risk category prompt elicit response
Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming
Han, Vernon Toh Yan, Bhardwaj, Rishabh, Poria, Soujanya
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.
2406.11654
Country:
- North America > United States > Pennsylvania (0.04)
- Europe > Monaco (0.04)
- Asia > Singapore (0.04)
- Asia > Middle East > Jordan (0.04)
Industry:
- Law Enforcement & Public Safety > Crime Prevention & Enforcement (1.00)
- Law > Criminal Law (0.94)
- Health & Medicine > Therapeutic Area (0.68)
- Government > Military (0.68)
Technology: