ArticleNature communications2025
Adversarial prompt and fine-tuning attacks threaten medical large language models.
Article in Nature communications, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 8 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
8 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Large Language Models in Colorectal Cancer Care and Clinical Decision Support: Systematic Review.Journal of medical Internet research · 2026Pooled it
- Prompt Injection in Clinical Artificial Intelligence Systems: The Emerging Security Challenge of Large Language Models and Agentic AI.Annals of biomedical engineering · 2026Article
- Deployment protocol and base model jointly determine residual risk in rule-based clinical LLM supervision.Research square · 2026Article
- FaithfulnessFindings of ACL. ACL · 2026Article
- Differences in Safety Risks Across Languages in Health-Relevant Queries: Vulnerability Analysis of Large Language Model Responses.JMIR formative research · 2026Article
- Enhancing adversarial resilience in semantic caching for secure retrieval augmented generation systems.Scientific reports · 2026Article
- Drug or Pokémon? An analysis of the ability of large language models to discern fabricated medications.medRxiv : the preprint server for health sciences · 2026Article
- Clinical warrant in medical LLM evaluation.Frontiers in digital health · 2026Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses a significant threat, potentially leading to harmful outcomes in delicate medical contexts. This study investigates the vulnerability of LLMs to two types of adversarial attacks-prompt injections with malicious instructions and fine-tuning with poisoned samples-across three medical tasks: disease prevention, diagnosis, and treatment. Utilizing real-world patient data, we demonstrate that both open-source and proprietary LLMs are vulnerable to malicious manipulation across multiple tasks. We discover that while integrating poisoned data does not markedly degrade overall model performance on medical benchmarks, it can lead to noticeable shifts in fine-tuned model weights, suggesting a potential pathway for detecting and countering model attacks. This research highlights the urgent need for robust security measures and the development of defensive mechanisms to safeguard LLMs in medical applications, to ensure their safe and effective deployment in healthcare settings.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.