Search Results for author:
Found 10 papers, 2 papers with code
Universally Robust Graph Neural Networks by Preserving Neighbor Similarity
This theoretical proof explains the empirical observations that the graph attacker tends to connect dissimilar node pairs based on the similarities of neighbor features instead of ego features both on homophilic and heterophilic graphs.
Cost Aware Untargeted Poisoning Attack against Graph Neural Networks,
Graph Neural Networks (GNNs) have become widely used in the field of graph mining.
Node-aware Bi-smoothing: Certified Robustness against Graph Injection Attacks
Furthermore, we extend two state-of-the-art certified robustness frameworks to address node injection attacks and compare our approach against them.
Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approach
Graph anomaly detection (GAD) has achieved success and has been widely applied in various domains, such as fraud detection, cybersecurity, finance security, and biochemistry.
Coupled-Space Attacks against Random-Walk-based Anomaly Detection
In addition, we conduct transfer attack experiments in a black-box setting, which show that our feature attack significantly decreases the anomaly scores of target nodes.
Homophily-Driven Sanitation View for Robust Graph Contrastive Learning
We conduct extensive experiments to evaluate the performance of our proposed model, GCHS (Graph Contrastive Learning with Homophily-driven Sanitation View), against two state of the art structural attacks on GCL.
Simple yet Effective Gradient-Free Graph Convolutional Networks
Linearized Graph Neural Networks (GNNs) have attracted great attention in recent years for graph representation learning.
Towards Adversarially Robust Recommendation from Adaptive Fraudster Detection
The robustness of recommender systems under node injection attacks has garnered significant attention.
FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification
Graph Neural Networks (GNNs) are vulnerable to data poisoning attacks, which will generate a poisoned graph as the input to the GNN models.
BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detection
Graph-based Anomaly Detection (GAD) is becoming prevalent due to the powerful representation abilities of graphs as well as recent advances in graph mining techniques.
