J. Xu
11 records found
1
Authored
Connecting the dots
Exploring backdoor attacks on graph neural networks
Unveiling the Threat
Investigating Distributed and Centralized Backdoor Attacks in Federated Graph Neural Networks
Deep learning found its place in various real-world applications, where many also have security requirements. Unfortunately, as these systems become more pervasive, understanding how they fail becomes more challenging. While there are multiple failure modes in machine learning ...
Graph Neural Networks (GNNs) have achieved promising performance in various real-world applications. Building a powerful GNN model is not a trivial task, as it requires a large amount of training data, powerful computing resources, and human expertise. Moreover, with the devel ...
This work explores backdoor attacks for automatic speech recognition systems where we inject inaudible triggers. By doing so, we make the backdoor attack challenging to detect for legitimate users and, consequently, potentially more dangerous. We conduct experiments on two ver ...
Poster
Clean-label Backdoor Attack on Graph Neural Networks
Graph Neural Networks (GNNs) have achieved impressive results in various graph learning tasks. They have found their way into many applications, such as fraud detection, molecular property prediction, or knowledge graph reasoning. However, GNNs have been recently demonstrated ...
Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already numerous works on backdoor attacks on ...