<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2026-guardrailagent">
    <titleInfo>
        <title>GuardrailAgent: An Agentic Framework for Jailbreak Defense</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tianze</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junjie</namePart>
        <namePart type="family">Chu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yixin</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Backes</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Zhang</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Despite undergoing safety training to align with human values, large language models (LLMs) remain vulnerable to jailbreak attacks that circumvent built-in safeguards and elicit malicious behaviors given by the adversary. Existing defenses are mostly static and fail to adapt to new or unknown attack strategies, providing limited resilience. To address these, we propose a multi-agent defense framework, GuardrailAgent, that offers adaptive, end-to-end protection. The system autonomously gathers and summarizes attack characteristics into a continuously updated knowledge base that supports both input- and output-side detection. A feedback module integrates misclassified cases for iterative improvement at minimal cost. Tested on over ten representative jailbreaks, the framework achieved a 93.1% input-side detection rate, 93.9% overall detection, and a 94.7% F1 score, while rapidly adapting to unseen attacks. These results demonstrate GuardrailAgent’s outstanding capability to maintain LLM safety in the face of evolving jailbreak tactics.</abstract>
    <identifier type="citekey">chang-etal-2026-guardrailagent</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.70/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1412</start>
            <end>1428</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T GuardrailAgent: An Agentic Framework for Jailbreak Defense
%A Chang, Tianze
%A Chu, Junjie
%A Wu, Yixin
%A Backes, Michael
%A Zhang, Yang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F chang-etal-2026-guardrailagent
%X Despite undergoing safety training to align with human values, large language models (LLMs) remain vulnerable to jailbreak attacks that circumvent built-in safeguards and elicit malicious behaviors given by the adversary. Existing defenses are mostly static and fail to adapt to new or unknown attack strategies, providing limited resilience. To address these, we propose a multi-agent defense framework, GuardrailAgent, that offers adaptive, end-to-end protection. The system autonomously gathers and summarizes attack characteristics into a continuously updated knowledge base that supports both input- and output-side detection. A feedback module integrates misclassified cases for iterative improvement at minimal cost. Tested on over ten representative jailbreaks, the framework achieved a 93.1% input-side detection rate, 93.9% overall detection, and a 94.7% F1 score, while rapidly adapting to unseen attacks. These results demonstrate GuardrailAgent’s outstanding capability to maintain LLM safety in the face of evolving jailbreak tactics.
%U https://aclanthology.org/2026.findings-emnlp.70/
%P 1412-1428

Markdown (Informal)

[GuardrailAgent: An Agentic Framework for Jailbreak Defense](https://aclanthology.org/2026.findings-emnlp.70/) (Chang et al., Findings 2026)

• GuardrailAgent: An Agentic Framework for Jailbreak Defense (Chang et al., Findings 2026)

ACL

• Tianze Chang, Junjie Chu, Yixin Wu, Michael Backes, and Yang Zhang. 2026. GuardrailAgent: An Agentic Framework for Jailbreak Defense. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 1412–1428, Budapest, Hungary. Association for Computational Linguistics.