Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration. (arXiv:2311.06062v1 [cs.CL])

Membership Inference Attacks (MIA) aim to infer whether a target data record
has been utilized for model training or not. Prior attempts have quantified the
privacy risks of language models (LMs) via MIAs, but there is still no
consensus on whether existing MIA algorithms can cause remarkable privacy
leakage on practical Large Language Models (LLMs). Existing MIAs designed for
LMs can be classified into two categories: reference-free and reference-based
attacks. They are both based on the hypothesis that training records …

aim algorithms attacks data language language models large lms model training privacy privacy risks prompt record risks target training