Search Results for author:
Found 3 papers, 3 papers with code
Data-Free Hard-Label Robustness Stealing Attack
In response to these identified gaps, we introduce a novel Data-Free Hard-Label Robustness Stealing (DFHL-RS) attack in this paper, which enables the stealing of both model accuracy and robustness by simply querying hard labels of the target model without the help of any natural data.
Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network
At first, a top-n selection strategy is proposed to provide pseudo-labels for public data, and use pseudo-labels to guide the training of the cGAN.
Fer2013 Recognition - ResNet18 With Tricks
This work is the final project of the Computer Vision Course of USTC.
Ranked #7 on
Facial Expression Recognition (FER)
on FER2013
