LogBERT: Log Anomaly Detection via BERT

By Haixuan Guo, Shuhan Yuan, Xintao Wu. IEEE International Joint Conference on Neural Network, 2021

437 citations recorded by the source corpus.

Detecting anomalous events in online computer systems is crucial to protect the systems from malicious attacks or malfunctions. System logs, which record detailed information of computational events, are widely used for system status analysis. In this paper, we propose LogBERT, a self-supervised framework for log anomaly detection based on Bidirectional Encoder Representations from Transformers (BERT). LogBERT learns the patterns of normal log sequences by two novel self-supervised training tasks, masked log message prediction and volume of hypersphere minimization. After training, LogBERT is able to capture the patterns of normal log sequences and further detect anomalies where the underlying patterns deviate from expected patterns. The experimental results on three log datasets show that LogBERT outperforms state-of-the-art approaches for anomaly detection.

View Paper: https://www.semanticscholar.org/paper/38c0543aa72b68d1ded4237e8cc5333b165ea249

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Van-Hoang Le
2. Hongyu Zhang
3. Jian Zhang

Citations in the corpus

• Log-based Anomaly Detection Without Log Parsing (2021, methodology): “automatically detect anomalies by analyzing log data [3], [4], [5], [6], [7], [8], [9].”