Face recognition has received significant attention because of its numerous applications in
access control, law enforcement, security, surveillance, Internet communication and …

Deep learning, in particular the deep convolutional neural networks, has received
increasing interests in face recognition recently, and a number of deep learning methods …

Recent work proposed the concept of backdoor attacks on deep neural networks (DNNs),
where misclassification rules are hidden inside normal models, only to be triggered by very …

Machine learning techniques based on neural networks are achieving remarkable results in
a wide variety of domains. Often, the training of models requires large, representative …

Abstract Face Super-Resolution (SR) is a domain-specific superresolution problem. The
facial prior knowledge can be leveraged to better super-resolve face images. We present a …

An introduction to a broad range of topics in deep learning, covering mathematical and
conceptual background, deep learning techniques used in industry, and research …

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only
activate and cause misclassifications on model inputs containing a specific" trigger." Existing …

Linear discriminant analysis (LDA) is a very popular supervised feature extraction method
and has been extended to different variants. However, classical LDA has the following …

Inventors have long dreamed of creating machines that think. Ancient Greek myths tell of
intelligent objects, such as animated statues of human beings and tables that arrive full of …

With the widespread use of deep neural networks (DNNs) in high-stake applications, the
security problem of the DNN models has received extensive attention. In this paper, we …