1 code implementation • 19 Dec 2023 • Jing Cui, Yufei Han, Yuzhe ma, Jianbin Jiao, Junge Zhang
Our algorithm, BadRL, strategically chooses state observations with high attack values to inject triggers during training and testing, thereby reducing the chances of detection.
no code implementations • 14 Dec 2022 • Yufei Xie, Jing Cui, Mengdie Wang
With the development of China's economy and society, the importance of "craftsman's spirit" has become more and more prominent.