Line-Entry System (SMILES) as a parameter to develop Long short term memory (LSTM) based models.
  arXiv  Detail & Related papers  (2021-01-21T07:02:21Z)
• RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models [93.151822563361]
  Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language, and the effectiveness of controllable text generation algorithms at preventing such toxic degeneration.
  arXiv  Detail & Related papers  (2020-09-24T03:17:19Z)
• Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics [109.70543391923344]
  CLaSS (Controlled Latent attribute Space Sampling) is an efficient computational method for attribute-controlled generation of molecules. We screen the generated molecules for additional key attributes by using deep learning classifiers in conjunction with novel features derived from atomistic simulations. The proposed approach is demonstrated for designing non-toxic antimicrobial peptides (AMPs) with strong broad-spectrum potency.
  arXiv  Detail & Related papers  (2020-05-22T15:57:58Z)

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.