{"ID":2849507,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.23074","arxiv_id":"2510.23074","title":"Fast-MIA: Efficient and Scalable Membership Inference for LLMs","abstract":"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.","short_abstract":"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 s...","url_abs":"https://arxiv.org/abs/2510.23074","url_pdf":"https://arxiv.org/pdf/2510.23074v2","authors":"[\"Hiromu Takahashi\",\"Shotaro Ishihara\"]","published":"2025-10-27T07:18:32Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":607709,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2849507,"paper_url":"https://arxiv.org/abs/2510.23074","paper_title":"Fast-MIA: Efficient and Scalable Membership Inference for LLMs","repo_url":"https://github.com/Nikkei/fast-mia","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}