English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large language models (LLMs) have broad medical knowledge and can reasonabout medical information across many domains, holding promising potential fordiverse medical applications in the near future. In this study, we demonstratea concerning vulnerability of LLMs in medicine. Through targeted manipulationof just 1.1% of the model's weights, we can deliberately inject an incorrectbiomedical fact. The erroneous information is then propagated in the model'soutput, whilst its performance on other biomedical tasks remains intact. Wevalidate our findings in a set of 1,038 incorrect biomedical facts. Thispeculiar susceptibility raises serious security and trustworthiness concernsfor the application of LLMs in healthcare settings. It accentuates the need forrobust protective measures, thorough verification mechanisms, and stringentmanagement of access to these models, ensuring their reliable and safe use inmedical practice.

Medical Foundation Models are Susceptible to Targeted Misinformation Attacks