research
∙
02/28/2023
A semantic backdoor attack against Graph Convolutional Networks
Graph Convolutional Networks (GCNs) have been very effective in addressi...
share
research
∙
02/28/2022
Towards Robust Stacked Capsule Autoencoder with Hybrid Adversarial Training
Capsule networks (CapsNets) are new neural networks that classify images...
research
∙
11/29/2020
A Targeted Universal Attack on Graph Convolutional Network
Graph-structured data exist in numerous applications in real life. As a ...
research
∙
10/14/2020
An Adversarial Attack against Stacked Capsule Autoencoder
Capsule network is a kind of neural network which uses spatial relations...
research
∙
07/11/2020
Mitigating backdoor attacks in LSTM-based Text Classification Systems by Backdoor Keyword Identification
It has been proved that deep neural networks are facing a new threat cal...
research
∙
11/04/2019
Fast-UAP: Algorithm for Speeding up Universal Adversarial Perturbation Generation with Orientation of Perturbation Vectors
Convolutional neural networks (CNN) have become one of the most popular ...
research
∙
05/29/2019