<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishna-etal-2021-adept">
    <titleInfo>
        <title>ADePT: Auto-encoder based Differentially Private Text Transformation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Satyapriya</namePart>
        <namePart type="family">Krishna</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rahul</namePart>
        <namePart type="family">Gupta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christophe</namePart>
        <namePart type="family">Dupuy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Paola</namePart>
            <namePart type="family">Merlo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jorg</namePart>
            <namePart type="family">Tiedemann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Reut</namePart>
            <namePart type="family">Tsarfaty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns. Multiple solutions have been proposed for the differentially-private transformation of datasets containing sensitive information. However, such transformation algorithms offer poor utility in Natural Language Processing (NLP) tasks due to noise added in the process. This paper addresses this issue by providing a utility-preserving differentially private text transformation algorithm using auto-encoders. Our algorithm transforms text to offer robustness against attacks and produces transformations with high semantic quality that perform well on downstream NLP tasks. We prove our algorithm‘s theoretical privacy guarantee and assess its privacy leakage under Membership Inference Attacks (MIA) on models trained with transformed data. Our results show that the proposed model performs better against MIA attacks while offering lower to no degradation in the utility of the underlying transformation process compared to existing baselines.</abstract>
    <identifier type="citekey">krishna-etal-2021-adept</identifier>
    <identifier type="doi">10.18653/v1/2021.eacl-main.207</identifier>
    <location>
        <url>https://aclanthology.org/2021.eacl-main.207/</url>
    </location>
    <part>
        <date>2021-04</date>
        <extent unit="page">
            <start>2435</start>
            <end>2439</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ADePT: Auto-encoder based Differentially Private Text Transformation
%A Krishna, Satyapriya
%A Gupta, Rahul
%A Dupuy, Christophe
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F krishna-etal-2021-adept
%X Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns. Multiple solutions have been proposed for the differentially-private transformation of datasets containing sensitive information. However, such transformation algorithms offer poor utility in Natural Language Processing (NLP) tasks due to noise added in the process. This paper addresses this issue by providing a utility-preserving differentially private text transformation algorithm using auto-encoders. Our algorithm transforms text to offer robustness against attacks and produces transformations with high semantic quality that perform well on downstream NLP tasks. We prove our algorithm‘s theoretical privacy guarantee and assess its privacy leakage under Membership Inference Attacks (MIA) on models trained with transformed data. Our results show that the proposed model performs better against MIA attacks while offering lower to no degradation in the utility of the underlying transformation process compared to existing baselines.
%R 10.18653/v1/2021.eacl-main.207
%U https://aclanthology.org/2021.eacl-main.207/
%U https://doi.org/10.18653/v1/2021.eacl-main.207
%P 2435-2439

Markdown (Informal)

[ADePT: Auto-encoder based Differentially Private Text Transformation](https://aclanthology.org/2021.eacl-main.207/) (Krishna et al., EACL 2021)

• ADePT: Auto-encoder based Differentially Private Text Transformation (Krishna et al., EACL 2021)

ACL

• Satyapriya Krishna, Rahul Gupta, and Christophe Dupuy. 2021. ADePT: Auto-encoder based Differentially Private Text Transformation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2435–2439, Online. Association for Computational Linguistics.