BLINC: multilevel traffic classification in the dark

By Thomas Karagiannis, Konstantina (Dina) Papagiannaki, Michalis Faloutsos. Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication, 2005

1,292 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/8b1df0da70d459b8aaefac4362d9e63b9e688cf0

How researchers see this paper

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

Citations in the corpus

Profiling internet backbone traffic: behavior models and applications (2005, background): “Concurrent with our work, [20, 21] are most similar in spirit, and in a sense are complimentary, to ours.”
P4p: provider portal for applications (2008, background): “These devices rely on deep packet inspection or other P2P traffic identification schemes (e.g., [ 11 , 31]).”
Deep packet: a novel approach for encrypted traffic classification using deep learning (2017, methodology): “There have been abundant studies on the network traffic classification subject [9, 10, 5].”
A survey of methods for encrypted traffic classification and analysis (2015, background): “A visual representation of transport-layer interactions for various applications [67]”
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., 2007; Karagiannis et al., 2005) features have been proposed in the literature to identify traffic accurately.”
Bayesian Neural Networks for Internet Traffic Classification (2007, background): “[8] present a more-generic classification scheme that, inst ead of examining individual flows, it looks at patterns of flows among sets of ports and hosts.”
A comprehensive survey on machine learning for networking: evolution, applications and research opportunities (2018, background): “However, the accuracy of the host behavior-based traffic classification strongly depends on the location of the monitoring system, especially since the observed communication pattern may be affected by routing asymmetries in the network core [229].”
No NAT'd User Left Behind: Fingerprinting Users behind NAT from NetFlow Records Alone (2014, background): “Ta rg et User and Host Profiling [22], [21] [34], [35], [32], [4], [16], [24] [36], [12] Traffic and Application Profiling [3], [25], [28] [37], [23], [15], [29] [6] Information Leaks [19], [30], [5], [33] Device Profiling [17], [11], [8]”
Issues and future directions in traffic classification (2012, background): “Identifying particular traffic classes or applications (e.g., VoIP or Skype) requires discerning even more specific features, and must contend with application software changes, including those designed to preclude classification.”
Traffic classification using clustering algorithms (2006, methodology): “developed another method that uses the social, functional, and application behaviors to identify all types of traffic [9].”
Traffic classification through simple statistical fingerprinting (2007, methodology): “The resulting 40+ GB traces were then run through a payload-based, pattern-matching classifier that we built, according to the patterns described in [5] and [17].”
PeerRush: Mining for unwanted P2P traffic (2013, background): “Because modern P2P applications avoid using fixed port numbers and implement encryption to prevent DPI-based detection [15], more recent work has addressed the problem of identifying P2P traffic based on statistical traffic analysis [12, 13].”
A Survey on Internet Traffic Identification (2009, methodology): “In [43], Karagiannis et al present an important seminal and novel approach to classify traffic flows according to application groups, e.”
A survey of techniques for internet traffic classification using machine learning (2008, methodology): “[15] developed an application classification method based on the behaviours of the source host at the transport layer, divided into three different levels.”
Offline/realtime traffic classification using semi-supervised learning (2007, methodology): “developed a method that leverages the social, functional, and application behaviors of hosts to identify traffic classes [18].”
Real Time Identification of SSH Encrypted Application Flows by Using Cluster Analysis Techniques (2009, background): “In [1], Karagiannis et al.”