Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …

Delusive attacks aim to substantially deteriorate the test accuracy of the learning model by
slightly perturbing the features of correctly labeled training examples. By formalizing this …

The maximum mean discrepancy (MMD) test could in principle detect any distributional
discrepancy between two datasets. However, it has been shown that the MMD test is …

Abstract The real-world Facial Expression Recognition (FER) datasets usually exhibit
complex scenarios with coupled noise annotations and imbalanced classes distribution …

Adversarial training (AT) with imperfect supervision is significant but receives limited
attention. To push AT towards more practical scenarios, we explore a brand new yet …

Adversarial training, originally designed to resist test-time adversarial examples, has shown
to be promising in mitigating training-time availability attacks. This defense ability, however …

We propose a novel method to capture data points near decision boundary in neural
network that are often referred to a specific type of uncertainty. In our approach, we sought to …

Recent years have witnessed a burgeoning interest in federated learning (FL). However, the
contexts in which clients engage in sequential learning remain under-explored. Bridging FL …

In supervised learning, it has been shown that label noise in the data can be interpolated
without penalties on test accuracy. We show that interpolating label noise induces …

Adversarial training is an effective learning technique to improve the robustness of deep
neural networks. In this study, the influence of adversarial training on deep learning models …