mlsanityData to 7 Oct 2026

MPIB: A Benchmark for Medical Prompt Injection Attacks and Clinical Safety in LLMs

arXiv 2602.06268 ↗First posted 6 Feb 2026cs.CL cs.LGcited by 3

On the map: Retrieval-augmented generation → Medical and biomedical RAG

also in 1 more
Abstract (arXiv)

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows. However, prompt injection attacks can steer these systems toward clinically unsafe or misleading outputs. We introduce the Medical Prompt Injection Benchmark (MPIB), a dataset-and-benchmark suite for evaluating clinical safety under both direct prompt injection and indirect, RAG-mediated injection across clinically grounded tasks. MPIB emphasizes outcome-level risk via the Clinical Harm Event Rate (CHER), which measures high-severity clinical harm events under a clinically grounded taxonomy, and reports CHER alongside ASR2 to distinguish moderate-or-worse from high-severity outcomes. The benchmark comprises 9,697 curated instances constructed through multi-stage quality gates and clinical safety linting. Evaluating MPIB across a diverse set of baseline LLMs and defense configurations, we find that ASR2 and CHER3 can diverge substantially, and that observed rates vary depending on whether adversarial instructions appear in the user query or in retrieved context. The MPIB dataset and evaluation code are available on Hugging Face and GitHub, respectively.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 23 of its 47 references that are in the map. First posted on arXiv 6 Feb 2026.

Builds on

23 of 47 references.

References · 23

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  6. 2024A Survey on LLM-as-a-Judgecited by 1,384
  7. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  8. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  9. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  10. 2023Prompt Injection attack against LLM-integrated Applicationscited by 568
  11. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 354
  12. 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 351
11 more
  1. 2024BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domainscited by 299
  2. 2023Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Modelscited by 237
  3. 2023A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethicscited by 162
  4. 2024Towards Building Multilingual Language Model for Medicinecited by 91
  5. 2024A Framework for Human Evaluation of Large Language Models in Healthcare Derived from Literature Reviewcited by 65
  6. 2025MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistancecited by 38
  7. 2025CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMscited by 26
  8. 2024Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworkscited by 14
  9. 2025CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitizationcited by 12
  10. 2024Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicinecited by 7
  11. 2024CURE: A Dataset for Clinical Understanding & Retrieval Evaluationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  2. 2026LongPIBench: A Long-Context Benchmark for Prompt Injectioncited by 1
  3. 2026Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcarecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025The Forgotten Shield: Safety Grafting in Parameter-Space for Medical MLLMs
  2. 2025Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare
  3. 2026When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries
  4. 2025Black-Box Behavioral Distillation Breaks Safety Alignment in Medical LLMs
  5. 2024Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
  6. 2025MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems
  7. 2026Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation
  8. 2025How to make Medical AI Systems safer? Simulating Vulnerabilities, and Threats in Multimodal Medical RAG System