SOURCE-LINKED INTELLIGENCE

QuanText: Protecting Dataset-Level Secrets in Textual Data Sharing

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Natural-language datasets support many downstream applications and research studies, but releasing text can reveal sensitive global properties of the underlying data source, such as the proportion of records associated with a particular gender, diagnosis, or political stance. Existing work has largely focused on property inference attacks that recover such global properties, while defenses for protecting these dataset-level secrets remain limited. Differential privacy, although effective for protecting individual records, provides only weak protection for aggregate properties. We propose Rando

Read original source ↗ Open in workspace

recordType

paper

region

Global