A preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification

By N. Williams, Sebastian Zander, Grenville J. Armitage. CCRV, 2006

784 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/3f18dd7ff7a6d442d8c28b1cade2149bd105a365

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

Machine Learning Based Intrusion Detection Systems for IoT Applications (2019, background): “The main reason behind computing MBT is that it is very important to consider the training time a model takes, as it would directly impact the resources usage, which is an important criterion for resourceconstrained devices [66].”
Issues and future directions in traffic classification (2012, background): “Traffic classification techniques in the literature have not kept pace with these three challenging trends.”
A comprehensive survey on machine learning for networking: evolution, applications and research opportunities (2018, background): “Examples of feature selection techniques include, colored traffic activity graphs (TAG) [221], breadth-first search (BFS) [496], L1 Regularization [259], backward greedy feature selection (BGFS) [137], consistency-based (CON) and correlation-based feature selection (CFS) [321, 476].”
Machine Learning for Encrypted Malware Traffic Classification: Accounting for Noisy Labels and Non-Stationarity (2017, methodology): “For example, linear regression using the more expressive feature set easily outperformed the random forest method using a standard network connection representation [39] on all criteria that we considered.”
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”
A Survey on Internet Traffic Identification (2009, methodology): “The most frequently discussed method is the Bayesian analysis technique as in [44][53], but some papers compare different methods [54][55][56].”
Cloudy with a Chance of Breach: Forecasting Cyber Security Incidents (2015, background): “, [52]; more is explained in Section 4.”
Network Traffic Classification Using Correlation Information (2013, methodology): “5 [11], BayesNet [11], and Erman’s clustering-based method [10].”
State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems (2017, neutral): “While classifiers like naive Bayes, decision trees, and neural networks [177]–[179] are”
Support Vector Machines for TCP traffic classification (2009, background): “Williams et al. [12] extensively reported about ML approaches for traffic classification .”
SVM Parameter Optimization using Grid Search and Genetic Algorithm to Improve Classification Performance (2016, background): “The main goal of classification is to apply machine learning algorithms to achieve the best prediction accuracy [2].”
A survey of techniques for internet traffic classification using machine learning (2008, methodology): “[65] Naive Bayes with Discretisation, Naive Bayes with Kernel Estimation, C4.”
Characterization of Encrypted and VPN Traffic using Time-related Features (2016, background): “Flows are considered to be bidirectional (forward and reverse directions) as in most of the reviewed papers (e.g.,(McGregor et al., 2004; Zander et al., 2005; Bernaille et al., 2006; Williams et al., 2006; Palmieri and Fiore, 2009)).”
Offline/realtime traffic classification using semi-supervised learning (2007, background): “[30] presented a preliminary comparison of five supervised learning algorithms.”