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

By Hyunchul Kim, K. Claffy, Marina Fomenkov, Dhiman Barman, Michalis Faloutsos, KiYoung Lee. Conference on Emerging Network Experiment and Technology, 2008

587 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/4a692e42b3d6599ae0cd656241ad26312f3d3970

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

In Hardware and Architecture

Citations in the corpus

MAWILab: combining diverse anomaly detectors for automated anomaly labeling and performance benchmarking (2010, background): “MAWI has enabled researchers to study Internet traffic characteristics [7, 16, 19], anomaly detectors [11, 14], and traffic classifiers [10].”
Issues and future directions in traffic classification (2012, background): “…content) or fine-grained (e.g., text, picture, audio, video, compressed, base64-encoded image, base64-encoded text) Figure 2 illustrates several different types of flow objects, the proper selection of which often depends on the purpose of classification (e.g., traffic management,…”
On dominant characteristics of residential broadband internet traffic (2009, methodology): “[23] found that port-based dete ction quality is inversely proportional to the fraction of P2P tra ffic.”
A Survey of Payload-Based Traffic Classification Approaches (2014, background): “Finally, a very interesting survey on traffic classification approaches was presented in [48].”
Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM Learning (2009, methodology): “Over the last decade, there has been an uptake in the application of SVMs used for classification to a variety of application domains such as Internet traffic classification (Kim et al., 2008), recommendation systems (Xu and Araki, 2006), web search (Joachims, 2002), cancer diagnosis (Ramaswamy et a”
Network Traffic Classification Using Correlation Information (2013, methodology): “[3] extensively evaluated ports-based CorelReef method, host behavior-based BLINC method and seven common statistical feature-based methods using supervised algorithms on seven different traffic traces.”
SubFlow: Towards practical flow-level traffic classification (2012, methodology): “The performance of previous supervised ML flow-level classifiers degrades when new applications appear: We verified this observation using a large set of real-world data and different supervised classifiers proposed in the literature [9],”
UbeHealth: A Personalized Ubiquitous Cloud and Edge-Enabled Networked Healthcare System for Smart Cities (2018, background): “DEEP LEARNING NETWORK TRAFFIC CLASSIFICATION (DLNTC) COMPONENT Traffic classification is fundamental for any network, especially mobile cloud networks for determining anomalies, for traffic prioritization over a limited bandwidth, to ensure Quality of Service (QoS) [128], [129].”
Characterization of Encrypted and VPN Traffic using Time-related Features (2016, background): “putational overhead by reducing the set of features to a set that can be extracted with low computational complexity (Kim et al., 2008; Li et al., 2009).”