Anomal flow detection is an important cornerstone in the field of network security, and has been widely used in various fields. Traditional anomal flow detection schemes are usually based on statistical methods for flow detection. However, with the rapid development of artificial intelligence technology, more and more anomal flow detection schemes are mainly based on machine learning and deep learning, and their application scope is also becoming more and more extensive. Due to the shortcomings of a single model, research on flow detection using multiple models is increasing. Researchers hope to use multiple model schemes to improve the performance of flow detection, but in the use of multiple models, there are many problems such as the number of models and the difficulty of selecting multiple combinations. Based on the F2HDM (Filtering 2-stage Hybrid Detection Method) in multiple model schemes, this paper conducts a mathematical analysis of it, studies model selection issues in different scenarios, proposes a method to calculate the performance of multiple models based on the parameters of a single model, and selects the appropriate combination of anomal flow detection multiple models according to the desired scenario. Finally, we demonstrate through experiments that the selection method proposed in this article has high accuracy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.