LogDP: Combining Dependency and Proximity for Log-Based Anomaly Detection

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 sequences to detect anomalies in massive unlabeled data. LogDP divides into dependent independent events, then learns normal patterns based on dependencies deviation values from historic mean. Events violating any pattern are identified as anomalies. By combining proximity, able achieve high accuracy. Extensive experiments have been conducted real-world datasets, results show outperforms six state-of-the-art methods.