Feb. 13, 2024, 5:49 a.m. | Michael Duan Anshuman Suri Niloofar Mireshghallah Sewon Min Weijia Shi Luke Zettlemoyer Yulia Tsvetkov

cs.CL updates on arXiv.org arxiv.org

Membership inference attacks (MIAs) attempt to predict whether a particular datapoint is a member of a target model's training data. Despite extensive research on traditional machine learning models, there has been limited work studying MIA on the pre-training data of large language models (LLMs). We perform a large-scale evaluation of MIAs over a suite of language models (LMs) trained on the Pile, ranging from 160M to 12B parameters. We find that MIAs barely outperform random guessing for most settings across …

attacks cs.cl data evaluation inference language language models large language large language models llms machine machine learning machine learning models pre-training research scale studying traditional machine learning training training data work

Doctoral Researcher (m/f/div) in Automated Processing of Bioimages

@ Leibniz Institute for Natural Product Research and Infection Biology (Leibniz-HKI) | Jena

Research Scholar (Technical Research)

@ Centre for the Governance of AI | Hybrid; Oxford, UK

HPC Engineer (x/f/m) - DACH

@ Meshcapade GmbH | Remote, Germany

ETL Developer

@ Gainwell Technologies | Bengaluru, KA, IN, 560100

Medical Radiation Technologist, Breast Imaging

@ University Health Network | Toronto, ON, Canada

Data Scientist

@ PayPal | USA - Texas - Austin - Corp - Alterra Pkwy