Experience Report: System Log Analysis for Anomaly Detection

By Shilin He, Jieming Zhu, Pinjia He, Michael R. Lyu. IEEE International Symposium on Software Reliability Engineering, 2016

589 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/2c1ed7e32a85d72fb270ebd07a45641acfba02a9

How researchers see this paper

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

In Artificial Intelligence

1. Hongyu Zhang
2. Van-Hoang Le
3. Michael R. Lyu
4. Pinjia He
5. Guineng Zheng
6. Vivek Srikumar
7. Min Du
8. Feifei Li

In Computer Networks and Communications

1. Hongyu Zhang
2. Van-Hoang Le
3. Michael R. Lyu
4. Pinjia He
5. Guineng Zheng
6. Vivek Srikumar
7. Min Du
8. Feifei Li

Citations in the corpus

• Machine Learning for Anomaly Detection: A Systematic Review (2021, background): “On the other hand, He et al. [19] surveyed the framework of log based anomaly detection.”
• LogAnomaly: Unsupervised Detection of Sequential and Quantitative Anomalies in Unstructured Logs (2019, methodology): “As for Log Clustering, PCA and Invariant Mining, we use a popular open-source toolkit implemented in [He et al., 2016].”
• LogBERT: Log Anomaly Detection via BERT (2021, unknown): “tree or SVM, are used to detect the anomalous sequences [11].”
• A Survey on Automated Log Analysis for Reliability Engineering (2020, methodology): “nting learning algorithm by dynamically selecting an optimal number of mixture components. Anomaly scores are assigned using universal test statistics whose threshold can be dynamically optimized. In [63], He et al. employed a logistic regression model to detect anomalies. They adopted event count v”
• DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning (2017, methodology): “…that could be satisfied by the majority of vectors, and then treats those vectors that do not satisfy these invariants as abnormal execution sessions. approach is shown to be more effective than an earlier work [11] which utilizes workflow automata. implementation is open-sourced by [17].”
• Log-based Anomaly Detection Without Log Parsing (2021, methodology): “) used in the previous work [28], [48], [8].”
• Benchmarking Small Language Models and Small Reasoning Language Models on System Log Severity Classification (2026, unknown): “Due to this specialization, developers may have gaps in their understanding of overall system behaviors and relationships [28].”