JetBrains022 phút
Our Research on Membership Inference Attacks and Preventing Privacy Leaks
JetBrains researchers present EZ MIA (Error Zone Membership Inference Attack), a lightweight method for detecting whether specific data was used to train fine-tuned LLMs. Unlike existing approaches that rely on aggregate sequence loss or expensive shadow model training, EZ MIA focuses on token-level error positions where memorization signals are most concentrated, requiring only two forward passes per sequence. Experiments on GPT-2, GPT-2-XL, and Llama-2 show EZ MIA outperforms baselines like LOSS, Min-K++, and SPV-MIA by up to 9x. The research also confirms that full fine-tuning creates significantly more membership leakage than LoRA-based fine-tuning, though LoRA does not eliminate the risk entirely — especially for larger models.
