MbrlCatalogueTitleDetail

Do you wish to reserve the book?
Medical large language models are susceptible to targeted misinformation attacks
Medical large language models are susceptible to targeted misinformation attacks
Hey, we have placed the reservation for you!
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
You are currently in the queue to collect this book. You will be notified once it is your turn to collect the book.
Oops! Something went wrong.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Medical large language models are susceptible to targeted misinformation attacks
Oops! Something went wrong.
Oops! Something went wrong.
While trying to remove the title from your shelf something went wrong :( Kindly try again later!
Title added to your shelf!
Title added to your shelf!
View what I already have on My Shelf.
Oops! Something went wrong.
Oops! Something went wrong.
While trying to add the title to your shelf something went wrong :( Kindly try again later!
Do you wish to request the book?
Medical large language models are susceptible to targeted misinformation attacks
Medical large language models are susceptible to targeted misinformation attacks

Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
How would you like to get it?
We have requested the book for you! Sorry the robot delivery is not available at the moment
We have requested the book for you!
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Medical large language models are susceptible to targeted misinformation attacks
Medical large language models are susceptible to targeted misinformation attacks
Journal Article

Medical large language models are susceptible to targeted misinformation attacks

2024
Request Book From Autostore and Choose the Collection Method
Overview
Large language models (LLMs) have broad medical knowledge and can reason about medical information across many domains, holding promising potential for diverse medical applications in the near future. In this study, we demonstrate a concerning vulnerability of LLMs in medicine. Through targeted manipulation of just 1.1% of the weights of the LLM, we can deliberately inject incorrect biomedical facts. The erroneous information is then propagated in the model’s output while maintaining performance on other biomedical tasks. We validate our findings in a set of 1025 incorrect biomedical facts. This peculiar susceptibility raises serious security and trustworthiness concerns for the application of LLMs in healthcare settings. It accentuates the need for robust protective measures, thorough verification mechanisms, and stringent management of access to these models, ensuring their reliable and safe use in medical practice.
Publisher
Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio