<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-enhancing-byzantine">
    <titleInfo>
        <title>Enhancing Byzantine-Resistant Aggregations with Client Embedding</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">Hao</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fandong</namePart>
        <namePart type="family">Meng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jie</namePart>
        <namePart type="family">Zhou</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>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2024</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>Byzantine-resistant aggregations detect poisonous clients and discard them to ensure that the global model is not poisoned or attacked by malicious clients. However, these aggregations are mainly conducted on the parameter space, and the parameter distances cannot reflect the data distribution divergences between clients. Therefore, existing Byzantine-resistant aggregations cannot defend against backdoor injection by malicious attackers in federated natural language tasks. In this paper, we propose the client embedding for malicious client detection to enhance Byzantine-resistant aggregations. The distances between client embeddings are required to reflect the data distribution divergences of the corresponding clients. Experimental results validate the effectiveness of the proposed client embeddings.</abstract>
    <identifier type="citekey">zhang-etal-2024-enhancing-byzantine</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-emnlp.339</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.339</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>5889</start>
            <end>5896</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enhancing Byzantine-Resistant Aggregations with Client Embedding
%A Zhang, Zhiyuan
%A Zhou, Hao
%A Meng, Fandong
%A Zhou, Jie
%A Sun, Xu
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F zhang-etal-2024-enhancing-byzantine
%X Byzantine-resistant aggregations detect poisonous clients and discard them to ensure that the global model is not poisoned or attacked by malicious clients. However, these aggregations are mainly conducted on the parameter space, and the parameter distances cannot reflect the data distribution divergences between clients. Therefore, existing Byzantine-resistant aggregations cannot defend against backdoor injection by malicious attackers in federated natural language tasks. In this paper, we propose the client embedding for malicious client detection to enhance Byzantine-resistant aggregations. The distances between client embeddings are required to reflect the data distribution divergences of the corresponding clients. Experimental results validate the effectiveness of the proposed client embeddings.
%R 10.18653/v1/2024.findings-emnlp.339
%U https://aclanthology.org/2024.findings-emnlp.339
%U https://doi.org/10.18653/v1/2024.findings-emnlp.339
%P 5889-5896

Markdown (Informal)

[Enhancing Byzantine-Resistant Aggregations with Client Embedding](https://aclanthology.org/2024.findings-emnlp.339) (Zhang et al., Findings 2024)

• Enhancing Byzantine-Resistant Aggregations with Client Embedding (Zhang et al., Findings 2024)

ACL

• Zhiyuan Zhang, Hao Zhou, Fandong Meng, Jie Zhou, and Xu Sun. 2024. Enhancing Byzantine-Resistant Aggregations with Client Embedding. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5889–5896, Miami, Florida, USA. Association for Computational Linguistics.