2 papers
cs.CR2025
Fast-MIA: Efficient and Scalable Membership Inference for LLMs
Hiromu Takahashi, Shotaro Ishihara
We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against large language models (LLMs). MIA h…
cs.CL2024
Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper
Shotaro Ishihara, Hiromu Takahashi
Dominant pre-trained language models (PLMs) have demonstrated the potential risk of memorizing and outputting the training data. While this concern has been discussed mainly in Eng…