Slide 8 of 27
Part 1 · What Is It?Slide 8
Slide 8 · The Common Misconception
“This only matters if my app trains on user data.” Wrong.
The Misconception

Many teams assume LLM02 is purely a training-data problem — if you don't fine-tune on user conversations, you're safe.

The Reality

Disclosure happens at the output layer too. A RAG system can retrieve another customer's document and hand it straight to the wrong user. An over-permissioned agent can read a database it shouldn't and just answer with what it found. None of that requires training on anything.

One Line

If your LLM can access sensitive data — through training, retrieval, or live API calls — it can disclose it. Training is only one of three paths.

← BackNext → Types Overview