Skip to content
conftrace_
2026 EMNLP EMNLP 2026

RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search

AbstractLarge 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× 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× faster (1.45 vs. 13.50 hours). Code: https://github.com/knoveleng/rainbowplus

More from EMNLP 2026

All EMNLP 2026 papers →