A medical RAG chatbot leaked sensitive system prompts, configurations, and patient conversation records via client-side browser tools, contradicting its privacy claims.
Testing and Evaluation of Health Care Applications of Large Language Models.JAMA2025;333:319
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
When RAG Chatbots Expose Their Backend: An Anonymized Case Study of Privacy and Security Risks in Patient-Facing Medical AI
A medical RAG chatbot leaked sensitive system prompts, configurations, and patient conversation records via client-side browser tools, contradicting its privacy claims.