<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-evading">
    <titleInfo>
        <title>Evading Fake News Detection: Self-evolving Social Manipulation via LLM-driven Agent Orchestration</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mengyang</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lingwei</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Songlin</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>While propagation-based fake news detection improves performance by modeling how news spreads, it remains vulnerable to adversarial social manipulation, where adversaries distort propagation patterns through malicious social interactions to evade detection. Existing attacks often target only one type of social behavior with predefined rules, making them vulnerable to robust defenses. To bridge this gap, we propose a new Self-evolving Social Manipulation framework (EvoSM) that utilizes Large Language Models (LLMs) to orchestrate evolutionary social manipulation campaigns for evading fake news detection. First, we design an LLM-driven Social Manipulation Orchestrator that uses a social graph interface to perceive the propagation environment, coordinate diverse manipulation actions, and refine attack strategies in context. Second, to further strengthen the manipulation capability, we introduce Reflective Experience Memory, which distills reusable manipulation insights from previous successful and failed attack attempts through reflection. Experiments on four real-world fake news datasets demonstrate that EvoSM consistently outperforms comparison baselines in attack success rates and transferability. Further analysis shows that EvoSM benefits from coordinated multi-behavior manipulation and experience-guided strategy evolution. Our study highlights the vulnerability of existing fake news detection systems to adaptive social manipulation.</abstract>
    <identifier type="citekey">chen-etal-2026-evading</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1083/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>24869</start>
            <end>24900</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Evading Fake News Detection: Self-evolving Social Manipulation via LLM-driven Agent Orchestration
%A Chen, Mengyang
%A Wei, Lingwei
%A Zhou, Wei
%A Hu, Songlin
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F chen-etal-2026-evading
%X While propagation-based fake news detection improves performance by modeling how news spreads, it remains vulnerable to adversarial social manipulation, where adversaries distort propagation patterns through malicious social interactions to evade detection. Existing attacks often target only one type of social behavior with predefined rules, making them vulnerable to robust defenses. To bridge this gap, we propose a new Self-evolving Social Manipulation framework (EvoSM) that utilizes Large Language Models (LLMs) to orchestrate evolutionary social manipulation campaigns for evading fake news detection. First, we design an LLM-driven Social Manipulation Orchestrator that uses a social graph interface to perceive the propagation environment, coordinate diverse manipulation actions, and refine attack strategies in context. Second, to further strengthen the manipulation capability, we introduce Reflective Experience Memory, which distills reusable manipulation insights from previous successful and failed attack attempts through reflection. Experiments on four real-world fake news datasets demonstrate that EvoSM consistently outperforms comparison baselines in attack success rates and transferability. Further analysis shows that EvoSM benefits from coordinated multi-behavior manipulation and experience-guided strategy evolution. Our study highlights the vulnerability of existing fake news detection systems to adaptive social manipulation.
%U https://aclanthology.org/2026.emnlp-main.1083/
%P 24869-24900

Markdown (Informal)

[Evading Fake News Detection: Self-evolving Social Manipulation via LLM-driven Agent Orchestration](https://aclanthology.org/2026.emnlp-main.1083/) (Chen et al., EMNLP 2026)

• Evading Fake News Detection: Self-evolving Social Manipulation via LLM-driven Agent Orchestration (Chen et al., EMNLP 2026)

ACL

• Mengyang Chen, Lingwei Wei, Wei Zhou, and Songlin Hu. 2026. Evading Fake News Detection: Self-evolving Social Manipulation via LLM-driven Agent Orchestration. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 24869–24900, Budapest, Hungary. Association for Computational Linguistics.