<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-dim">
    <titleInfo>
        <title>Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhiyuan</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qi</namePart>
        <namePart type="family">Su</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xu</namePart>
        <namePart type="family">Sun</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>Despite the potential of federated learning, it is known to be vulnerable to backdoor attacks. Many robust federated aggregation methods are proposed to reduce the potential backdoor risk. However, they are mainly validated in the CV field. In this paper, we find that NLP backdoors are hard to defend against than CV, and we provide a theoretical analysis that the malicious update detection error probabilities are determined by the relative backdoor strengths. NLP attacks tend to have small relative backdoor strengths, which may result in the failure of robust federated aggregation methods for NLP attacks. Inspired by the theoretical results, we can choose some dimensions with higher backdoor strengths to settle this issue. We propose a novel federated aggregation algorithm, Dim-Krum, for NLP tasks, and experimental results validate its effectiveness.</abstract>
    <identifier type="citekey">zhang-etal-2022-dim</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.25</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.25</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>339</start>
            <end>354</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation
%A Zhang, Zhiyuan
%A Su, Qi
%A Sun, Xu
%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 zhang-etal-2022-dim
%X Despite the potential of federated learning, it is known to be vulnerable to backdoor attacks. Many robust federated aggregation methods are proposed to reduce the potential backdoor risk. However, they are mainly validated in the CV field. In this paper, we find that NLP backdoors are hard to defend against than CV, and we provide a theoretical analysis that the malicious update detection error probabilities are determined by the relative backdoor strengths. NLP attacks tend to have small relative backdoor strengths, which may result in the failure of robust federated aggregation methods for NLP attacks. Inspired by the theoretical results, we can choose some dimensions with higher backdoor strengths to settle this issue. We propose a novel federated aggregation algorithm, Dim-Krum, for NLP tasks, and experimental results validate its effectiveness.
%R 10.18653/v1/2022.findings-emnlp.25
%U https://aclanthology.org/2022.findings-emnlp.25
%U https://doi.org/10.18653/v1/2022.findings-emnlp.25
%P 339-354

Markdown (Informal)

[Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation](https://aclanthology.org/2022.findings-emnlp.25) (Zhang et al., Findings 2022)

• Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation (Zhang et al., Findings 2022)

ACL

• Zhiyuan Zhang, Qi Su, and Xu Sun. 2022. Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 339–354, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.