Distributed and Private Textual Data Synthesis from Embeddings
Researchers propose a distributed differentially private text synthesis method combining DP summaries and secure protocols, removing the need for a trusted curator.
The paper presents a differential privacy and cryptography co-design for synthesizing textual training data without a trusted curator or tightly synchronized user participation. It releases a one-time DP summary in embedding space, identifying frequent semantic regions and their DP centroids to enable training-free offline text synthesis, with semantic support protection to avoid exposing rare user texts. A custom secure protocol enforces end-to-end DP guarantees over distributed user data. Across four benchmarks the approach achieves utility comparable to the state-of-the-art centralized DP synthesis method.
- DP-cryptography co-design removes the trusted-curator assumption for distributed text synthesis
- Releases one-time DP embedding centroids, enabling training-free offline synthesis
- Semantic support protection keeps released summaries away from rare user texts
- Matches state-of-the-art centralized DP synthesis utility on four benchmarks
From the original article
1 min read at arxiv.orgWe revisit differentially private (DP) text synthesis in the realistic setting of distributed users, where privacy concerns preclude a trusted curator with access to raw user texts.
By Ergute Bao · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.