Page 393 - 《软件学报》2026年第2期

872 软件学报 2026 年第 37 卷第 2 期

以上欺诈链路模式关联分析表明, 本文所提出的方法具备一定的可解释性, 可以通过链路信息交互发现潜在
的共性欺诈模式, 相似的欺诈模式之间会获得更大的模式交互系数, 从而驱动节点学习这些重要的共性欺诈模式
并获得更具表现力的表示.
4 总 结

本文关注了信息空间风险外溢至人类社会和物理空间所带来的严峻挑战, 尤其是欺诈行为的日益增多及其对
社会造成的负面影响, 并聚焦于图欺诈检测领域, 指出了传统欺诈检测方法的局限性. 考虑到欺诈场景下欺诈实体
间高阶交互的复杂性、依赖关系的错综复杂性及高度隐蔽性的特点, 本文提出了一种基于链路聚合的图欺诈检测
模型 PA-GNN. 该模型通过长距离链路采样编码、链路信息交互与聚合的方式, 有效弥补了主流 GNN 算法在处
理长程依赖图结构方面的不足. 实验结果表明, 该模型在金融交易、社交网络和评论网络这 3 类欺诈场景下均实
现了显著的性能提升, 并具备一定的可解释性, 能够更好地揭示不同欺诈行为间的关联模式. 本文为图欺诈检测领
域提供了新的思路和方法, 有望在实际应用中发挥重要作用, 为构建更加安全、可靠的信息空间环境做出积极贡
献, 为欺诈行为的预防和打击提供有力支持.

References
[1] Ma XX, Wu J, Xue S, Yang J, Zhou C, Sheng QZ, Xiong H, Akoglu L. A comprehensive survey on graph anomaly detection with deep
learning. IEEE Trans. on Knowledge and Data Engineering, 2023, 35(12): 12012–12038. [doi: 10.1109/TKDE.2021.3118815]
[2] Kim H, Lee BS, Shin WY, Lim S. Graph anomaly detection with graph neural networks: Current status and challenges. IEEE Access,
2022, 10: 111820–111829. [doi: 10.1109/ACCESS.2022.3211306]
[3] Liu HL, Liu YX, Xu JY, Chen SH, Qiao L. Research progress in application of graph anomaly detection in financial anti-fraud. Computer
Engineering and Applications, 2022, 58(22): 41–53 (in Chinese with English abstract). [doi: 10.3778/j.issn.1002-8331.2203-0233]
[4] Ren J, Xia F, Lee I, Noori Hoshyar A, Aggarwal C. Graph learning for anomaly analytics: Algorithms, applications, and challenges.
ACM Trans. on Intelligent Systems and Technology, 2023, 14(2): 28. [doi: 10.1145/3570906]
[5] Chen JL, Chen X, Jing YJ, Wang SY. Survey of application of graph neural network in anomaly detection. Computer Engineering and
Applications, 2024, 60(13): 51–65 (in Chinese with English abstract). [doi: 10.3778/j.issn.1002-8331.2310-0234]
[6] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436–444. [doi: 10.1038/nature14539]
[7] Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge: MIT Press, 2016.
[8] Wu ZH, Pan SR, Chen FW, Long GD, Zhang CQ, Yu PS. A comprehensive survey on graph neural networks. IEEE Trans. on Neural
Networks and Learning Systems, 2021, 32(1): 4–24. [doi: 10.1109/TNNLS.2020.2978386]
[9] Zhou J, Cui GQ, Hu SD, Zhang ZY, Yang C, Liu ZY, Wang LF, Li CC, Sun MS. Graph neural networks: A review of methods and
applications. AI Open, 2020, 1: 57–81. [doi: 10.1016/j.aiopen.2021.01.001]
[10] Zhou Y, Zheng HX, Huang X, Hao SF, Li DA, Zhao JM. Graph neural networks: Taxonomy, advances, and trends. ACM Trans. on
Intelligent Systems and Technology, 2022, 13(1): 15. [doi: 10.1145/3495161]
[11] Liu J, Shang XQ, Song LY, Tan YC. Progress of graph neural networks on complex graph mining. Ruan Jian Xue Bao/Journal of
Software, 2022, 33(10): 3582–3618 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6626.htm [doi: 10.13328/j.cnki.
jos.006626]
[12] Song LY, Ma ZY, Li ZH, Shang XQ. Review on temporal graph neural networks for financial risk prediction. Ruan Jian Xue Bao/Journal
of Software, 2024, 35(8): 3897–3922 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/7087.htm [doi: 10.13328/j.cnki.
jos.007087]
[13] Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. In: Proc. of the 5th Int’l Conf. on Learning
Representations. Toulon: OpenReview.net, 2017. 1–14.
[14] Hamilton WL, Ying RT, Leskovec J. Inductive representation learning on large graphs. In: Proc. of the 31st Conf. on Neural Information
Processing Systems. Long Beach: NIPS, 2017. 1–19.
[15] Veličković P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y. Graph attention networks. In: Proc. of the 7th Int’l Conf. on
Learning Representations. Vancouver: OpenReview.net, 2018. 1–12.
[16] Chai ZW, You SQ, Yang Y, Pu SL, Xu JR, Cai HY, Jiang WH. Can abnormality be detected by graph neural networks? In: Proc. of the
31st Int’l Joint Conf. on Artificial Intelligence. Vienna: IJCAI, 2022. 1945–1951. [doi: 10.24963/ijcai.2022/270]