Related papers: Augmenting Rule-based DNS Censorship Detection at …

Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explaining complex human visual representations. However, the…

Semi-Supervised Learning (SSL) has been proved to be an effective way to leverage both labeled and unlabeled data at the same time. Recent semi-supervised approaches focus on deep neural networks and have achieved promising results on…

Noisy labeled data represent a rich source of information that often are easily accessible and cheap to obtain, but label noise might also have many negative consequences if not accounted for. How to fully utilize noisy labels has been…

Consistency regularization-based methods are prevalent in semi-supervised learning (SSL) algorithms due to their exceptional performance. However, they mainly depend on domain-specific data augmentations, which are not usable in domains…

Deep learning demands a huge amount of well-labeled data to train the network parameters. How to use the least amount of labeled data to obtain the desired classification accuracy is of great practical significance, because for many…

As the Internet of Things (IoT) continues to expand, ensuring the security of connected devices has become increasingly critical. Traditional Intrusion Detection Systems (IDS) often fall short in managing the dynamic and large-scale nature…

High-bandwidth covert channels pose significant risks to sensitive and proprietary information inside company networks. Domain Name System (DNS) tunnels provide a means to covertly infiltrate and exfiltrate large amounts of information…

Semi-supervised learning (SSL) has been extensively studied to improve the generalization ability of deep neural networks for visual recognition. To involve the unlabelled data, most existing SSL methods are based on common density-based…

Supervised training of deep neural networks (DNNs) by noisy labels has been studied extensively in image classification but much less in image segmentation. Our understanding of the learning behavior of DNNs trained by noisy segmentation…

In the context of globalization and the rapid expansion of the digital economy, anti-money laundering (AML) has become a crucial aspect of financial oversight, particularly in cross-border transactions. The rising complexity and scale of…

Obtaining high-quality labels for large datasets is expensive, requiring massive annotations from human experts. While AI models offer a cost-effective alternative by predicting labels, their label quality is compromised by the unavoidable…

Accurately predicting the time of occurrence of an event of interest is a critical problem in longitudinal data analysis. One of the main challenges in this context is the presence of instances whose event outcomes become unobservable after…

Researchers have studied Internet censorship for nearly as long as attempts to censor contents have taken place. Most studies have however been limited to a short period of time and/or a few countries; the few exceptions have traded off…

Given the growing complexity of healthcare data over the last several years, using machine learning techniques like Deep Neural Network (DNN) models has gained increased appeal. In order to extract hidden patterns and other valuable…

While neural networks for learning representation of multi-view data have been previously proposed as one of the state-of-the-art multi-view dimension reduction techniques, how to make the representation discriminative with only a small…

We introduce NinjaDoH, a novel DNS over HTTPS (DoH) protocol that leverages the InterPlanetary Name System (IPNS), along with public cloud infrastructure, to create a censorship-resistant moving target DoH service. NinjaDoH is specifically…

To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unlabeled target domain. However, existing methods assume that…

Whose labels should a machine learning (ML) algorithm learn to emulate? For ML tasks ranging from online comment toxicity to misinformation detection to medical diagnosis, different groups in society may have irreconcilable disagreements…

Large scale image dataset and deep convolutional neural network (DCNN) are two primary driving forces for the rapid progress made in generic object recognition tasks in recent years. While lots of network architectures have been…

As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…