SOURCE-LINKED INTELLIGENCE

Privacy Protection and Auditing for Foundation Models

CORDIS · observation · Publication date unknown

and Stable Diffusion are achieving exceptional performance across diverse tasks, generating high-quality text, images, and audio, and driving industry innovations. This progress stems from a shift in machine learning paradigm: instead of training task-specific models on curated datasets, FMs are first pretrained on vast, uncurated data to become strong general-purpose models, then adapted on smaller, domain-specific datasets for specific tasks. However, FMs leak information from their training data. For example, recent studies reveal that they can re-create individual data points from their pretraining and adaptation datasets. This poses serious privacy risks when private data is involved. Preventing exposure requires developing methods to ensure privacy-preservation throughout FMs' lifecycle, from pretraining to deployment. To achieve this, our project will identify sources of privacy leakage, provide privacy guarantees over both pretraining and adaptation, and audit FMs to detect privacy violations. Therefore, we must overcome three major challenges: the limited understanding of p

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

1499973

unit

EUR