AML.T0057
LLM Data Leakage
Description
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.
Honesty-tier rationale
Exfiltration is mostly bound to real model/inference-API access; some sub-techniques can be shown as concepts (see membership inference), the rest need infrastructure.