Deep generative models are a class of techniques that train deep neural networks to model
the distribution of training samples. Research has fragmented into various interconnected …

Malware poses a severe threat to cyber security. Attackers use malware to achieve their
malicious purposes, such as unauthorized access, stealing confidential data, blackmailing …

With the rapid developments of artificial intelligence (AI) and deep learning (DL) techniques,
it is critical to ensure the security and robustness of the deployed algorithms. Recently, the …

Recent successes in Generative Adversarial Networks (GAN) have affirmed the importance
of using more data in GAN training. Yet it is expensive to collect data in many domains such …

Conventional machine learning algorithms suffer the problem that the model trained on
existing data fails to generalize well to the data sampled from other distributions. To tackle …

Differentiable architecture search (DARTS) is a prevailing NAS solution to identify
architectures. Based on the continuous relaxation of the architecture space, DARTS learns a …

The methods for remote sensing image (RSI) scene classification based on deep
convolutional neural networks (DCNNs) have achieved prominent success. However …

Neural networks are vulnerable to adversarial examples, ie inputs that are imperceptibly
perturbed from natural data and yet incorrectly classified by the network. Adversarial …

Although adversarial examples and model robust-ness have been extensively studied in the
context of neural networks, research on this issue in tree-based models and how to make …

In recent years, researches on adversarial attacks and defense mechanisms have obtained
much attention. It's observed that adversarial examples crafted with small malicious …