CLJun 30, 2024

DP-MLM: Differentially Private Text Rewriting Using Masked Language Models

arXiv:2407.00637v137 citationsHas Code
Originality Incremental advance
AI Analysis

This addresses privacy concerns in text data processing, offering a more efficient and customizable approach for applications like secure data sharing, though it is incremental in improving existing text rewriting techniques.

The paper tackles the problem of text privatization via differential privacy by proposing DP-MLM, a method using masked language models for text rewriting, which achieves better utility preservation at lower privacy levels compared to previous autoregressive methods.

The task of text privatization using Differential Privacy has recently taken the form of $\textit{text rewriting}$, in which an input text is obfuscated via the use of generative (large) language models. While these methods have shown promising results in the ability to preserve privacy, these methods rely on autoregressive models which lack a mechanism to contextualize the private rewriting process. In response to this, we propose $\textbf{DP-MLM}$, a new method for differentially private text rewriting based on leveraging masked language models (MLMs) to rewrite text in a semantically similar $\textit{and}$ obfuscated manner. We accomplish this with a simple contextualization technique, whereby we rewrite a text one token at a time. We find that utilizing encoder-only MLMs provides better utility preservation at lower $\varepsilon$ levels, as compared to previous methods relying on larger models with a decoder. In addition, MLMs allow for greater customization of the rewriting mechanism, as opposed to generative approaches. We make the code for $\textbf{DP-MLM}$ public and reusable, found at https://github.com/sjmeis/DPMLM .

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes