<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-da3">
    <titleInfo>
        <title>DA³: A Distribution-Aware Adversarial Attack against Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yibo</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiangjue</namePart>
        <namePart type="family">Dong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">James</namePart>
        <namePart type="family">Caverlee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Philip</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Language models can be manipulated by adversarial attacks, which introduce subtle perturbations to input data. While recent attack methods can achieve a relatively high attack success rate (ASR), we’ve observed that the generated adversarial examples have a different data distribution compared with the original examples. Specifically, these adversarial examples exhibit reduced confidence levels and greater divergence from the training data distribution. Consequently, they are easy to detect using straightforward detection methods, diminishing the efficacy of such attacks. To address this issue, we propose a Distribution-Aware Adversarial Attack (DA³) method. DA³ considers the distribution shifts of adversarial examples to improve attacks’ effectiveness under detection methods. We further design a novel evaluation metric, the Non-detectable Attack Success Rate (NASR), which integrates both ASR and detectability for the attack task. We conduct experiments on four widely used datasets to validate the attack effectiveness and transferability of adversarial examples generated by DA³ against both the white-box BERT-base and RoBERTa-base models and the black-box LLaMA2-7b model.</abstract>
    <identifier type="citekey">wang-etal-2024-da3</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.107</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>1808</start>
            <end>1825</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DA³: A Distribution-Aware Adversarial Attack against Language Models
%A Wang, Yibo
%A Dong, Xiangjue
%A Caverlee, James
%A Yu, Philip
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F wang-etal-2024-da3
%X Language models can be manipulated by adversarial attacks, which introduce subtle perturbations to input data. While recent attack methods can achieve a relatively high attack success rate (ASR), we’ve observed that the generated adversarial examples have a different data distribution compared with the original examples. Specifically, these adversarial examples exhibit reduced confidence levels and greater divergence from the training data distribution. Consequently, they are easy to detect using straightforward detection methods, diminishing the efficacy of such attacks. To address this issue, we propose a Distribution-Aware Adversarial Attack (DA³) method. DA³ considers the distribution shifts of adversarial examples to improve attacks’ effectiveness under detection methods. We further design a novel evaluation metric, the Non-detectable Attack Success Rate (NASR), which integrates both ASR and detectability for the attack task. We conduct experiments on four widely used datasets to validate the attack effectiveness and transferability of adversarial examples generated by DA³ against both the white-box BERT-base and RoBERTa-base models and the black-box LLaMA2-7b model.
%U https://aclanthology.org/2024.emnlp-main.107
%P 1808-1825

Markdown (Informal)

[DA3: A Distribution-Aware Adversarial Attack against Language Models](https://aclanthology.org/2024.emnlp-main.107) (Wang et al., EMNLP 2024)

• DA3: A Distribution-Aware Adversarial Attack against Language Models (Wang et al., EMNLP 2024)

ACL

• Yibo Wang, Xiangjue Dong, James Caverlee, and Philip Yu. 2024. DA3: A Distribution-Aware Adversarial Attack against Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1808–1825, Miami, Florida, USA. Association for Computational Linguistics.