Saved in:
Bibliographic Details
Main Authors: Yang, Yifan, Jin, Qiao, Huang, Furong, Lu, Zhiyong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.12259
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912159059935232
author Yang, Yifan
Jin, Qiao
Huang, Furong
Lu, Zhiyong
author_facet Yang, Yifan
Jin, Qiao
Huang, Furong
Lu, Zhiyong
contents 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 in three medical tasks. Utilizing real-world patient data, we demonstrate that both open-source and proprietary LLMs are susceptible to manipulation across multiple tasks. This research further reveals that domain-specific tasks demand more adversarial data in model fine-tuning than general domain tasks for effective attack execution, especially for more capable models. We discover that while integrating adversarial data does not markedly degrade overall model performance on medical benchmarks, it does 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12259
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adversarial Attacks on Large Language Models in Medicine
Yang, Yifan
Jin, Qiao
Huang, Furong
Lu, Zhiyong
Artificial Intelligence
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 in three medical tasks. Utilizing real-world patient data, we demonstrate that both open-source and proprietary LLMs are susceptible to manipulation across multiple tasks. This research further reveals that domain-specific tasks demand more adversarial data in model fine-tuning than general domain tasks for effective attack execution, especially for more capable models. We discover that while integrating adversarial data does not markedly degrade overall model performance on medical benchmarks, it does 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.
title Adversarial Attacks on Large Language Models in Medicine
topic Artificial Intelligence
url https://arxiv.org/abs/2406.12259