Benchmarking GNNs with GenCAT Workbench

Maekawa, Seiji; Sasaki, Yu; Fletcher, George P.; Onizuka, Makoto

doi:10.1007/978-3-031-26422-1_40

Cited by 2 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Federated Graph Neural Network (FedGNN) has emerged as a fast-evolving research area that combines the capabilities of graph neural networks and federated learning. Such integration allows for advanced machine learning applications without requiring direct access to sensitive data [1,2,3,4,5,6,7,8,9]. However, despite its numerous advantages, the distributed nature of FedGNN introduces additional vulnerabilities, particularly related to backdoor attacks originating from malicious participants.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring metadiscourse in university lectures in Hong Kong

Liu¹

View full text Add to dashboard Cite

Federated Graph Neural Network (FedGNN) has recently emerged as a rapidly growing research topic, as it integrates the strengths of graph neural networks and federated learning to enable advanced machine learning applications without direct access to sensitive data. Despite its advantages, the distributed nature of FedGNN introduces additional vulnerabilities, particularly backdoor attacks stemming from malicious participants. Although graph backdoor attacks have been explored, the compounded complexity introduced by the combination of GNNs and federated learning has hindered a comprehensive understanding of these attacks, as existing research lacks extensive benchmark coverage and in-depth analysis of critical factors. To address these limitations, we propose Bkd-FedGNN, a benchmark for backdoor attacks on FedGNN. Specifically, Bkd-FedGNN decomposes the graph backdoor attack into trigger generation and injection steps, and extending the attack to the node-level federated setting, resulting in a unified framework that covers both node-level and graph-level classification tasks. Moreover, we thoroughly investigate the impact of multiple critical factors in backdoor attacks on FedGNN. These factors are categorized into global-level and local-level factors, including data distribution, the number of malicious attackers, attack time, overlapping rate, trigger size, trigger type, trigger position, and poisoning rate. Finally, we conduct comprehensive evaluations on 13 benchmark datasets and 13 critical factors, comprising 1,725 experimental configurations for node-level and graphlevel tasks from six domains. These experiments encompass over 8,000 individual tests, allowing us to provide a thorough evaluation and insightful observations that advance our understanding of backdoor attacks on FedGNN. The Bkd-FedGNN benchmark is publicly available at https://github.com/usail-hkust/ BkdFedGCN.Preprint. Under review.

show abstract

Section: Introductionmentioning

confidence: 99%

“…experiments investigating critical factors are depicted in Several key observations can be made:(1) In both node and graph-level tasks, an increase in PR is associated with a rise in ASR across the majority of datasets. (2) In node-level tasks, ASR decreases as NMA increases, whereas in graph-level tasks, ASR increases with the growth of NMA.…”

mentioning

confidence: 99%