Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership inference attack that tests whether a model can recall specific training examples. The core idea is to turn target data into quiz-style multiple-choice questions and infer membership from the model's answers. Across six widely used LLMs (GPT-3.5, GPT-4o, LLaMA2-7b, LLaMA2-13b, Mistral-7b, and Vicuna-7b) and four datasets, our method achieves an average ROC-AUC of 0.873 and outperforms existing approaches by 20.6%. We further analyze factors affecting attack success, including query complexity, data type, data structure, and training settings. We also evaluate instruction-based, filter-based, and differential privacy-based defenses, which reduce performance but do not eliminate the risk. Our results highlight persistent privacy vulnerabilities in modern LLMs.
@article{arxiv.2605.06423,
title = {Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models},
author = {Zeyuan Chen and Yihan Ma and Xinyue Shen and Michael Backes and Yang Zhang},
journal= {arXiv preprint arXiv:2605.06423},
year = {2026}
}