Adversarial prompt and fine-tuning attacks threaten medical large language models.

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

SUBMITTER: Yang Y 

PROVIDER: S-EPMC12511276 | biostudies-literature | 2025 Oct

REPOSITORIES: biostudies-literature