Bayesian Neural Networks for Internet Traffic Classification

Internet traffic identification is an important tool for network management. It allows operators to better predict future traffic matrices and demands, security personnel to detect anomalous behavior, and researchers to develop more realistic traffic models. We present here a traffic classifier that...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2007-01, Vol.18 (1), p.223-239
Main Authors: Auld, T., Moore, A.W., Gull, S.F.
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial intelligence
Bayes Theorem
Bayesian analysis
Bayesian methods
Classification
Cluster Analysis
Computer science
control theory
systems
Computer Security
Computer systems and distributed systems. User interface
Exact sciences and technology
Information security
Information Storage and Retrieval - methods
Internet
Internet traffic
IP networks
Machine learning
Mathematical models
network operations
neural network applications
Neural networks
Neural Networks (Computer)
pattern recognition
Pattern Recognition, Automated - methods
Personnel
Predictive models
Signal Processing, Computer-Assisted
Software
Telecommunication traffic
Traffic control
Traffic engineering
Traffic flow
traffic identification
Training
Training data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Internet traffic identification is an important tool for network management. It allows operators to better predict future traffic matrices and demands, security personnel to detect anomalous behavior, and researchers to develop more realistic traffic models. We present here a traffic classifier that can achieve a high accuracy across a range of application types without any source or destination host-address or port information. We use supervised machine learning based on a Bayesian trained neural network. Though our technique uses training data with categories derived from packet content, training and testing were done using features derived from packet streams consisting of one or more packet headers. By providing classification without access to the contents of packets, our technique offers wider application than methods that require full packet/payloads for classification. This is a powerful advantage, using samples of classified traffic to permit the categorization of traffic based only upon commonly available information
ISSN:1045-9227
2162-237X
1941-0093
2162-2388
DOI:10.1109/TNN.2006.883010