no code implementations • 3 Mar 2024 • Yuni Lai, Bailin Pan, Kaihuang Chen, Yancheng Yuan, Kai Zhou
We investigate certified robustness for GNNs under graph injection attacks.
no code implementations • 19 Jan 2024 • Jialong Zhou, Xing Ai, Yuni Lai, Kai Zhou
Similar to how structure learning can restore unsigned graphs, balance learning can be applied to signed graphs by improving the balance degree of the poisoned graph.
no code implementations • 18 Jan 2024 • Yulin Zhu, Yuni Lai, Xing Ai, Kai Zhou
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.
no code implementations • 12 Dec 2023 • Yuwei Han, Yuni Lai, Yulin Zhu, Kai Zhou
Graph Neural Networks (GNNs) have become widely used in the field of graph mining.
no code implementations • 7 Dec 2023 • Yuni Lai, Yulin Zhu, Bailin Pan, Kai Zhou
Furthermore, we extend two state-of-the-art certified robustness frameworks to address node injection attacks and compare our approach against them.
2 code implementations • 26 Jul 2023 • Yuni Lai, Marcin Waniek, Liying Li, Jingwen Wu, Yulin Zhu, Tomasz P. Michalak, Talal Rahwan, Kai Zhou
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.
no code implementations • 8 Nov 2022 • Yuni Lai, Yulin Zhu, Wenqi Fan, Xiaoge Zhang, Kai Zhou
The robustness of recommender systems under node injection attacks has garnered significant attention.
1 code implementation • 18 Jun 2021 • Yulin Zhu, Yuni Lai, Kaifa Zhao, Xiapu Luo, Mingquan Yuan, Jian Ren, Kai Zhou
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.
1 code implementation • 5 Dec 2019 • Yuni Lai, Linfeng Zhang, Donghong Han, Rui Zhou, Guoren Wang
In addition, a pooling method based on percentile is proposed to improve the accuracy of the model.