Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming
We propose Ruby Teaming, a method that improves on Rainbow Teaming by including a memory cache as its third dimension. The memory dimension provides cues to the mutator to yield better-quality prompts, both in terms of attack success rate (ASR) and quality diversity. The prompt archive generated by Ruby Teaming has an ASR of 74%, which is 20% higher than the baseline. In terms of quality diversity, Ruby Teaming outperforms Rainbow Teaming by 6% and 3% on Shannon's Evenness Index (SEI) and Simpson's Diversity Index (SDI), respectively.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityRed TeamingSimilar Papers 제목 키워드 기반
RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search
Large Language Models (LLMs) exhibit remarkable capabilities but are susceptible to adversarial prompts that exploit vulnerabilities to produce unsafe or biased outputs. Existing red-teaming methods often face scalabilit…
DiversityEvolutionary AlgorithmsRed TeamingQuality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models
Ensuring safety of large language models (LLMs) is important. Red teaming--a systematic approach to identifying adversarial prompts that elicit harmful responses from target LLMs--has emerged as a crucial safety evaluati…
DiversityRed TeamingSentence EmbeddingSentence-EmbeddingDoes BLEU Score Work for Code Migration?
Statistical machine translation (SMT) is a fast-growing sub-field of computational linguistics. Until now, the most popular automatic metric to measure the quality of SMT is BiLingual Evaluation Understudy (BLEU) score. …
Machine TranslationTranslationFerret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
In today's era, where large language models (LLMs) are integrated into numerous real-world applications, ensuring their safety and robustness is crucial for responsible AI usage. Automated red-teaming methods play a key …
AI and SafetyDiversityRed TeamingSafety AlignmentBe a Multitude to Itself: A Prompt Evolution Framework for Red Teaming
Large Language Models (LLMs) have gained increasing attention for their remarkable capacity, alongside concerns about safety arising from their potential to produce harmful content. Red teaming aims to find prompts that …
DiversityIn-Context LearningRed Teaming