Bayesian Neural Networks for Internet Traffic Classification

By Tom Auld, Andrew William Moore, Stephen F. Gull. 2007

547 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Hardware and Architecture

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jun Zhang
2. Yang Xiang
3. K. Claffy
4. Wanlei Zhou
5. Michalis Faloutsos
6. Yong Guan
7. Yang Wang
8. Thuy T. T. Nguyen

In Computer Networks and Communications

1. Jun Zhang
2. Yang Xiang
3. K. Claffy
4. Wanlei Zhou
5. Michalis Faloutsos
6. Yong Guan
7. Yang Wang
8. Thuy T. T. Nguyen

In Hardware and Architecture

1. K. Claffy
2. Wanlei Zhou
3. Jun Zhang
4. Yang Xiang
5. Yong Guan
6. Yang Wang
7. Thuy T. T. Nguyen
8. Michalis Faloutsos

Citations in the corpus

• Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers (2013, methodology): “SVM for network traffic classification As shown by the extensive literature on this topic [28, 27, 49, 15], network traffic classification is commonly realized by means of Machine Learning algorithms, like K-Means, HMM, decision trees, and SVM.”
• A comprehensive survey on machine learning for networking: evolution, applications and research opportunities (2018, methodology): “[26] Supervised BNN Proprietary Packet-level and flow-level features ATTACK, BULK, DB, MAIL, P2P, SERVICE, WWW Number of features = 246, hidden layers = 0-1, 0-30 nodes in the hidden layer, output = 10 Accuracy > 99%, 95% with temporally distant training and testing datasets”
• Internet traffic classification demystified: myths, caveats, and the best practices (2008, methodology): “Neural Networks [7, 38] is a highly interconnected net­work of units, neurons, whose output is a combination of the multiple weighted inputs from others neurons.”
• Confronting the Challenge of Modeling Cloud and Precipitation Microphysics (2020, background): “Bayesian neural networks (e.g., Auld et al., 2007; Titterington, 2004) can also provide information about uncertainty.”
• Network Traffic Classification Using Correlation Information (2013, background): “5 decision tree [11], Bayesian network [11], SVM [3], and neural networks [12], require an intensive training procedure for the classifier parameters.”
• Advances in Bayesian network modelling: Integration of modelling technologies (2019, methodology): “Bayesian neural networks have been used to forecast energy load requirements (Lauret et al., 2008), solar irradiation (Yacef et al., 2012), stock market performance (Ticknor, 2013), and internet traffic loads (Auld et al., 2007).”
• Deep packet: a novel approach for encrypted traffic classification using deep learning (2017, methodology): “proposed a Bayesian neural network that was trained to classify most well-known P2P protocols including Kazaa, BitTorrent, GnuTella, and achieved 99% accuracy (Auld et al. 2007).”
• A survey of techniques for internet traffic classification using machine learning (2008, methodology): “[55] Bayesian Neural Network 246 features in total, including:”