Mining Invariants from Console Logs for System Problem Detection

By Jian-Guang Lou, Qiang Fu, Shengqi Yang, Ye Xu, Jiang Li. USENIX Annual Technical Conference, 2010

395 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/852094207ef6083d807a5215028e46e50685acbb

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. Shilin He
3. Hongyu Zhang
4. Pinjia He
5. Jieming Zhu
6. Min Du
7. Michael R. Lyu
8. Zibin Zheng

Citations in the corpus

• Robust log-based anomaly detection on unstable log data (2019, methodology): “This is also one of the advantages of LogRobust over existing approaches [3, 10, 18, 29, 31, 44].”
• Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy (2019, methodology): “Over the past decade this log dataset has been extensively used for research in system log anomaly detection ([15, 16, 5]).”
• Spell: Streaming Parsing of System Event Logs (2016, methodology): “To alleviate the pain of diving into massive unstructured log data, in most prior work, the first and foremost step is to automatically parse the unstructured system logs to structured data [2], [3], [4], [6].”
• Experience Report: System Log Analysis for Anomaly Detection (2016, methodology): “In this paper, we review and evaluate six anomaly detection methods employing log analysis [12], [15], [26], [27], [28], [47] because of their novelty and representativeness.”
• Log Clustering Based Problem Identification for Online Service Systems (2016, methodology): “To facilitate analysis, a common practice is to parse the log messages into constant strings and parameters [6, 11, 12, 24] and form abstract log messages.”
• A Survey on Automated Log Analysis for Reliability Engineering (2020, methodology): “ assist developers in maintaining big data analytics applications such as Hadoop. They examined the differences between execution log sequences produced in lab and in production environments. Louetal.[97]werethefirsttoconsidermininginvariantsamonglogmessagesforsystemanomaly detection. Two kinds of i”
• LogBERT: Log Anomaly Detection via BERT (2021, unknown): “Hence, in most cases, an unsupervised approach is applied for detecting the anomalous sequences [12], [13].”
• Log-based Anomaly Detection Without Log Parsing (2021, background): “We compare the results of NeuralLog and five existing approaches, including Support Vector Machine-based approach (SVM) [6], Logistic Regression-based approach (LR) [10], Invariant Mining (IM) [11], LogRobust [8], and Log2Vec [48].”
• Tools and Benchmarks for Automated Log Parsing (2018, background): “Some recent work has investigated the use of machine learning techniques (e.g., PCA [18] invariant mining [34], and deep learning [10]) for anomaly detection.”
• DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning (2017, methodology): “…identifiers can group log entries together or untangle log entries produced by concurrent processes to separate, single-thread sequential sequences [22, 39, 42, 45]. state-of-the-art log parsing method is represented by Spell [9], an unsupervised streaming parser that parses incoming log entries…”