AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Shanghai Artificial Intelligence Laboratory
Scientific Directors: Xia Hu, Chaochao Lu
Project Co-Leaders (Corresponding authors): Dongrui Liu, Jing Shao
Core Contributors: Dongrui Liu, Qihan Ren, Chen Qian, Shuai Shao, Yuejin Xie, Yu Li, Zhonghao Yang, Haoyu Luo, Peng Wang, Qingyu Liu
Contributors: Binxin Hu, Ling Tang, Jilin Mei, Dadi Guo, Leitao Yuan, Junyao Yang, Guanxu Chen, Qihao Lin, Yi Yu, Bo Zhang, Jiaxuan Guo, Jie Zhang, Wenqi Shao, Huiqi Deng, Zhiheng Xi, Wenjie Wang, Wenxuan Wang, Wen Shen
Technical Acknowledgements: Zhikai Chen, Haoyu Xie, Jialing Tao, Juntao Dai, Jiaming Ji, Zhongjie Ba, Linfeng Zhang, Yong Liu, Quanshi Zhang, Lei Zhu, Zhihua Wei, Hui Xue
A diagnostic guardrail framework uses a unified three-dimensional risk taxonomy to monitor agent trajectories. Fine-grained attribution identifies the causes of unsafe behavior and supports root-cause analysis.