Understanding the Limits of Deep Packet Inspection for Network Traffic Classification
Abstract
We present our human network application labeling system that contributes a new level of distinction between the network traffic that should be labeled from the network traffic that should not be labeled. This distinction improves the label accuracy of the training data set produced from the human labeled data and will subsequently improve the performance of supervised machine learning classifiers used for network traffic classification. This system also allows for the human network user to label traffic, with little effort, in a manner consistent with normal network usage, i.e., no need for a contrived experiment. Lastly, we use human supplied ground truth network application labels to analyze the performance of deep packet inspection techniques, specifically the nDPI library.
Subject Area
Computer Engineering|Information Technology
Recommended Citation
Ramey, Herman Foston, "Understanding the Limits of Deep Packet Inspection for Network Traffic Classification" (2024). ETD Collection for University of Texas, El Paso. AAI31327577.
https://scholarworks.utep.edu/dissertations/AAI31327577