In medical imaging, the last decade has witnessed a remarkable increase in the availability
and diversity of chest X-ray (CXR) datasets. Concurrently, there has been a significant …

Leveraging labels in a supervised learning framework as prior knowledge to enhance
network anomaly detection has become a trend. Unfortunately, just a few labels are typically …

Node injection attacks on Graph Neural Networks (GNNs) have received increasing
attention recently, due to their ability to degrade GNN performance with high attack success …

Convolutional neural networks (CNNs) and visual transformers (ViTs) are both known to be
vulnerable to adversarial examples. Recent work has illustrated the existence of …

Abstract Model extraction attacks are considered to be a significant avenue of vulnerability in
machine learning. In model extraction attacks, the attacker repeatedly queries a victim model …

Person re-identification (Re-ID) has achieved tremendous success in the fields of computer
vision and security. However, Re-ID models are susceptible to adversarial examples, which …

Abstract Graph Neural Networks (GNNs) have demonstrated remarkable success across
diverse fields, yet remain susceptible to subtle adversarial perturbations that significantly …

This paper focuses on the representation/latent space in neural architectures to develop an
end-to-end explanation approach for Image Captioning (IC) models. By injecting Gaussian …

Neural network models have been successfully used to predict stock prices, weather, and
traffic patterns. Due to the sensitivity of the data, it is very effective in identifying and …

Graph neural networks (GNNs) have been widely applied in the Internet of Things (IoT) for
the intelligent analysis of data collected by sensors, particularly complex relationships and …