By combining task-aware importance scoring with privacy sensitivity detection, STAMP achieves better privacy-utility trade-offs than uniform noise approaches—meaning you can protect sensitive data without sacrificing model performance.
STAMP is a privacy framework that protects sensitive information in text while keeping it useful for AI tasks. It smartly decides which parts of text need more protection (like names and dates) versus which parts are less sensitive, then applies targeted noise to embeddings using a novel 'polar mechanism' that preserves semantic meaning better than traditional approaches.