What is it about?
State machine models can be used to model the behaviour of a network or a system. We show in this work that we can infer a model from NetFlow data extracted from a microservice architecture system(specifically Kubernetes) and use the model to monitor and detect network anomalies that occur during the run-time of the system.
Featured Image
Why is it important?
Currently, little or no work has been done on inferring a state machine model from a microservice architecture system and using the learned model to detect anomalies during the run-time of the microservice architecture system. We show in this work that we can infer such models from a microservice architecture and use it to accurately detect anomalies occurring during the system's run-time.
Perspectives
We hope that this work can encourage more researchers to apply state machine models to microservice architecture systems or other types of system architectures. We believe that state machine models can help system administrators to better understand the run-time behaviour of their system. We hope the readers can get useful insights into the applications of state machine models
Clinton Cao
Technische Universiteit Delft
Read the Original
This page is a summary of: Learning State Machines to Monitor and Detect Anomalies on a Kubernetes Cluster, August 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3538969.3543810.
You can read the full text:
Contributors
The following have contributed to this page
