Traffic classification through simple statistical fingerprinting

By Manuel Crotti, Maurizio Dusi, Francesco Gringoli, Luca Salgarelli. CCRV, 2007

451 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/cb6548ccba0c373073cd78280b98f49c8b6f5665

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

Deep Learning for Intelligent Wireless Networks: A Comprehensive Survey (2018, background): “In the past several years, traffic identification methods using statistical models [91], [92] or machine learning [93]–[95] have been extensively studied, for which the traffic features such as time interval between packets, packet size, etc.”
Real Time Identification of SSH Encrypted Application Flows by Using Cluster Analysis Techniques (2009, methodology): “[2] used only size and inter-arrival time of first n packets to create a statistical descriptor (a Fingerprint) of an application layer protocol: this fingerprint is then used to measure the similarity of a certain flow to the corresponding protocol.”
A survey of techniques for internet traffic classification using machine learning (2008, background): “Some ( [53] and [61]) have explored the performance of ML classifiers that utilise only the first few packets of a flow, but they cannot cope with missing the flow’s initial packets.”
A Survey of Payload-Based Traffic Classification Approaches (2014, methodology): “Thus, the traffic classifiers L7-filter [65] [66] and OpenDPI [67] [68] are often used to obtain the ground truth of traffic traces.”
Internet traffic classification demystified: myths, caveats, and the best practices (2008, methodology): “Previous efforts on flowfeatures-based classification [29, 31, 36, 9, 16, 7, 14, 42, 20, 39] have shown that bidirectional TCP flow statistics provide such fingerprints for various applications.”
Support Vector Machines for TCP traffic classification (2009, methodology): “We have recently introduced a new supervised ML approach based on the notion of protocol fingerprints [7].”
Offline/realtime traffic classification using semi-supervised learning (2007, background): “[7] use a classification framework that is similar to our previous work [11].”
Network Traffic Classification Using Correlation Information (2013, background): “[19] proposed the probability density function (PDF)-based protocol fingerprints to express three traffic statistical properties in a compact way.”
Deep packet: a novel approach for encrypted traffic classification using deep learning (2017, background): “[22] proposed protocol fingerprints based on the probability density function (PDF) of packets inter-arrival time and normalized thresholds.”