AI in Medicine: Who Else Is Reading Your Prompt? Security and Privacy in Clinical AI – Hosted by the Geisel Academy of Educators and Scholars is organized by Dartmouth Health and will be held on Jan 28, 2027.
Overview:
This session covers how AI systems fail when someone intends them to. Plummer sets out the healthcare threat model, then the attacks particular to language models: direct and indirect prompt injection, data leakage through prompts and training data, jailbreaks, and abuse of agentic tool access. He then reverses the direction, to AI as the weapon, through voice cloning, phishing at scale, and deepfake social engineering. The practical question throughout is what happens to text a clinician types into a chatbot, and how a consumer product differs from a contracted enterprise instance.
Learning Objectives:
At the conclusion of this learning activity, participants will be able to:
Accreditation:
In support of improving patient care, Dartmouth Health is jointly accredited by the Accreditation Council for Continuing Medical Education (ACCME), the Accreditation Council for Pharmacy Education (ACPE), and the American Nurses Credentialing Center (ANCC), to provide continuing education for the healthcare team.
American Medical Association (AMA):
Dartmouth Health designates this Live Activity for a maximum of 1.00 AMA PRA Category 1 Credits™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.
American Nurses Credentialing Center (ANCC):
Dartmouth Health designates this Live Activity for a maximum of 1.00 ANCC contact hours.
Accreditation Council of Pharmacy Education (ACPE):
Dartmouth Health designates this knowledge-based activity for a maximum of 1.00 hour. Credit will be provided to NABP CPE Monitor within 60 days after the activity completion.
Copyrights © 2026 eMedEvents Corporation, All Rights Reserved