<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brack-etal-2023-distilling">
    <titleInfo>
        <title>Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Manuel</namePart>
        <namePart type="family">Brack</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Patrick</namePart>
        <namePart type="family">Schramowski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kristian</namePart>
        <namePart type="family">Kersting</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the ART of Safety: Workshop on Adversarial testing and Red-Teaming for generative AI</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Alicia</namePart>
            <namePart type="family">Parrish</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bali, Indonesia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <identifier type="citekey">brack-etal-2023-distilling</identifier>
    <identifier type="doi">10.18653/v1/2023.artofsafety-1.3</identifier>
    <location>
        <url>https://aclanthology.org/2023.artofsafety-1.3</url>
    </location>
    <part>
        <date>2023-11</date>
        <extent unit="page">
            <start>24</start>
            <end>28</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge
%A Brack, Manuel
%A Schramowski, Patrick
%A Kersting, Kristian
%Y Parrish, Alicia
%S Proceedings of the ART of Safety: Workshop on Adversarial testing and Red-Teaming for generative AI
%D 2023
%8 November
%I Association for Computational Linguistics
%C Bali, Indonesia
%F brack-etal-2023-distilling
%R 10.18653/v1/2023.artofsafety-1.3
%U https://aclanthology.org/2023.artofsafety-1.3
%U https://doi.org/10.18653/v1/2023.artofsafety-1.3
%P 24-28

Markdown (Informal)

[Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge](https://aclanthology.org/2023.artofsafety-1.3) (Brack et al., artofsafety-WS 2023)

• Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge (Brack et al., artofsafety-WS 2023)

ACL

• Manuel Brack, Patrick Schramowski, and Kristian Kersting. 2023. Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge. In Proceedings of the ART of Safety: Workshop on Adversarial testing and Red-Teaming for generative AI, pages 24–28, Bali, Indonesia. Association for Computational Linguistics.