Xiaolin Huang

A Double-Variational Bayesian Framework in Random Fourier Features for Indefinite Kernels

2019 · IEEE Transactions on Neural Networks and Learning Systems

Random Fourier features (RFFs) have been successfully employed to kernel approximation in large-scale situations. The rationale behind RFF relies on Bochner's theorem, but the condition is too strict and excludes many widely used kernels, e.g., …

Double Backpropagation for Training Autoencoders against Adversarial Attack

2020 · arXiv (Cornell University)

Deep learning, as widely known, is vulnerable to adversarial samples. This paper focuses on the adversarial attack on autoencoders. Safety of the autoencoders (AEs) is important because they are widely used as a compression scheme …

Residual Enhanced Multi-Hypergraph Neural Network

2021

Hypergraphs are a generalized data structure of graphs to model higher-order correlations among entities, which have been successfully adopted into various researching fields. Meanwhile, HyperGraph Neural Network (HGNN) is currently the de-facto method for hypergraph …

Noise Perturbation Based Graph Contrastive Learning via Flexible Filters for Node Classification

2024

Graph neural networks (GNNs), as a powerful deep learning framework for modeling graph-structured data, have attracted lots of attention recently. Most of existing GNNs need a lot of labeled data. However, constructing generalizable and robust …

Towards Robust Synthetic Aperture Radar Classification: Counteracting Black‐Box Adversarial Attacks

2025 · IET Radar Sonar & Navigation

ABSTRACT Synthetic Aperture Radar (SAR) image classification using deep neural networks (DNNs) has demonstrated vulnerability to adversarial attacks, particularly black‐box attacks, which rely solely on model output scores to craft effective perturbations. Despite their practical …