<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raina-gales-2023-sample">
    <titleInfo>
        <title>Sample Attackability in Natural Language Adversarial Attacks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vyas</namePart>
        <namePart type="family">Raina</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mark</namePart>
        <namePart type="family">Gales</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>Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anaelia</namePart>
            <namePart type="family">Ovalle</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kai-Wei</namePart>
            <namePart type="family">Chang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ninareh</namePart>
            <namePart type="family">Mehrabi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yada</namePart>
            <namePart type="family">Pruksachatkun</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aram</namePart>
            <namePart type="family">Galystan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jwala</namePart>
            <namePart type="family">Dhamala</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Apurv</namePart>
            <namePart type="family">Verma</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Trista</namePart>
            <namePart type="family">Cao</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Anoop</namePart>
            <namePart type="family">Kumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rahul</namePart>
            <namePart type="family">Gupta</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>Adversarial attack research in natural language processing (NLP) has made significant progress in designing powerful attack methods and defence approaches. However, few efforts have sought to identify which source samples are the most attackable or robust, i.e. can we determine for an unseen target model, which samples are the most vulnerable to an adversarial attack. This work formally extends the definition of sample attackability/robustness for NLP attacks. Experiments on two popular NLP datasets, four state of the art models and four different NLP adversarial attack methods, demonstrate that sample uncertainty is insufficient for describing characteristics of attackable/robust samples and hence a deep learning based detector can perform much better at identifying the most attackable and robust samples for an unseen target model. Nevertheless, further analysis finds that there is little agreement in which samples are considered the most attackable/robust across different NLP attack methods, explaining a lack of portability of attackability detection methods across attack methods.</abstract>
    <identifier type="citekey">raina-gales-2023-sample</identifier>
    <identifier type="doi">10.18653/v1/2023.trustnlp-1.9</identifier>
    <location>
        <url>https://aclanthology.org/2023.trustnlp-1.9</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>96</start>
            <end>107</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sample Attackability in Natural Language Adversarial Attacks
%A Raina, Vyas
%A Gales, Mark
%Y Ovalle, Anaelia
%Y Chang, Kai-Wei
%Y Mehrabi, Ninareh
%Y Pruksachatkun, Yada
%Y Galystan, Aram
%Y Dhamala, Jwala
%Y Verma, Apurv
%Y Cao, Trista
%Y Kumar, Anoop
%Y Gupta, Rahul
%S Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F raina-gales-2023-sample
%X Adversarial attack research in natural language processing (NLP) has made significant progress in designing powerful attack methods and defence approaches. However, few efforts have sought to identify which source samples are the most attackable or robust, i.e. can we determine for an unseen target model, which samples are the most vulnerable to an adversarial attack. This work formally extends the definition of sample attackability/robustness for NLP attacks. Experiments on two popular NLP datasets, four state of the art models and four different NLP adversarial attack methods, demonstrate that sample uncertainty is insufficient for describing characteristics of attackable/robust samples and hence a deep learning based detector can perform much better at identifying the most attackable and robust samples for an unseen target model. Nevertheless, further analysis finds that there is little agreement in which samples are considered the most attackable/robust across different NLP attack methods, explaining a lack of portability of attackability detection methods across attack methods.
%R 10.18653/v1/2023.trustnlp-1.9
%U https://aclanthology.org/2023.trustnlp-1.9
%U https://doi.org/10.18653/v1/2023.trustnlp-1.9
%P 96-107

Markdown (Informal)

[Sample Attackability in Natural Language Adversarial Attacks](https://aclanthology.org/2023.trustnlp-1.9) (Raina & Gales, TrustNLP 2023)

• Sample Attackability in Natural Language Adversarial Attacks (Raina & Gales, TrustNLP 2023)

ACL

• Vyas Raina and Mark Gales. 2023. Sample Attackability in Natural Language Adversarial Attacks. In Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023), pages 96–107, Toronto, Canada. Association for Computational Linguistics.