EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

A Security Monitoring and Multi-source Anomaly Detection Method for New Distributed Systems Oriented to Economic Data Asset Circulation

Chenfei Zhuang, Jiajia Cao, Xingchao Ni

ICST Transactions on Scalable Information Systems · 18.11.2026 · 13 (8)

DOI: 10.4108/eetsis.13812 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ICST Transactions on Scalable Information Systems, online erschienen am 18.11.2026. Verfasst von Chenfei Zhuang und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the difficulty of unified security risk monitoring caused by the coupling of on-chain auditing, microservice invocation, distributed databases, and network communication states during economic data asset circulation, this paper proposes a multi-source spatio-temporal graph anomaly detection method for new distributed systems, namely MSTG-AD. The method aligns five monitoring sources—transaction behavior, on-chain auditing, microservice invocation, database metrics, and network traffic—with a six-entity relation schema covering users, data assets, contracts, services, databases, and network nodes. Rather than claiming novelty for the individual temporal, Transformer, graph-attention, or spectral operators, the proposed contribution lies in their cross-layer semantic coupling: multi-window temporal encoding captures periodic changes and abrupt fluctuations, call-chain/database encoding characterizes service and node states, an asset-context-aware gate prioritizes anomaly evidence according to value and exposure context, and a relation-constrained decoder traces temporally consistent root-cause paths along the economic-data-asset chain. On a simulated economic data asset trading platform and a multi-source fusion test set, MSTG-AD achieves a Precision of 95.1%, a Recall of 94.0%, an F1-score of 94.5%, and an AUC of 0.973, with an average detection latency of 38.6 ms. In the root cause localization task, AC@1, AC@3, and AC@5 reach 0.91, 0.96, and 0.98, respectively. The results demonstrate the effectiveness of full-link multi-source modeling for anomaly identification, risk monitoring, and explainable root-cause localization.

Zitieren

APA

Zhuang, C., Cao, J., & Ni, X. (2026). A Security Monitoring and Multi-source Anomaly Detection Method for New Distributed Systems Oriented to Economic Data Asset Circulation. ICST Transactions on Scalable Information Systems, 13(8). https://doi.org/10.4108/eetsis.13812

Vancouver

Zhuang C, Cao J, Ni X. A Security Monitoring and Multi-source Anomaly Detection Method for New Distributed Systems Oriented to Economic Data Asset Circulation. ICST Transactions on Scalable Information Systems. 2026;13(8). doi:10.4108/eetsis.13812

BibTeX
@article{Zhuang2026,
  author = {Zhuang, Chenfei and Cao, Jiajia and Ni, Xingchao},
  title = {A Security Monitoring and Multi-source Anomaly Detection Method for New Distributed Systems Oriented to Economic Data Asset Circulation},
  journal = {ICST Transactions on Scalable Information Systems},
  year = {2026},
  volume = {13},
  number = {8},
  doi = {10.4108/eetsis.13812}
}
Kostenlos starten →