Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks. A range of defense methods have been proposed to train adversarially robust DNNs, among which …
Cyber Physical Systems (CPS) are characterized by their ability to integrate the physical and information or cyber worlds. Their deployment in critical infrastructure have demonstrated a …
Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models …
Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To …
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have …
A recent study (Rice et al., 2020) revealed overfitting to be a dominant phenomenon in adversarially robust training of deep networks, and that appropriate early-stopping of …
X Wang, Z Zhang, J Zhang - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Given the severe vulnerability of Deep Neural Networks (DNNs) against adversarial examples, there is an urgent need for an effective adversarial attack to identify the …
The outstanding performance of deep neural networks has promoted deep learning applications in a broad set of domains. However, the potential risks caused by adversarial …
Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems eg, for classification, segmentation and object detection. The …