计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (8): 374-384.doi: 10.11896/jsjkx.241000140

• 信息安全 • 上一篇    下一篇

基于双重分类和重建的跨域图异常检测

苏世玉1, 于炯2, 李姝3, 酒世承1   

  1. 1 新疆大学软件学院 乌鲁木齐 830000
    2 新疆大学信息科学与工程学院 乌鲁木齐 830000
    3 新疆大学计算机科学与技术学院 乌鲁木齐 830000
  • 收稿日期:2024-10-28 修回日期:2025-03-12 出版日期:2025-08-15 发布日期:2025-08-08
  • 通讯作者: 于炯(yujiong@xju.edu.cn)
  • 作者简介:(107552201726@stu.xju.edu.cn)
  • 基金资助:
    国家自然科学基金(62262064)

Cross-domain Graph Anomaly Detection Via Dual Classification and Reconstruction

SU Shiyu 1, YU Jiong 2, LI Shu3, JIU Shicheng1   

  1. 1 School of Software Engineering,Xinjiang University,Urumqi 830000,China
    2 College of Information Science and Engineering,Xinjiang University,Urumqi 830000,China
    3 School of Computer Science and Technology,Xinjiang University,Urumqi 830000,China
  • Received:2024-10-28 Revised:2025-03-12 Online:2025-08-15 Published:2025-08-08
  • About author:SU Shiyu,born in 1998,postgraduate,is a member of CCF(No.W8728G).His main research interests include anomaly detection and attribute graphs.
    YU Jiong,born in 1964,Ph.D,professor,Ph.D supervisor.His main research interests include network security and distributed computing.
  • Supported by:
    National Natural Science Foundation of China(62262064).

PDF (PC)

11

摘要： 跨域图异常检测通过带标签的源图辅助无标签目标图,提升了异常节点检测的准确性,进而有效降低了无监督图异常检测中的高误报率。尽管已有多种领域自适应方法被相继提出,但图数据复杂的拓扑结构与节点属性之间的关系使得源图与目标图之间的特征难以对齐;此外,图异常节点的多样性进一步增加了域对齐后的检测难度。为了解决上述问题,提出了一种新的跨域图异常检测框架,即双重分类和重建网络(Dual Classification and Reconstruction Network,DCRN)。该网络采用重建策略进行领域自适应,通过联合优化结构和属性的共享编码器、异常分类器和解码器,使共享编码器能够有效捕捉源图与目标图之间复杂的拓扑结构和节点属性关系,实现特征对齐与知识迁移。在对目标图进行异常检测的过程中,DCRN结合异常分类器和解码器的检测结果,识别与源图相似的异常节点以及仅存在于目标图中的特有异常,从而提升了模型的检测效果。在4个真实数据集上的实验表明,与10种基线方法相比,DCRN的AUC-ROC和AUC-PR平均提升了4.5%和20.5%,且FAR指标降低了16.13%。这些结果表明DCRN能够有效地检测目标图中的异常节点。

关键词: 异常检测, 属性图, 域自适应, 图神经网络, 知识迁移

Abstract: Cross-domain graph anomaly detection improves the accuracy of detecting anomalous nodes by leveraging labeled source graphs to assist in detecting anomalies in unlabeled target graphs,effectively reducing the high false positive rate in unsupervised detection.Aligning features between source and target graphs remain challenging due to the complex relationships between graph topology and node attributes,and the diversity of anomalous nodes further complicates detection.To address this,a Dual Classification and Reconstruction Network(DCRN) is proposed.DCRN employs a reconstruction-based strategy for domain adaptation,optimizing shared structure and attribute encoders,anomaly classifiers,and decoders.This enables the model to capture complex topological and attribute relationships between source and target graphs,achieving effective feature alignment and knowledge transfer.DCRN combines classifier and decoder results to identify both shared and unique anomalies in the target graph,enhancing detection accuracy and robustness.Experiments on four real-world datasets show that DCRN outperforms 10 baseline algorithms,with an average improvement of 4.5% in AUC-ROC,20.5% in AUC-PR,and a 16.13% reduction in FAR,demonstrating its effectiveness in detecting anomalous nodes in target graphs.

Key words: Anomaly detection, Attribute graph, Domain adaptation, Graph neural network, Knowledge transfe

中图分类号: 

  • TP391
[1]ZHANG Y Y,QIAN Y R,TAO W B,et al.Survey of Attribute Graph Anomaly Detection Based on Deep Learning[J].ComputerEngineering and Applications,2022,58(19):1-13.
[2]HAJLI N,SAEED U,TAJVIDI M,et al.Social bots and thespread of disinformation in social media:the challenges of artificial intelligence[J].British Journal of Management,2022,33(3):1238-1253.
[3]LU Y J,SHENG L K,ZHANG Y L.Research on structural diversity of citation network oriented to evaluation of literature [J].Application Research of Computers,2024,41(2):408-414.
[4]LIU H L,LIU Y X,XU J Y,et al.Research Progress in Application of Graph Anomaly Detection in Financial Anti-Fraud[J].Computer Engineering and Applications,2022,58(22):41-53.
[5]LI Z,JIN X L,WANG Y J,et al.Anomaly Node DetectionMethod Based on Variational Graph Auto-Encoders in Attri-bute Networks[J].Pattern Recognition and Artificial Intelligence,2022,35(1):17-25.
[6]XU X,YURUK N,FENG Z,et al.Scan:a structural clustering algorithm for networks[C]//Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2007:824-833.
[7]LI S,YU J,LU Y,et al.Self-supervised enhanced denoising diffusion for anomaly detection[J].Information Sciences,2024,669:120612.
[8]ZHUANG Y S,LIN S L,LIN Z X,et al.Study on Generative Adversarial Network for Data Anomaly Detection[J].Computer Engineering and Applications,2022,58(4):143-149.
[9]DING K,SHU K,SHAN X,et al.Cross-domain graph anomaly detection[J].IEEE Transactions on Neural Networks and Learning Systems,2021,33(6):2406-2415.
[10]LI Y,YANG X,GAO Q,et al.Cross-regional Fraud Detection via Continual Learning with Knowledge Transfer[J].IEEE Transactions on Knowledge and Data Engineering,2024,36(12):7865-7877.
[11]ZHANG F,FAN H,WANG R,et al.Deep dual support vector data description for anomaly detection on attributed networks[J].International Journal of Intelligent Systems,2022,37(2):1509-1528.
[12]BANDYOPADHYAY S,LOKESH N,MURTY M N.Outlieraware network embedding for attributed networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:12-19.
[13]WANG Q,PANG G,SALEHI M,et al.Cross-domain graphanomaly detection via anomaly-aware contrastive alignment[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2023:4676-4684.
[14]LI Z,LIANG S,SHI J,et al.Cross-domain graph level anomaly detection[J].IEEE Transactions on Knowledge and Data Engineering,2024,36(12):7839-7850.
[15]QU C,JI F,QIU M,et al.Learning to selectively transfer:Reinforced transfer learning for deep text matching[C]//Procee-dings of the twelfth ACM International Conference on Web Search and Data Mining.2019:699-707.
[16]TZENG E,HOFFMAN J,SAENKO K,et al.Adversarial dis-criminative domain adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:7167-7176.
[17]GUO J Y,LI R H,ZHANG Y,et al.Graph neural networkbased anomaly detection in dynamic networks[J].Journal of Software,2020,31(3):748-762.
[18]CHEN B F,LI J D,LU X J,et al.Survey of Deep Learning Based Graph Anomaly Detection Methods[J].Journal of Computer Research and Development,2021,58(7):1436-1455
[19]MA X,WU J,XUE S,et al.A comprehensive survey on graph anomaly detection with deep learning[J].IEEE Transactions on Knowledge and Data Engineering,2021,35(12):12012-12038.
[20]LIU N,HUANG X,HU X.Accelerated Local Anomaly Detection via Resolving Attributed Networks[C]//IJCAI.2017:2337-2343.
[21]LI J,DANI H,HU X,et al.Radar:Residual analysis for anomaly detection in attributed networks[C]//IJCAI.2017:2152-2158.
