Rainbow Teaming: Open-Ended Generation of Diverse Adversarial PromptsMikayel Samvelyan,Sharath Chandra Raparthy,Andrei Lupu,Eric Hambro,Aram H. Markosyan,Manish Bhatt,Yuning Mao,Minqi Jiang,Jack Parker-Holder,Jakob Foerster,Tim Rocktäschel,Roberta RaileanuNeurIPS 2024(2024)引用 65|浏览63关键词open-endedness,adversarial robustness,safetyAI 理解论文溯源树样例生成溯源树,研究论文发展脉络Chat Paper正在生成论文摘要