快速评估大模型隐私风险，提升成员推理攻击效率五倍。
Fast-MIA: Efficient and Scalable Membership Inference for LLMs
- 用vLLM实现批量高速推理，提速约5倍。
- 共享中间结果缓存，避免重复计算日志概率。
- 支持多种攻击方法与基准测试，可灵活配置。
我们提出Fast-MIA（https://github.com/Nikkei/fast-mia），一个用于高效评估大语言模型（LLMs）成员推理攻击（MIA）的Python库。MIA已成为审计LLM隐私风险与版权侵权的关键技术。然而，计算需求大幅增加：现有方法依赖反复推理，实际审计需大规模评估。同时，现有实现各自独立运行，重复计算共享的中间结果（如对数概率），造成资源浪费。为应对挑战，Fast-MIA结合两种策略：(1) 借助vLLM实现高吞吐批量推理，实现约5×加速；(2) 采用跨方法缓存架构，仅计算一次中间结果并共享使用。该库在统一框架下集成代表性MIA方法，兼容主流基准测试，支持灵活YAML配置。Fast-MIA以Apache License 2.0开源，旨在推动可扩展、可复现的MIA研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。