[22]WU L,HU X,MORSTATTER F,et al.Adaptive spammer detection with sparse group modeling[C]//Proceedings of the International AAAI Conference on Web and Social Media.2017:319-326.
[23]DING K,LI J,BHANUSHALI R,et al.Deep anomaly detection on attributed networks[C]//Proceedings of the 2019 SIAM International Conference on Data Mining.Society for Industrial and Applied Mathematics,2019:594-602.
[24]FAN H,ZHANG F,LI Z.Anomalydae:Dual autoencoder for anomaly detection on attributed networks[C]//2020 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP 2020).IEEE,2020:5685-5689.
[25]LUO X,WU J,BEHESHTI A,et al.Comga:Community-aware attributed graph anomaly detection[C]//Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining.2022:657-665.
[26]LIU Y,LI Z,PAN S,et al.Anomaly detection on attributed networks via contrastive self-supervised learning[J].IEEE transactions on neural networks and learning systems,2021,33(6):2378-2392.
[27]ZHENG Y,JIN M,LIU Y,et al.Generative and contrastive self-supervised learning for graph anomaly detection[J].IEEE Transactions on Knowledge and Data Engineering,2021,35(12):12220-12233.
[28]ZHANG J,WANG S,CHEN S.Reconstruction enhanced multi-view contrastive learning for anomaly detection on attributed networks[J].arXiv:2205.04816,2022.
[29]HAN X,YUAN S.Unsupervised cross-system log anomaly detection via domain adaptation[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management.2021:3068-3072.
[30]SU Y,TAN Y,AN S,et al.Semantic-driven dual consistency learning for weakly supervised video anomaly detection[J].Pattern Recognition,2025,157:110898.
[31]LONG M,CAO Y,WANG J,et al.Learning transferable features with deep adaptation networks[C]//International Confe-rence on Machine Learning.PMLR,2015:97-105.
[32]ZELLINGER W,GRUBINGER T,LUGHOFER E,et al.Central moment discrepancy(CMD) for domain-invariant representation learning[J].arXiv:1702.08811,2017.
[33]KANG G,JIANG L,YANG Y,et al.Contrastive adaptation network for unsupervised domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:4893-4902.
[34]FLAMARY R,COURTY N,TUIA D,et al.Optimal transport for domain adaptation[J].arXiv:1507.00504,2016.
[35]GHIFARY M,KLEIJN W B,ZHANG M,et al.Deep recon-struction-classification networks for unsupervised domain adaptation[C]//Computer Vision-ECCV 2016:14th European Conference,Amsterdam,The Netherlands,October 11-14,2016,Proceedings,Part IV 14.Springer International Publishing,2016:597-613.
[36]BOUSMALIS K,TRIGEORGIS G,SILBERMAN N,et al.Domain separation networks[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems.2016:343-351.
[37]GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems.2014:2672-2680.
[38]GANIN Y,USTINOVA E,AJAKAN H,et al.Domain-adversarial training of neural networks[J].Journal of Machine Lear-ning Research,2016,17(59):1-35.
[39]LONG M,CAO Z,WANG J,et al.Conditional adversarial do-main adaptation[C]//Proceedings of the 32nd International Conference on Neural Information processing Systems.2018:1647-1657.
[40]KONG L C,LIU G Z.Review of Outlier Detection Algorithms[J].Computer Science,2024,51(8):20-33.
[41]PENG Z,LUO M,LI J,et al.ANOMALOUS:A Joint Modeling Approach for Anomaly Detection on Attributed Networks[C]//IJCAI.2018:3513-3519.
[42]BANDYOPADHYAY S,LOKESH N,VIVEK S V,et al.Outlier resistant unsupervised deep architectures for attributed network embedding[C]//Proceedings of the 13th International Conference on Web Search and Data Mining.2020:25-33.
[43]WANG X,JIN B,DU Y,et al.One-class graph neural networks for anomaly detection in attributed networks[J].Neural Computing and Applications,2021,33:12073-12085.
[44]DIEDERIK P K.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发