Federated learning (FL) is a nascent distributed learning paradigm
to tr...
Self-supervised learning usually uses a large amount of unlabeled data t...
Adversarial examples (AEs) for DNNs have been shown to be transferable: ...
While collaborative systems provide convenience to our lives, they also ...
Federated learning (FL) is vulnerable to poisoning attacks, where advers...
Adversarial attacks are a serious threat to the reliable deployment of
m...
Point cloud completion, as the upstream procedure of 3D recognition and
...
Recent studies show that deep neural networks (DNNs) are vulnerable to
b...
Federated learning is a newly emerging distributed learning framework th...
Due to its powerful feature learning capability and high efficiency, dee...
The usage of deep learning is being escalated in many applications. Due ...
Federated learning (FL) enables multiple clients to collaboratively trai...
Machine learning promotes the continuous development of signal processin...
Fine-tuning attacks are effective in removing the embedded watermarks in...
While deep face recognition (FR) systems have shown amazing performance ...
Advances of emerging Information and Communications Technology (ICT)
tec...
Recently emerged federated learning (FL) is an attractive distributed
le...
Applying chaos theory for secure digital communications is promising and...
The advent of the big data era drives the media data owner to seek help ...
Deep learning models are known to be vulnerable to adversarial examples ...