Search Results for author:
Found 8 papers, 4 papers with code
A backdoor attack against link prediction tasks with graph neural networks
In this paper, we propose a backdoor attack against the link prediction tasks based on GNNs and reveal the existence of such security vulnerability in GNN models, which make the backdoored GNN models to incorrectly predict unlinked two nodes as having a link relationship when a trigger appear.
A semantic backdoor attack against Graph Convolutional Networks
A semantic backdoor attack is a new type of backdoor attack on deep neural networks (DNNs), where a naturally occurring semantic feature of samples can serve as a backdoor trigger such that the infected DNN models will misclassify testing samples containing the predefined semantic feature even without the requirement of modifying the testing samples.
Towards Robust Stacked Capsule Autoencoder with Hybrid Adversarial Training
Furthermore, we propose a defense method called Hybrid Adversarial Training (HAT) against such evasion attacks.
A Targeted Universal Attack on Graph Convolutional Network
The experiments on three popular datasets show that the average attack success rate of the proposed attack on any victim node in the graph reaches 83% when using only 3 attack nodes and 6 fake nodes.
An Evasion Attack against Stacked Capsule Autoencoder
We hope that our work will make the community aware of the threat of this attack and raise the attention given to the SCAE's security.
Mitigating backdoor attacks in LSTM-based Text Classification Systems by Backdoor Keyword Identification
In this paper, through analyzing the changes in inner LSTM neurons, we proposed a defense method called Backdoor Keyword Identification (BKI) to mitigate backdoor attacks which the adversary performs against LSTM-based text classification by data poisoning.
Fast-UAP: An Algorithm for Speeding up Universal Adversarial Perturbation Generation with Orientation of Perturbation Vectors
Convolutional neural networks (CNN) have become one of the most popular machine learning tools and are being applied in various tasks, however, CNN models are vulnerable to universal perturbations, which are usually human-imperceptible but can cause natural images to be misclassified with high probability.
A backdoor attack against LSTM-based text classification systems
When the backdoor is injected, the model will misclassify any text samples that contains a specific trigger sentence into the target category determined by the adversary.
Cryptography and Security
