<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-hong-2021-reconstruction">
    <titleInfo>
        <title>Reconstruction Attack on Instance Encoding for Language Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shangyu</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuan</namePart>
        <namePart type="family">Hong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A private learning scheme TextHide was recently proposed to protect the private text data during the training phase via so-called instance encoding. We propose a novel reconstruction attack to break TextHide by recovering the private training data, and thus unveil the privacy risks of instance encoding. We have experimentally validated the effectiveness of the reconstruction attack with two commonly-used datasets for sentence classification. Our attack would advance the development of privacy preserving machine learning in the context of natural language processing.</abstract>
    <identifier type="citekey">xie-hong-2021-reconstruction</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.154</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.154</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>2038</start>
            <end>2044</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Reconstruction Attack on Instance Encoding for Language Understanding
%A Xie, Shangyu
%A Hong, Yuan
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F xie-hong-2021-reconstruction
%X A private learning scheme TextHide was recently proposed to protect the private text data during the training phase via so-called instance encoding. We propose a novel reconstruction attack to break TextHide by recovering the private training data, and thus unveil the privacy risks of instance encoding. We have experimentally validated the effectiveness of the reconstruction attack with two commonly-used datasets for sentence classification. Our attack would advance the development of privacy preserving machine learning in the context of natural language processing.
%R 10.18653/v1/2021.emnlp-main.154
%U https://aclanthology.org/2021.emnlp-main.154
%U https://doi.org/10.18653/v1/2021.emnlp-main.154
%P 2038-2044

Markdown (Informal)

[Reconstruction Attack on Instance Encoding for Language Understanding](https://aclanthology.org/2021.emnlp-main.154) (Xie & Hong, EMNLP 2021)

• Reconstruction Attack on Instance Encoding for Language Understanding (Xie & Hong, EMNLP 2021)

ACL

• Shangyu Xie and Yuan Hong. 2021. Reconstruction Attack on Instance Encoding for Language Understanding. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2038–2044, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.