<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-etal-2024-defending">
    <titleInfo>
        <title>Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bochuan</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuanpu</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lu</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinghui</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content. Though a line of research has focused on aligning LLMs with human values and preventing them from producing inappropriate content, such alignments are usually vulnerable and can be bypassed by alignment-breaking attacks via adversarially optimized or handcrafted jailbreaking prompts. In this work, we introduce a Robustly Aligned LLM (RA-LLM) to defend against potential alignment-breaking attacks. RA-LLM can be directly constructed upon an existing aligned LLM with a robust alignment checking function, without requiring any expensive retraining or fine-tuning process of the original LLM. Furthermore, we also provide a theoretical analysis for RA-LLM to verify its effectiveness in defending against alignment-breaking attacks. Through real-world experiments on open-source large language models, we demonstrate that RA-LLM can successfully defend against both state-of-the-art adversarial prompts and popular handcrafted jailbreaking prompts by reducing their attack success rates from nearly 100% to around 10% or less.</abstract>
    <identifier type="citekey">cao-etal-2024-defending</identifier>
    <location>
        <url>https://aclanthology.org/2024.acl-long.568</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>10542</start>
            <end>10560</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
%A Cao, Bochuan
%A Cao, Yuanpu
%A Lin, Lu
%A Chen, Jinghui
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F cao-etal-2024-defending
%X Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content. Though a line of research has focused on aligning LLMs with human values and preventing them from producing inappropriate content, such alignments are usually vulnerable and can be bypassed by alignment-breaking attacks via adversarially optimized or handcrafted jailbreaking prompts. In this work, we introduce a Robustly Aligned LLM (RA-LLM) to defend against potential alignment-breaking attacks. RA-LLM can be directly constructed upon an existing aligned LLM with a robust alignment checking function, without requiring any expensive retraining or fine-tuning process of the original LLM. Furthermore, we also provide a theoretical analysis for RA-LLM to verify its effectiveness in defending against alignment-breaking attacks. Through real-world experiments on open-source large language models, we demonstrate that RA-LLM can successfully defend against both state-of-the-art adversarial prompts and popular handcrafted jailbreaking prompts by reducing their attack success rates from nearly 100% to around 10% or less.
%U https://aclanthology.org/2024.acl-long.568
%P 10542-10560

Markdown (Informal)

[Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM](https://aclanthology.org/2024.acl-long.568) (Cao et al., ACL 2024)

• Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM (Cao et al., ACL 2024)

ACL

• Bochuan Cao, Yuanpu Cao, Lu Lin, and Jinghui Chen. 2024. Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10542–10560, Bangkok, Thailand. Association for Computational Linguistics.