2021
DOI: 10.48550/arxiv.2108.01955
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Log-based Anomaly Detection Without Log Parsing

Abstract: Software systems often record important runtime information in system logs for troubleshooting purposes. There have been many studies that use log data to construct machine learning models for detecting system anomalies. Through our empirical study, we find that existing log-based anomaly detection approaches are significantly affected by log parsing errors that are introduced by 1) OOV (out-of-vocabulary) words, and 2) semantic misunderstandings. The log parsing errors could cause the loss of important inform… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 53 publications
0
1
0
Order By: Relevance
“…Several studies have proposed to use self-attention with different transformer variants to detect HPC anomalies. These approaches rely on self-attention-based transformer-decoder [48], self-attention with different transformer-encoder variants [49], [50]. Compared to these approaches, our Time Machine is a real-time generative model for predicting log events, components (e.g., node) failures, and the lead time to the predicted failures in HPC systems via utilizing two stacks of self-supervised transformer-decoders.…”
Section: Related Workmentioning
confidence: 99%
“…Several studies have proposed to use self-attention with different transformer variants to detect HPC anomalies. These approaches rely on self-attention-based transformer-decoder [48], self-attention with different transformer-encoder variants [49], [50]. Compared to these approaches, our Time Machine is a real-time generative model for predicting log events, components (e.g., node) failures, and the lead time to the predicted failures in HPC systems via utilizing two stacks of self-supervised transformer-decoders.…”
Section: Related Workmentioning
confidence: 99%