Internet traffic classification using bayesian analysis techniques

By Andrew William Moore, Denis Zuev. Measurement and Modeling of Computer Systems, 2005

1,499 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/95ae4502a59e5c1c20dbdfe497fee39705c8ae7f

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

In Computer Networks and Communications

Citations in the corpus

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities (2018, methodology): “Moore and Zuev [321] Supervised NBKE Proprietary: campus network Baseline and derivative packet-level features BULK, WWW,MAIL, SERVICES, DB, P2P, ATTACK, MULTIMEDIA N/A Accuracy upto 95%, TPR upto 99%”
SubFlow: Towards practical flow-level traffic classification (2012, methodology): “However, despite significant research efforts [14], [1], [12], these methods have not made the anticipated impact in the real world.”
A Survey on Internet Traffic Identification (2009, methodology): “Accurate traf ﬁ c classi ﬁ cation is fundamental to numerous network activities [43][44], including: (cid:129) Identi ﬁ cation of application usage and trends: the correct identi ﬁ cation of user applications and application popularity trends may give valuable information for network operators to…”
Internet traffic classification demystified: myths, caveats, and the best practices (2008, methodology): “Naive Bayes Naive Bayes Naive Bayes Naive Bayes Kernel Estimation Naive Bayes Kernel Estimation Naive Bayes Kernel Estimation Bayesian Network Bayesian Network Bayesian Network 20 20 C4.5 Decision Tree C4.5 Decision Tree C4.5 Decision Tree Support Vector Machines Support Vector Machines Support V”
Network Traffic Classification Using Correlation Information (2013, methodology): “Machine learning can automatically search for and describe useful structural patterns in a supplied traffic data set, which is helpful to intelligently conduct traffic classification [8], [7].”
Revealing skype traffic: when randomness plays with you (2007, background): “Recently they have also been adopted to classify Internet tr affic, showing very good performance, see [12] and references ther ein.”
Machine Learning Techniques for Anomaly Detection: An Overview (2013, methodology): “Moore and Zuev [35] used a supervised Naive Bayes classifier and 248 flow features to differentiate between different types of application such as packet length and inter arrival times, in addition to numerous TCP header derived features.”
BLINC: multilevel traffic classification in the dark (2005, methodology): “To address the ineﬃciency of port-based classiﬁcation, recent studies have employed statistical classiﬁcation techniques to probabilistically assign ﬂows to classes, e.g., machine learning [12] or statistical clustering [18, 15].”
Traffic classification using clustering algorithms (2006, neutral): “The limitations of port-based and payload-based analysis have motivated use of transport layer statistics for traffic classification [8, 10, 12, 14, 17].”
Advances in Cryptology - EUROCRYPT 2006 (2006, methodology): “As another example, our attacks should in fact be prevented by any RFC-compliant implementation of IPsec, because of some seemingly innocuous post-processing checks specified in the architectural standard for IPsec [15].”
Network Traffic Classifier With Convolutional and Recurrent Neural Networks for Internet of Things (2017, methodology): “They report having better results than other works using C4.5, kNN, Naïve Bayes, Bayesian Networks and Erman’ s semi-supervised methods [17]–[21].”
Characterization of Encrypted and VPN Traffic using Time-related Features (2016, background): “A number of machine learning classification methods based on flow (Bernaille and Teixeira, 2007; Moore and Zuev, 2005) and packet-based (Iliofotou et al.”
Offline/realtime traffic classification using semi-supervised learning (2007, methodology): “Traditionally, learning is accomplished using a fully labeled training data set, as has been previously considered in the traffic classification context [23,27].”
Machine Learning for Encrypted Malware Traffic Classification: Accounting for Noisy Labels and Non-Stationarity (2017, background): “While not applied directly to detecting threats in encrypted tra c, this basic formula of machine learning and network metadata has been well-researched [6, 24, 31].”