<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="igamberdiev-habernal-2023-dp">
    <titleInfo>
        <title>DP-BART for Privatized Text Rewriting under Local Differential Privacy</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Timour</namePart>
        <namePart type="family">Igamberdiev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Habernal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Privatized text rewriting with local differential privacy (LDP) is a recent approach that enables sharing of sensitive textual documents while formally guaranteeing privacy protection to individuals. However, existing systems face several issues, such as formal mathematical flaws, unrealistic privacy guarantees, privatization of only individual words, as well as a lack of transparency and reproducibility. In this paper, we propose a new system ‘DP-BART’ that largely outperforms existing LDP systems. Our approach uses a novel clipping method, iterative pruning, and further training of internal representations which drastically reduces the amount of noise required for DP guarantees. We run experiments on five textual datasets of varying sizes, rewriting them at different privacy guarantees and evaluating the rewritten texts on downstream text classification tasks. Finally, we thoroughly discuss the privatized text rewriting approach and its limitations, including the problem of the strict text adjacency constraint in the LDP paradigm that leads to the high noise requirement.</abstract>
    <identifier type="citekey">igamberdiev-habernal-2023-dp</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.874</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.874</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>13914</start>
            <end>13934</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DP-BART for Privatized Text Rewriting under Local Differential Privacy
%A Igamberdiev, Timour
%A Habernal, Ivan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F igamberdiev-habernal-2023-dp
%X Privatized text rewriting with local differential privacy (LDP) is a recent approach that enables sharing of sensitive textual documents while formally guaranteeing privacy protection to individuals. However, existing systems face several issues, such as formal mathematical flaws, unrealistic privacy guarantees, privatization of only individual words, as well as a lack of transparency and reproducibility. In this paper, we propose a new system ‘DP-BART’ that largely outperforms existing LDP systems. Our approach uses a novel clipping method, iterative pruning, and further training of internal representations which drastically reduces the amount of noise required for DP guarantees. We run experiments on five textual datasets of varying sizes, rewriting them at different privacy guarantees and evaluating the rewritten texts on downstream text classification tasks. Finally, we thoroughly discuss the privatized text rewriting approach and its limitations, including the problem of the strict text adjacency constraint in the LDP paradigm that leads to the high noise requirement.
%R 10.18653/v1/2023.findings-acl.874
%U https://aclanthology.org/2023.findings-acl.874
%U https://doi.org/10.18653/v1/2023.findings-acl.874
%P 13914-13934

Markdown (Informal)

[DP-BART for Privatized Text Rewriting under Local Differential Privacy](https://aclanthology.org/2023.findings-acl.874) (Igamberdiev & Habernal, Findings 2023)

• DP-BART for Privatized Text Rewriting under Local Differential Privacy (Igamberdiev & Habernal, Findings 2023)

ACL

• Timour Igamberdiev and Ivan Habernal. 2023. DP-BART for Privatized Text Rewriting under Local Differential Privacy. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13914–13934, Toronto, Canada. Association for Computational Linguistics.