Deep learning has been widely applied in various fields such as computer vision, natural
language processing, and data mining. Although deep learning has achieved significant …

The popularity of adapting deep neural networks (DNNs) in solving hard problems has
increased substantially. Specifically, in the field of computer vision, DNNs are becoming a …

As a research community, we are still lacking a systematic understanding of the progress on
adversarial robustness which often makes it hard to identify the most promising ideas in …

The evaluation of robustness against adversarial manipulation of neural networks-based
classifiers is mainly tested with empirical attacks as methods for the exact computation, even …

Skip connections are an essential component of current state-of-the-art deep neural
networks (DNNs) such as ResNet, WideResNet, DenseNet, and ResNeXt. Despite their …

Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From
a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the …

Adversarial patch attacks are among one of the most practical threat models against real-
world computer vision systems. This paper studies certified and empirical defenses against …

Vision transformers (ViTs) process input images as sequences of patches via self-attention;
a radically different architecture than convolutional neural networks (CNNs). This makes it …

Data privacy has become an increasingly important issue in Machine Learning (ML), where
many approaches have been developed to tackle this challenge, eg, cryptography …

基于深度神经网络的雷达像智能识别技术已经成为雷达信息处理领域的前沿和热点. 然而,
神经网络分类模型易受到对抗攻击的威胁. 攻击者可以在隐蔽的条件下误导智能目标识别模型做 …