@inproceedings{meisenbacher-etal-2024-dp,
title = "{DP}-{MLM}: Differentially Private Text Rewriting Using Masked Language Models",
author = "Meisenbacher, Stephen and
Chevli, Maulik and
Vladika, Juraj and
Matthes, Florian",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.554",
pages = "9314--9328",
abstract = "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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meisenbacher-etal-2024-dp">
<titleInfo>
<title>DP-MLM: Differentially Private Text Rewriting Using Masked Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Meisenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maulik</namePart>
<namePart type="family">Chevli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juraj</namePart>
<namePart type="family">Vladika</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Matthes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of text privatization using Differential Privacy has recently taken the form of 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 DP-MLM, a new method for differentially private text rewriting based on leveraging masked language models (MLMs) to rewrite text in a semantically similar 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 ǎrepsilon 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 DP-MLM public and reusable, found at https://github.com/sjmeis/DPMLM.</abstract>
<identifier type="citekey">meisenbacher-etal-2024-dp</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.554</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>9314</start>
<end>9328</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DP-MLM: Differentially Private Text Rewriting Using Masked Language Models
%A Meisenbacher, Stephen
%A Chevli, Maulik
%A Vladika, Juraj
%A Matthes, Florian
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F meisenbacher-etal-2024-dp
%X The task of text privatization using Differential Privacy has recently taken the form of 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 DP-MLM, a new method for differentially private text rewriting based on leveraging masked language models (MLMs) to rewrite text in a semantically similar 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 ǎrepsilon 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 DP-MLM public and reusable, found at https://github.com/sjmeis/DPMLM.
%U https://aclanthology.org/2024.findings-acl.554
%P 9314-9328
Markdown (Informal)
[DP-MLM: Differentially Private Text Rewriting Using Masked Language Models](https://aclanthology.org/2024.findings-acl.554) (Meisenbacher et al., Findings 2024)
ACL