<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-etal-2021-onion">
    <titleInfo>
        <title>ONION: A Simple and Effective Defense Against Textual Backdoor Attacks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Fanchao</namePart>
        <namePart type="family">Qi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yangyi</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mukai</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuan</namePart>
        <namePart type="family">Yao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhiyuan</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maosong</namePart>
        <namePart type="family">Sun</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>Backdoor attacks are a kind of emergent training-time threat to deep neural networks (DNNs). They can manipulate the output of DNNs and possess high insidiousness. In the field of natural language processing, some attack methods have been proposed and achieve very high attack success rates on multiple popular models. Nevertheless, there are few studies on defending against textual backdoor attacks. In this paper, we propose a simple and effective textual backdoor defense named ONION, which is based on outlier word detection and, to the best of our knowledge, is the first method that can handle all the textual backdoor attack situations. Experiments demonstrate the effectiveness of our model in defending BiLSTM and BERT against five different backdoor attacks. All the code and data of this paper can be obtained at https://github.com/thunlp/ONION.</abstract>
    <identifier type="citekey">qi-etal-2021-onion</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.752</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.752/</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>9558</start>
            <end>9566</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ONION: A Simple and Effective Defense Against Textual Backdoor Attacks
%A Qi, Fanchao
%A Chen, Yangyi
%A Li, Mukai
%A Yao, Yuan
%A Liu, Zhiyuan
%A Sun, Maosong
%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 qi-etal-2021-onion
%X Backdoor attacks are a kind of emergent training-time threat to deep neural networks (DNNs). They can manipulate the output of DNNs and possess high insidiousness. In the field of natural language processing, some attack methods have been proposed and achieve very high attack success rates on multiple popular models. Nevertheless, there are few studies on defending against textual backdoor attacks. In this paper, we propose a simple and effective textual backdoor defense named ONION, which is based on outlier word detection and, to the best of our knowledge, is the first method that can handle all the textual backdoor attack situations. Experiments demonstrate the effectiveness of our model in defending BiLSTM and BERT against five different backdoor attacks. All the code and data of this paper can be obtained at https://github.com/thunlp/ONION.
%R 10.18653/v1/2021.emnlp-main.752
%U https://aclanthology.org/2021.emnlp-main.752/
%U https://doi.org/10.18653/v1/2021.emnlp-main.752
%P 9558-9566

Markdown (Informal)

[ONION: A Simple and Effective Defense Against Textual Backdoor Attacks](https://aclanthology.org/2021.emnlp-main.752/) (Qi et al., EMNLP 2021)

• ONION: A Simple and Effective Defense Against Textual Backdoor Attacks (Qi et al., EMNLP 2021)

ACL

• Fanchao Qi, Yangyi Chen, Mukai Li, Yuan Yao, Zhiyuan Liu, and Maosong Sun. 2021. ONION: A Simple and Effective Defense Against Textual Backdoor Attacks. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9558–9566, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.