Compositional AI systems, which combine multiple artificial intelligence...
Current deep neural networks (DNNs) are vulnerable to adversarial attack...
Contrastive learning (CL) can learn generalizable feature representation...
Machine learning (ML) models that learn and predict properties of comput...
Recent works have developed several methods of defending neural networks...
When the training data are maliciously tampered, the predictions of the
...
Recent works have empirically shown that there exist adversarial example...
Today, image classification is a common way for systems to process visua...
It is known that deep neural networks (DNNs) could be vulnerable to
adve...
It is widely known that convolutional neural networks (CNNs) are vulnera...