Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Lai, Yuni"'
With the trend of large graph learning models, business owners tend to employ a model provided by a third party to deliver business services to users. However, these models might be backdoored, and malicious users can submit trigger-embedded inputs t
Externí odkaz:
http://arxiv.org/abs/2410.04916
We investigate certified robustness for GNNs under graph injection attacks. Existing research only provides sample-wise certificates by verifying each node independently, leading to very limited certifying performance. In this paper, we present the f
Externí odkaz:
http://arxiv.org/abs/2403.01423
Signed graphs consist of edges and signs, which can be separated into structural information and balance-related information, respectively. Existing signed graph neural networks (SGNNs) typically rely on balance-related information to generate embedd
Externí odkaz:
http://arxiv.org/abs/2401.10590
Graph Neural Networks (GNNs) have become widely used in the field of graph mining. However, these networks are vulnerable to structural perturbations. While many research efforts have focused on analyzing vulnerability through poisoning attacks, we h
Externí odkaz:
http://arxiv.org/abs/2312.07158
Deep Graph Learning (DGL) has emerged as a crucial technique across various domains. However, recent studies have exposed vulnerabilities in DGL models, such as susceptibility to evasion and poisoning attacks. While empirical and provable robustness
Externí odkaz:
http://arxiv.org/abs/2312.03979
Publikováno v:
2024 International Conference on Computing, Networking and Communications (ICNC), pp. 530-535
Signed graphs are well-suited for modeling social networks as they capture both positive and negative relationships. Signed graph neural networks (SGNNs) are commonly employed to predict link signs (i.e., positive and negative) in such graphs due to
Externí odkaz:
http://arxiv.org/abs/2309.02396
Autor:
Lai, Yuni, Waniek, Marcin, Li, Liying, Wu, Jingwen, Zhu, Yulin, Michalak, Tomasz P., Rahwan, Talal, Zhou, Kai
Random Walks-based Anomaly Detection (RWAD) is commonly used to identify anomalous patterns in various applications. An intriguing characteristic of RWAD is that the input graph can either be pre-existing or constructed from raw features. Consequentl
Externí odkaz:
http://arxiv.org/abs/2307.14387
The robustness of recommender systems under node injection attacks has garnered significant attention. Recently, GraphRfi, a GNN-based recommender system, was proposed and shown to effectively mitigate the impact of injected fake users. However, we d
Externí odkaz:
http://arxiv.org/abs/2211.11534
Autor:
Zhu, Yulin, Lai, Yuni, Zhao, Kaifa, Luo, Xiapu, Yuan, Mingquan, Wu, Jun, Ren, Jian, Zhou, Kai
The success of graph neural networks stimulates the prosperity of graph mining and the corresponding downstream tasks including graph anomaly detection (GAD). However, it has been explored that those graph mining methods are vulnerable to structural
Externí odkaz:
http://arxiv.org/abs/2206.08260
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. These GAD tools, however, expose a new attacking surface, ironically due to their
Externí odkaz:
http://arxiv.org/abs/2106.09989