- Title
- LogDP: Combining Dependency and Proximity for Log-Based Anomaly Detection
- Creator
- Xie, Yongzheng; Zhang, Hongyu; Zhang, Bo; Babar, Muhammad Ali; Lu, Sha
- Relation
- 19th International Conference on Service-Oriented Computing, ICSOC 2021. Proceedings of the 19th International Conference on Service-Oriented Computing, ICSOC 2021, Vol. 13121 (Virtual 22-25 November, 2021) p. 708-716
- Relation
- ARC.DP200102940 http://purl.org/au-research/grants/arc/DP200102940
- Publisher Link
- http://dx.doi.org/10.1007/978-3-030-91431-8_47
- Publisher
- Springer
- Resource Type
- conference paper
- Date
- 2021
- Description
- Log analysis is an important technique that engineers use for troubleshooting faults of large-scale service-oriented systems. In this study, we propose a novel semi-supervised log-based anomaly detection approach, LogDP, which utilizes the dependency relationships among log events and proximity among log sequences to detect the anomalies in massive unlabeled log data. LogDP divides log events into dependent and independent events, then learns the normal patterns of dependent events based on the dependencies among events and the normal patterns of independent events based on the deviation of values from a historic mean. Events violating any normal pattern are identified as anomalies. By combining dependency and proximity, LogDP is able to achieve high detection accuracy. Extensive experiments have been conducted on real-world datasets, and the results show that LogDP outperforms six state-of-the-art methods.
- Subject
- log analysis; log-based anomaly detection; dependency-based anomaly detection; system operation and maintenance
- Identifier
- http://hdl.handle.net/1959.13/1474115
- Identifier
- uon:49213
- Identifier
- ISBN:9783030914301
- Language
- eng
- Reviewed
- Hits: 911
- Visitors: 910
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|