论文阅读：2024 NeurIPS JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Model

总目录 大模型安全相关研究：https://blog.csdn.net/WhiffeYF/article/details/142132328

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
JailbreakBench：用于越狱大型语言模型的开放稳健性基准

https://arxiv.org/pdf/2404.01318

https://github.com/JailbreakBench/jailbreakbench

https://www.doubao.com/chat/3224330646661122

https://huggingface.co/datasets/JailbreakBench/JBB-Behaviors<