Fast Adversarial Training (FAT) not only improves the model robustness b...
Practical object detection application can lose its effectiveness on ima...
Developing a practically-robust automatic speech recognition (ASR) is
ch...
Recent studies have shown that higher accuracy on ImageNet usually leads...
In a transfer-based attack against Automatic Speech Recognition (ASR)
sy...
With the development of deep learning technology, the facial manipulatio...
Out-Of-Distribution (OOD) detection has received broad attention over th...
Contrastive Language-Image Pre-trained (CLIP) models have zero-shot abil...
In this paper, we prove representation bottlenecks of a cascaded
convolu...
Due to the absence of connectives, implicit discourse relation recogniti...
Out-of-distribution (OOD) detection is a critical task for ensuring the
...
Adversarial Training (AT), which is commonly accepted as one of the most...
Due to the vulnerability of deep neural networks (DNNs) to adversarial
e...
Human can easily recognize visual objects with lost information: even lo...
Recent advances on Vision Transformers (ViT) have shown that
self-attent...
Though it is well known that the performance of deep neural networks (DN...
We study the query-based attack against image retrieval to evaluate its
...
The remarkable success in face forgery techniques has received considera...
Deep neural networks have been proved that they are vulnerable to advers...
Adversarial attack is a technique for deceiving Machine Learning (ML) mo...
With the rapid development of facial manipulation techniques, face forge...
Adversarial examples are perturbed inputs which can cause a serious thre...
Deep neural networks have been shown to be vulnerable to adversarial
exa...
Deep Neural Networks (DNNs) are known to be vulnerable to the maliciousl...
Recent work has demonstrated that neural networks are vulnerable to
adve...
Few-shot image classification aims to classify unseen classes with limit...
Recently a category of tracking methods based on "tracking-by-detection"...
The task of Language-Based Image Editing (LBIE) aims at generating a tar...