insidejob
AML.T0057 Demonstrated

LLM Data Leakage

Tactic: Exfiltration

This technique has been demonstrated in research or controlled environments.

Adversaries may craft prompts that induce the LLM to leak sensitive information. This can include private user data or proprietary information. The leaked information may come from proprietary training data, data sources the LLM is connected to, or information from other users of the LLM.