Bayesian Neural Networks for Internet Traffic Classification

@article{Auld2007BayesianNN,
  title={Bayesian Neural Networks for Internet Traffic Classification},
  author={Tom Auld and Andrew W. Moore and Stephen F. Gull},
  journal={IEEE Transactions on Neural Networks},
  year={2007},
  volume={18},
  pages={223-239}
}
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… CONTINUE READING

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • A classification accuracy of over 99% when training and testing on homogeneous traffic from the same site on the same day.

Citations

Publications citing this paper.
SHOWING 1-10 OF 280 CITATIONS

Internet traffic classification demystified: myths, caveats, and the best practices

VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Traffic identification method based on multiple probabilistic neural network model

  • Neural Computing and Applications
  • 2017
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Designing an accurate and efficient classification approach for network traffic monitoring

VIEW 13 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Network traffic application identification based on message size analysis

  • J. Network and Computer Applications
  • 2015
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2007
2019

CITATION STATISTICS

  • 28 Highly Influenced Citations

  • Averaged 15 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 41 REFERENCES

http://www.tcptrace .org

Shawn Ostermann
  • tcptrace,
  • 2003
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Moore and Denis Zuev . Internet traffic classification using bayesian analysis techniques

W Andrew
  • Proceedings of ACM Sigmetrics
  • 2005