<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mozes-etal-2022-identifying">
    <titleInfo>
        <title>Identifying Human Strategies for Generating Word-Level Adversarial Examples</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maximilian</namePart>
        <namePart type="family">Mozes</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bennett</namePart>
        <namePart type="family">Kleinberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lewis</namePart>
        <namePart type="family">Griffin</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>Adversarial examples in NLP are receiving increasing research attention. One line of investigation is the generation of word-level adversarial examples against fine-tuned Transformer models that preserve naturalness and grammaticality. Previous work found that human- and machine-generated adversarial examples are comparable in their naturalness and grammatical correctness. Most notably, humans were able to generate adversarial examples much more effortlessly than automated attacks. In this paper, we provide a detailed analysis of exactly how humans create these adversarial examples. By exploring the behavioural patterns of human workers during the generation process, we identify statistically significant tendencies based on which words humans prefer to select for adversarial replacement (e.g., word frequencies, word saliencies, sentiment) as well as where and when words are replaced in an input sequence. With our findings, we seek to inspire efforts that harness human strategies for more robust NLP models.</abstract>
    <identifier type="citekey">mozes-etal-2022-identifying</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.454</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.454</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>6118</start>
            <end>6126</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Identifying Human Strategies for Generating Word-Level Adversarial Examples
%A Mozes, Maximilian
%A Kleinberg, Bennett
%A Griffin, Lewis
%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 mozes-etal-2022-identifying
%X Adversarial examples in NLP are receiving increasing research attention. One line of investigation is the generation of word-level adversarial examples against fine-tuned Transformer models that preserve naturalness and grammaticality. Previous work found that human- and machine-generated adversarial examples are comparable in their naturalness and grammatical correctness. Most notably, humans were able to generate adversarial examples much more effortlessly than automated attacks. In this paper, we provide a detailed analysis of exactly how humans create these adversarial examples. By exploring the behavioural patterns of human workers during the generation process, we identify statistically significant tendencies based on which words humans prefer to select for adversarial replacement (e.g., word frequencies, word saliencies, sentiment) as well as where and when words are replaced in an input sequence. With our findings, we seek to inspire efforts that harness human strategies for more robust NLP models.
%R 10.18653/v1/2022.findings-emnlp.454
%U https://aclanthology.org/2022.findings-emnlp.454
%U https://doi.org/10.18653/v1/2022.findings-emnlp.454
%P 6118-6126

Markdown (Informal)

[Identifying Human Strategies for Generating Word-Level Adversarial Examples](https://aclanthology.org/2022.findings-emnlp.454) (Mozes et al., Findings 2022)

• Identifying Human Strategies for Generating Word-Level Adversarial Examples (Mozes et al., Findings 2022)

ACL

• Maximilian Mozes, Bennett Kleinberg, and Lewis Griffin. 2022. Identifying Human Strategies for Generating Word-Level Adversarial Examples. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6118–6126, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.