BioShield: A Context-Aware Firewall for Securing Bio-LLMs

• URL: http://arxiv.org/abs/2603.22612v1
• Date: Mon, 23 Mar 2026 22:18:54 GMT
• Title: BioShield: A Context-Aware Firewall for Securing Bio-LLMs
• Abstract summary: Bio-LLMs can be exploited to generate harmful biological insights under the guise of legitimate research queries.<n>Existing safeguards, such as static prompt filtering, are insufficient when Bio-LLMs are embedded within dynamic biological and application-layer systems.<n>We present BioShield, a context-aware application-level firewall designed to secure Bio LLMs against dual-use attacks.
• Score: 1.2694660563081597
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement of Large Language Models (LLMs) in biological research has significantly lowered the barrier to accessing complex bioinformatics knowledge, ex perimental design strategies, and analytical workflows. While these capabilities accelerate innovation, they also introduce serious dual-use risks, as Bio-LLMs can be exploited to generate harmful biological insights under the guise of legitimate research queries. Existing safeguards, such as static prompt filtering and policy-based restrictions, are insufficient when LLMs are embedded within dynamic biological workflows and application-layer systems. In this paper, we present BioShield, a context-aware application-level firewall designed to secure Bio LLMs against dual-use attacks. At the core of BioShield is a domain-specific prompt scanner that performs contextual risk analysis of incoming queries. The scanner leverages a harmful scoring mechanism tailored to biological dual-use threat cat egories to identify prompts that attempt to conceal malicious intent within seemingly benign research requests. Queries ex ceeding a predefined risk threshold are blocked before reaching the model, effectively preventing unsafe knowledge generation at the source. In addition to pre-generation protection, BioShield deploys a post-generation output verification module that inspects model responses for actionable or weaponizable biological content. If an unsafe response is detected, the system triggers controlled regeneration under strengthened safety constraints. By combining contextual prompt scanning with response-level validation, BioShield provides a layered defense framework specifically designed for bio-domain LLM deployments. Our framework advances cyberbiosecurity by formalizing dual-use threat detection in Bio-LLMs and proposing a structured mitigation strategy for secure, responsible AI driven biological research.

Related papers

• Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance [0.0]
  General-purpose large language models can retrieve and integrate scientific information.<n>Biological foundation models can predict, optimize, and generate proteins, genes, and genome-scale sequences.<n> automated laboratories can partially close the design-build-test-learn cycle.
  arXiv  Detail & Related papers  (2026-09-14T18:44:00Z)
• 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)
• An Early Warning of Emerging Biosecurity Risks in Frontier LLMs [62.01705276160883]
  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.
  arXiv  Detail & Related papers  (2026-07-20T15:26:23Z)
• Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability [65.56750741053266]
  Large language models (LLMs) have transformed misinformation from a content-centric problem into a broader ecosystem-level security challenge.<n>In this paper, we introduce a role-layer framework to unify these risks and defenses.<n>The role characterizes LLMs as attackers, defenders, and vulnerable components of verification systems, while the layer dimension covers content, social contexts, evidence environments, and verification.
  arXiv  Detail & Related papers  (2026-07-11T17:04:17Z)
• GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking [1.4804984980847007]
  Large Language Models (LLMs) constitute pivotal components within the AI-dominated technology ecosystem.<n>LLMs remain vulnerable to adversarial manipulation, particularly through jailbreaking and prompt injection techniques.<n>We propose GAS-Leak-LLM a novel jailbreaking attack based on a genetic algorithm that systematically evolves adversarial suffix to bypass safety constraints.
  arXiv  Detail & Related papers  (2026-06-14T12:41:21Z)
• Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework [60.82334952881798]
  Protein-Text Question Answering (QA) is crucial for interpreting biological sequences through natural language.<n>We propose 2D-ProteinRAG, a novel framework that empowers Large Language Models (LLMs) to operate within the gold-standard biological research workflow.<n>We show that 2D-Protein consistently achieves state-of-the-art performance, outperforming fine-tuned baselines and other RAG methods.
  arXiv  Detail & Related papers  (2026-05-17T05:03:24Z)
• Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [65.6660735371212]
  We present textbftextscJustAsk, a framework that autonomously discovers effective extraction strategies through interaction alone.<n>It formulates extraction as an online exploration problem, using Upper Confidence Bound--based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration.<n>Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.
  arXiv  Detail & Related papers  (2026-01-29T03:53:25Z)
• INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems [70.37731999972785]
  In this paper, we propose Infection-Aware Guard, INFA-Guard, a novel defense framework that explicitly identifies and addresses infected agents as a distinct threat category.<n>During remediation, INFA-Guard replaces attackers and rehabilitates infected ones, avoiding malicious propagation while preserving topological integrity.
  arXiv  Detail & Related papers  (2026-01-21T05:27:08Z)
• 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)
• Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity [56.331312963880215]
  generative artificial intelligence (GenAI) in the biosciences is transforming biotechnology, medicine, and synthetic biology.<n>This Perspective outlines the current state of GenAI in the biosciences and emerging threat vectors ranging from jailbreak attacks and privacy risks to the dual-use challenges posed by autonomous AI agents.<n>We advocate a multi-layered approach to GenAI safety, including rigorous data filtering, alignment with ethical principles during development, and real-time monitoring to block harmful requests.
  arXiv  Detail & Related papers  (2025-10-13T00:24:41Z)
• MalGEN: A Generative Agent Framework for Modeling Malicious Software in Cybersecurity [0.0]
  MalGEN is a multi agent framework that simulates adversarial behavior to generate malware samples.<n>Using MalGEN, we synthesized ten novel malware samples and evaluated them against leading antivirus and behavioral detection engines.<n>The framework addresses data scarcity, enables rigorous testing, and supports the development of resilient and future ready detection strategies.
  arXiv  Detail & Related papers  (2025-06-09T09:32:03Z)
• Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy [65.77763092833348]
  This perspective examines vulnerabilities in AI scientists, shedding light on potential risks associated with their misuse.<n>We take into account user intent, the specific scientific domain, and their potential impact on the external environment.<n>We propose a triadic framework involving human regulation, agent alignment, and an understanding of environmental feedback.
  arXiv  Detail & Related papers  (2024-02-06T18:54:07Z)
• 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)

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.