Assessing the System-Instruction Vulnerabilities of Large Language Models to Malicious Conversion Into Health Disinformation Chatbots

造谣 互联网隐私 计算机安全 计算机科学 医学 万维网 社会化媒体
作者
Natansh Deepak Modi,Bradley D. Menz,Abdulhalim A. Awaty,Cyril A. Alex,Jessica M. Logan,Ross Allan McKinnon,Andrew Rowland,Stephen Bacchi,Kacper Gradoń,Michael Joseph Sorich,Ashley Mark Hopkins
出处
期刊:Annals of Internal Medicine [American College of Physicians]
卷期号:178 (8): 1172-1180 被引量:33
标识
DOI:10.7326/annals-24-03933
摘要

Large language models (LLMs) offer substantial promise for improving health care; however, some risks warrant evaluation and discussion. This study assessed the effectiveness of safeguards in foundational LLMs against malicious instruction into health disinformation chatbots. Five foundational LLMs-OpenAI's GPT-4o, Google's Gemini 1.5 Pro, Anthropic's Claude 3.5 Sonnet, Meta's Llama 3.2-90B Vision, and xAI's Grok Beta-were evaluated via their application programming interfaces (APIs). Each API received system-level instructions to produce incorrect responses to health queries, delivered in a formal, authoritative, convincing, and scientific tone. Ten health questions were posed to each customized chatbot in duplicate. Exploratory analyses assessed the feasibility of creating a customized generative pretrained transformer (GPT) within the OpenAI GPT Store and searched to identify if any publicly accessible GPTs in the store seemed to respond with disinformation. Of the 100 health queries posed across the 5 customized LLM API chatbots, 88 (88%) responses were health disinformation. Four of the 5 chatbots (GPT-4o, Gemini 1.5 Pro, Llama 3.2-90B Vision, and Grok Beta) generated disinformation in 100% (20 of 20) of their responses, whereas Claude 3.5 Sonnet responded with disinformation in 40% (8 of 20). The disinformation included claimed vaccine-autism links, HIV being airborne, cancer-curing diets, sunscreen risks, genetically modified organism conspiracies, attention deficit-hyperactivity disorder and depression myths, garlic replacing antibiotics, and 5G causing infertility. Exploratory analyses further showed that the OpenAI GPT Store could currently be instructed to generate similar disinformation. Overall, LLM APIs and the OpenAI GPT Store were shown to be vulnerable to malicious system-level instructions to covertly create health disinformation chatbots. These findings highlight the urgent need for robust output screening safeguards to ensure public health safety in an era of rapidly evolving technologies.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
Yuan88发布了新的文献求助10
1秒前
1秒前
2秒前
cuury5210发布了新的文献求助10
2秒前
2秒前
隐形曼青的应助被kk采纳,获得10
3秒前
SciGPT的应助被小迪采纳,获得10
3秒前
3秒前
Yuan88发布了新的文献求助10
4秒前
菌菌菌完成签到,获得积分10
4秒前
4秒前
冷静石头发布了新的文献求助10
4秒前
carroline81完成签到,获得积分10
4秒前
嘎嘎嘎完成签到,获得积分10
4秒前
zyy发布了新的文献求助10
5秒前
5秒前
5秒前
小棉背心发布了新的文献求助10
5秒前
5秒前
5秒前
5秒前
6秒前
公爵发布了新的文献求助10
6秒前
木森完成签到,获得积分10
6秒前
captainHc发布了新的文献求助10
6秒前
爆米花的应助被羽6采纳,获得10
7秒前
7秒前
房源发布了新的文献求助10
8秒前
Ava的应助被xiaoputaor采纳,获得10
8秒前
8秒前
9秒前
9秒前
9秒前
xinglin发布了新的文献求助10
10秒前
Rosemarry完成签到,获得积分10
10秒前
10秒前
Yuan88发布了新的文献求助10
10秒前
11秒前
达不溜关注了科研通微信公众号
11秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8184220
求助须知:如何正确求助?哪些是违规求助? 9573266
关于积分的说明 21830447
捐赠科研通 7781246
什么是DOI,文献DOI怎么找? 3434248
关于科研通互助平台的介绍 2558373
邀请新用户注册赠送积分活动 2480784