This is the project of our ICCV paper.
Hong Liu, Rongrong Ji, Jie Li, Baochang Zhang, Yue Gao, Yongjian Wu, Feiyue Huang. Universal Adversarial Perturbation via Prior Driven Uncertainty Approximation. ICCV, 2019.
Our codes are based on the GD-UAP, which is written by TensorFlow.
Feel free to contact us (lynnliu.xmu at gmail dot com), if you have any problems.