Feb. 13, 2024, 5:45 a.m. | Diana M. Negoescu Humberto Gonzalez Saad Eddin Al Orjany Jilei Yang Yuliia Lut Rahul Tandra Xiaowen Zh

cs.LG updates on arXiv.org arxiv.org

We introduce Epsilon*, a new privacy metric for measuring the privacy risk of a single model instance prior to, during, or after deployment of privacy mitigation strategies. The metric requires only black-box access to model predictions, does not require training data re-sampling or model re-training, and can be used to measure the privacy risk of models not trained with differential privacy. Epsilon* is a function of true positive and false positive rates in a hypothesis test used by an adversary …

box cs.cr cs.ds cs.lg data deployment instance machine machine learning machine learning models measuring predictions prior privacy risk sampling strategies training training data

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