Training a high-performance deep neural network requires large amounts o...
Graph neural networks (GNNs) have been widely applied to learning over g...
Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous...
Increasing concerns have been raised on deep learning fairness in recent...
Existing out-of-distribution (OOD) detection methods are typically
bench...
Adversarial training (AT) defends deep neural networks against adversari...
Federated learning (FL) provides a distributed learning framework for
mu...
Data augmentation is a simple yet effective way to improve the robustnes...
Federated learning (FL) emerges as a popular distributed learning schema...
The open-world deployment of Machine Learning (ML) algorithms in
safety-...
Recently, the group maximum differentiation competition (gMAD) has been ...
Adversarial training and its many variants substantially improve deep ne...
Generative adversarial networks (GANs) have gained increasing popularity...
The compression of Generative Adversarial Networks (GANs) has lately dra...
The learning of hierarchical representations for image classification ha...
Deep networks were recently suggested to face the odds between accuracy ...
This paper aims to boost privacy-preserving visual recognition, an
incre...
The robustness of deep models to adversarial attacks has gained signific...