Saved in:
Bibliographic Details
Main Authors: Takahashi, Hiromu, Ishihara, Shotaro
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.23074
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909028740759552
author Takahashi, Hiromu
Ishihara, Shotaro
author_facet Takahashi, Hiromu
Ishihara, Shotaro
contents 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 has emerged as a crucial technique for auditing privacy risks and copyright infringement in LLMs. However, computational demands have grown substantially: recent methods rely on repeated inference, while practical auditing requires large-scale evaluation. Progress is further hindered by existing implementations that execute methods independently, redundantly computing shared intermediate results such as log-probabilities. To address these challenges, Fast-MIA combines two strategies: (1) high-throughput batch inference via vLLM, achieving approximately 5$\times$ speedup, and (2) a cross-method caching architecture that computes intermediate results once and shares them across methods. The library includes representative MIA methods under a unified framework, integrates with established benchmarks, and supports flexible YAML configuration. We release Fast-MIA under the Apache License 2.0 to support scalable and reproducible MIA research.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23074
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fast-MIA: Efficient and Scalable Membership Inference for LLMs
Takahashi, Hiromu
Ishihara, Shotaro
Cryptography and Security
Computation and Language
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 has emerged as a crucial technique for auditing privacy risks and copyright infringement in LLMs. However, computational demands have grown substantially: recent methods rely on repeated inference, while practical auditing requires large-scale evaluation. Progress is further hindered by existing implementations that execute methods independently, redundantly computing shared intermediate results such as log-probabilities. To address these challenges, Fast-MIA combines two strategies: (1) high-throughput batch inference via vLLM, achieving approximately 5$\times$ speedup, and (2) a cross-method caching architecture that computes intermediate results once and shares them across methods. The library includes representative MIA methods under a unified framework, integrates with established benchmarks, and supports flexible YAML configuration. We release Fast-MIA under the Apache License 2.0 to support scalable and reproducible MIA research.
title Fast-MIA: Efficient and Scalable Membership Inference for LLMs
topic Cryptography and Security
Computation and Language
url https://arxiv.org/abs/2510.23074