ModelRefs / Membership Inference Attack — AI Glossary
Membership Inference Attack — AI Glossary
An attack determining whether a specific data record was included in a model's training set by analyzing model confidence or outputs.
Overview
Membership inference (Shokri et al. 2017) exploits the fact that models are more confident on training examples than held-out examples. For LLMs, success is measured by perplexity differences on candidate examples. Relevant for GDPR 'right to erasure' (proving data inclusion) and training data auditing.
Reference details
| Topic | safety |
|---|---|
| Last reviewed | 2026-06-24 |
Related terms
Primary source
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Membership Inference Attack — AI Glossary.
Frequently asked questions
What is Membership Inference Attack?
An attack determining whether a specific data record was included in a model's training set by analyzing model confidence or outputs.
What concepts are related to Membership Inference Attack?
Closely related concepts include differential privacy, pii detection, llm security.