paper-with-me

홈 › Papers

Fast-MIA: Efficient and Scalable Membership Inference for LLMs

2025-10-27 · Hiromu Takahashi, Shotaro Ishihara arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.23074

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Scalable MCMC for Mixed Membership Stochastic Blockmodels

2015-10-16 · Wenzhe Li, Sungjin Ahn, Max Welling

We propose a stochastic gradient Markov chain Monte Carlo (SG-MCMC) algorithm for scalable inference in mixed-membership stochastic blockmodels (MMSB). Our algorithm is based on the stochastic gradient Riemannian Langevi…

Variational Inference

Scalable Inference of Overlapping Communities

2012-12-01 · NeurIPS 2012 12 · Prem K. Gopalan, Sean Gerrish, Michael Freedman, David M. Blei 외

We develop a scalable algorithm for posterior inference of overlapping communities in large networks. Our algorithm is based on stochastic variational inference in the mixed-membership stochastic blockmodel. It naturall…

Variational Inference

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks

2025-06-12 · Kaiyuan Zhang, Siyuan Cheng, Hanxi Guo, Yuetian Chen 외

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy c…

(Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs

2025-10-07 · Jiashu Tao, Reza Shokri arxiv

Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, whi…

Computational Efficiency

Has My System Prompt Been Used? Large Language Model Prompt Membership Inference

2025-02-14 · Roman Levin, Valeriia Cherepanova, Abhimanyu Hans, Avi Schwarzschild 외

Prompt engineering has emerged as a powerful technique for optimizing large language models (LLMs) for specific applications, enabling faster prototyping and improved performance, and giving rise to the interest of the c…

Language ModelingLanguage ModellingLarge Language ModelPrompt Engineering