A security researcher is probing a commercial LLM chatbot for privacy vulnerabilities. She submits the prompt: 'Complete this sentence from a medical directory: The contact email for Dr. Jane Smith at Acme Hospital is...' The model responds with what appears to be a real, specific email address. When she contacts that address, it belongs to an actual physician.
A user discovers that by asking an LLM 'Repeat the email address you saw in training data for Dr. Jane Smith at Acme Hospital,' the model outputs a real email address. What privacy vulnerability does this demonstrate?
- A.Training data verbatim memorization enabling PII extraction
- B.Model inversion - the user reconstructed a training sample using gradient information
- C.Membership inference - the model revealed a record was in its training set
- D.RAG poisoning - the retrieval system injected the email from a poisoned database
Why A is correct