<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2022-large">
    <titleInfo>
        <title>Are Large Pre-Trained Language Models Leaking Your Personal Information?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jie</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hanyin</namePart>
        <namePart type="family">Shao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="given">Chen-Chuan</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Are Large Pre-Trained Language Models Leaking Your Personal Information? In this paper, we analyze whether Pre-Trained Language Models (PLMs) are prone to leaking personal information. Specifically, we query PLMs for email addresses with contexts of the email address or prompts containing the owner’s name. We find that PLMs do leak personal information due to memorization. However, since the models are weak at association, the risk of specific personal information being extracted by attackers is low. We hope this work could help the community to better understand the privacy risk of PLMs and bring new insights to make PLMs safe.</abstract>
    <identifier type="citekey">huang-etal-2022-large</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.148</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.148</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>2038</start>
            <end>2047</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Are Large Pre-Trained Language Models Leaking Your Personal Information?
%A Huang, Jie
%A Shao, Hanyin
%A Chang, Kevin Chen-Chuan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F huang-etal-2022-large
%X Are Large Pre-Trained Language Models Leaking Your Personal Information? In this paper, we analyze whether Pre-Trained Language Models (PLMs) are prone to leaking personal information. Specifically, we query PLMs for email addresses with contexts of the email address or prompts containing the owner’s name. We find that PLMs do leak personal information due to memorization. However, since the models are weak at association, the risk of specific personal information being extracted by attackers is low. We hope this work could help the community to better understand the privacy risk of PLMs and bring new insights to make PLMs safe.
%R 10.18653/v1/2022.findings-emnlp.148
%U https://aclanthology.org/2022.findings-emnlp.148
%U https://doi.org/10.18653/v1/2022.findings-emnlp.148
%P 2038-2047

Markdown (Informal)

[Are Large Pre-Trained Language Models Leaking Your Personal Information?](https://aclanthology.org/2022.findings-emnlp.148) (Huang et al., Findings 2022)

• Are Large Pre-Trained Language Models Leaking Your Personal Information? (Huang et al., Findings 2022)

ACL

• Jie Huang, Hanyin Shao, and Kevin Chen-Chuan Chang. 2022. Are Large Pre-Trained Language Models Leaking Your Personal Information?. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2038–2047, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.