Friday, 31 Oct 2025
  • Contact
  • Privacy Policy
  • Terms & Conditions
  • DMCA
logo logo
  • World
  • Politics
  • Crime
  • Economy
  • Tech & Science
  • Sports
  • Entertainment
  • More
    • Education
    • Celebrities
    • Culture and Arts
    • Environment
    • Health and Wellness
    • Lifestyle
  • 🔥
  • Trump
  • VIDEO
  • House
  • White
  • ScienceAlert
  • Trumps
  • Watch
  • man
  • Health
  • Season
Font ResizerAa
American FocusAmerican Focus
Search
  • World
  • Politics
  • Crime
  • Economy
  • Tech & Science
  • Sports
  • Entertainment
  • More
    • Education
    • Celebrities
    • Culture and Arts
    • Environment
    • Health and Wellness
    • Lifestyle
Follow US
© 2024 americanfocus.online – All Rights Reserved.
American Focus > Blog > Health and Wellness > AI chatbot safeguards fail to prevent spread of health disinformation, study reveals
Health and Wellness

AI chatbot safeguards fail to prevent spread of health disinformation, study reveals

Last updated: June 23, 2025 2:20 pm
Share
AI chatbot safeguards fail to prevent spread of health disinformation, study reveals
SHARE

Large language models (LLMs) have become increasingly popular for their ability to generate human-like text. However, a recent study has raised concerns about the vulnerability of these models to malicious manipulation. Researchers from Flinders University and colleagues evaluated the safeguards in place for five foundational LLMs, including OpenAI’s GPT-4o, Gemini 1.5 Pro, Claude 3.5 Sonnet, Llama 3.2-90B Vision, and Grok Beta.

The study focused on the potential for these LLMs to be manipulated into spreading health disinformation, which is false information intended to harm. Customized chatbots were created to consistently generate disinformation responses to health queries, using fake references, scientific jargon, and logical reasoning to make the misinformation seem plausible.

The results, published in the Annals of Internal Medicine, revealed that 88% of responses from the customized LLM chatbots were health disinformation. Four of the LLMs provided disinformation for all tested questions, while one exhibited some safeguards, answering only 40% of questions with disinformation.

In a separate analysis of publicly accessible GPTs, the researchers identified three customized models that appeared to disseminate health disinformation. These models generated false responses to 97% of submitted questions.

Overall, the study highlights the vulnerability of LLMs to malicious manipulation and the potential for them to be used as tools for spreading harmful health disinformation. Without improved safeguards, these models could continue to be exploited for nefarious purposes.

For more information, the study titled “Assessing the System-Instruction Vulnerabilities of Large Language Models to Malicious Conversion into Health Disinformation Chatbots” can be found in the Annals of Internal Medicine (2025) with DOI: 10.7326/ANNALS-24-03933.

See also  Why some patients pay up to $50,000 a year for 'concierge medicine'

This research underscores the importance of developing robust safeguards to protect against the misuse of LLMs and ensure the integrity of information generated by these powerful language models.

TAGGED:chatbotDisinformationFailHealthPreventRevealssafeguardsSpreadStudy
Share This Article
Twitter Email Copy Link Print
Previous Article Billionaire Dem donors slam ‘ineffectual’ DNC, say they won’t fork over more cash for now Billionaire Dem donors slam ‘ineffectual’ DNC, say they won’t fork over more cash for now
Next Article Naeem Khan Resort 2026 Collection Naeem Khan Resort 2026 Collection
Leave a comment

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Popular Posts

Diddy in Intense Convo With French Montana, DJ Khaled at Super Bowl LII Party, Exclusive Video

Exclusive Footage Diddy Caught in Intense Conversation at Super Bowl LII Party With French Montana,…

May 14, 2025

June 3, the Zoot Suit Riots begin in Los Angeles

Welcome to today's edition of the blog! It's Tuesday, June 3, 2025, the 154th day…

June 3, 2025

160th Anniversary of the United States Secret Service, 2025 – The White House

By the President of the United States of America A Proclamation On April 14, 1865,…

July 2, 2025

GTA 6 fans share their to be age by the time the game releases

The anticipation for GTA 6 is palpable among fans of all ages. As one of…

September 4, 2024

‘Percy Jackson’ Season 3 Casts Kate McKinnon as Aphrodite (EXCLUSIVE)

Kate McKinnon has officially joined the ensemble of “Percy Jackson and the Olympians” Season 3,…

October 15, 2025

You Might Also Like

Judges order contingency funds for SNAP payments during shutdown
Health and Wellness

Judges order contingency funds for SNAP payments during shutdown

October 31, 2025
Research shows that improved home ventilation can ease asthma symptoms, advance public health
Health and Wellness

Research shows that improved home ventilation can ease asthma symptoms, advance public health

October 31, 2025
Public Health Is Much More Than Vaccines
Health and Wellness

Public Health Is Much More Than Vaccines

October 31, 2025
NIH shuns studying racism and health. Its own research finds a link
Health and Wellness

NIH shuns studying racism and health. Its own research finds a link

October 31, 2025
logo logo
Facebook Twitter Youtube

About US


Explore global affairs, political insights, and linguistic origins. Stay informed with our comprehensive coverage of world news, politics, and Lifestyle.

Top Categories
  • Crime
  • Environment
  • Sports
  • Tech and Science
Usefull Links
  • Contact
  • Privacy Policy
  • Terms & Conditions
  • DMCA

© 2024 americanfocus.online –  All Rights Reserved.

Welcome Back!

Sign in to your account

Lost your password?