REVIEW 3 cited by
Differentially Private Language Models for Secure Data Sharing
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the field of NLP, substantial efforts have been directed at building mechanisms following the framework of local differential privacy, thereby anonymizing individual text samples before releasing them. In practice, these approaches are often dissatisfying in terms of the quality of their output language due to the strong noise required for local differential privacy. In this paper, we approach the problem at hand using global differential privacy, particularly by training a generative language model in a differentially private manner and consequently sampling data from it. Using natural language prompts and a new prompt-mismatch loss, we are able to create highly accurate and fluent textual datasets taking on specific desired attributes such as sentiment or topic and resembling statistical properties of the training data. We perform thorough experiments indicating that our synthetic datasets do not leak information from our original data and are of high language quality and highly suitable for training models for further analysis on real-world data. Notably, we also demonstrate that training classifiers on private synthetic data outperforms directly training classifiers on real data with DP-SGD.
Forward citations
Cited by 3 Pith papers
-
Balancing Utility and Privacy: Dynamically Private SGD with Random Projection
D2P2-SGD combines time-decreasing privacy noise with random projection to improve the accuracy of differentially private SGD, with convergence rates matching ordinary SGD.
-
Improved Algorithms for Differentially Private Language Model Alignment
The central result is that DP-ADAMW/DP-ADAM outperform DP-SGD for private alignment, but the supporting evidence is internally inconsistent and the privacy analysis omits the number of gradient steps.
-
How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
A practical, extremely thorough survey of differentially private synthetic data generation: methods, privacy units, evaluation metrics, and end-to-end system components across four data modalities.
Discussion (0). Continue with ORCID to comment.