@inproceedings{dang-etal-2026-rainbowplus,
title = "{R}ainbow{P}lus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search",
author = "Dang, Quy-Anh and
Ngo, Chris and
Hy, Truong-Son",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.70/",
pages = "1179--1208",
ISBN = "979-8-89176-460-6",
abstract = "Large Language Models (LLMs) remain vulnerable to adversarial prompts that exploit safety mechanisms. Existing red-teaming methods face scalability challenges, computational bottlenecks, or limited attack diversity. We propose , a framework that reconceptualizes adversarial prompt generation as evolutionary quality-diversity search, where diverse attack strategies co-evolve across behavioral niches. introduces two synergistic innovations: (1) \textit{multi-element archives} that maintain populations of elite solutions per niche, and (2) \textit{parallel fitness evaluation} that replaces pairwise comparisons with efficient probabilistic scoring, achieving $\Theta(M)$ speedup (from $\Theta(M^2N)$ to $\Theta(MN)$). Experiments demonstrate superior performance: compared to Rainbow Teaming, generates $100\times$ more prompts (10,418 vs. 100) with higher attack success rates. Against nine state-of-the-art methods on HarmBench with 12 LLMs, achieves 81.1{\%} average ASR - surpassing AutoDAN-Turbo by 3.9 points - while being $9\times$ faster (1.45 vs. 13.50 hours). Code: https://github.com/knoveleng/rainbowplus"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dang-etal-2026-rainbowplus">
<titleInfo>
<title>RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quy-Anh</namePart>
<namePart type="family">Dang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Ngo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Truong-Son</namePart>
<namePart type="family">Hy</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: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) remain vulnerable to adversarial prompts that exploit safety mechanisms. Existing red-teaming methods face scalability challenges, computational bottlenecks, or limited attack diversity. We propose , a framework that reconceptualizes adversarial prompt generation as evolutionary quality-diversity search, where diverse attack strategies co-evolve across behavioral niches. introduces two synergistic innovations: (1) multi-element archives that maintain populations of elite solutions per niche, and (2) parallel fitness evaluation that replaces pairwise comparisons with efficient probabilistic scoring, achieving Θ(M) speedup (from Θ(M²N) to Θ(MN)). Experiments demonstrate superior performance: compared to Rainbow Teaming, generates 100\times more prompts (10,418 vs. 100) with higher attack success rates. Against nine state-of-the-art methods on HarmBench with 12 LLMs, achieves 81.1% average ASR - surpassing AutoDAN-Turbo by 3.9 points - while being 9\times faster (1.45 vs. 13.50 hours). Code: https://github.com/knoveleng/rainbowplus</abstract>
<identifier type="citekey">dang-etal-2026-rainbowplus</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.70/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1179</start>
<end>1208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search
%A Dang, Quy-Anh
%A Ngo, Chris
%A Hy, Truong-Son
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F dang-etal-2026-rainbowplus
%X Large Language Models (LLMs) remain vulnerable to adversarial prompts that exploit safety mechanisms. Existing red-teaming methods face scalability challenges, computational bottlenecks, or limited attack diversity. We propose , a framework that reconceptualizes adversarial prompt generation as evolutionary quality-diversity search, where diverse attack strategies co-evolve across behavioral niches. introduces two synergistic innovations: (1) multi-element archives that maintain populations of elite solutions per niche, and (2) parallel fitness evaluation that replaces pairwise comparisons with efficient probabilistic scoring, achieving Θ(M) speedup (from Θ(M²N) to Θ(MN)). Experiments demonstrate superior performance: compared to Rainbow Teaming, generates 100\times more prompts (10,418 vs. 100) with higher attack success rates. Against nine state-of-the-art methods on HarmBench with 12 LLMs, achieves 81.1% average ASR - surpassing AutoDAN-Turbo by 3.9 points - while being 9\times faster (1.45 vs. 13.50 hours). Code: https://github.com/knoveleng/rainbowplus
%U https://aclanthology.org/2026.emnlp-industry.70/
%P 1179-1208
Markdown (Informal)
[RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search](https://aclanthology.org/2026.emnlp-industry.70/) (Dang et al., EMNLP 2026)
ACL