Bayesian neural networks for internet traffic classification. Auld, T., Moore, A. W., & Gull, S. F. IEEE Transactions on neural networks, 18(1):223–239, IEEE, 2007. doi abstract bibtex Internet traffic identification is an important tool for network management. It allows operators to better predict future traffic matrices and demands, security personnel to detect anomalous behavior, and researchers to develop more realistic traffic models. We present here a traffic classifier that can achieve a high accuracy across a range of application types without any source or destination host-address or port information. We use supervised machine learning based on a Bayesian trained neural network. Though our technique uses training data with categories derived from packet content, training and testing were done using features derived from packet streams consisting of one or more packet headers. By providing classification without access to the contents of packets, our technique offers wider application than methods that require full packet/payloads for classification. This is a powerful advantage, using samples of classified traffic to permit the categorization of traffic based only upon commonly available information
@Article{Auld2007Bayesian,
author = {Auld, Tom and Moore, Andrew W. and Gull, Stephen F.},
journal = {IEEE Transactions on neural networks},
title = {Bayesian neural networks for internet traffic classification},
year = {2007},
issn = {1941-0093},
number = {1},
pages = {223--239},
volume = {18},
abstract = {Internet traffic identification is an important tool for network management. It allows operators to better predict future traffic matrices and demands, security personnel to detect anomalous behavior, and researchers to develop more realistic traffic models. We present here a traffic classifier that can achieve a high accuracy across a range of application types without any source or destination host-address or port information. We use supervised machine learning based on a Bayesian trained neural network. Though our technique uses training data with categories derived from packet content, training and testing were done using features derived from packet streams consisting of one or more packet headers. By providing classification without access to the contents of packets, our technique offers wider application than methods that require full packet/payloads for classification. This is a powerful advantage, using samples of classified traffic to permit the categorization of traffic based only upon commonly available information},
date = {Jan. 2007},
doi = {10.1109/TNN.2006.883010},
file = {:https\://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4049810:PDF},
issue = {1},
journaltitle = {IEEE Transactions on Neural Networks},
keywords = {Bayesian methods, Neural networks, IP networks, Telecommunication traffic, Traffic control, Information security, Personnel, Predictive models, Machine learning, Training data, Internet traffic, network operations, neural network applications, pattern recognition, traffic identification},
publisher = {IEEE},
}
Downloads: 0
{"_id":"uTbBebEWKeKvawruq","bibbaseid":"auld-moore-gull-bayesianneuralnetworksforinternettrafficclassification-2007","authorIDs":["23FvDKJM79risFbvk","2WRdLjsYbtmJQGXTj","3TdN7rFeMEefY9Hk7","3rTL65wF3DnHKjPrH","4D4M2oJhgoxJWmkcN","5e544e2f7a758fde010001b9","5e5456f588d190df01000080","5e546e797f0f44de01000043","5e54722a7f0f44de01000067","5e554f16e89e5fde0100002a","5e56ad6de177dede01000101","5e592f5fe60e02de010000a8","5e5b8cd399fee0df0100052f","5e5d95b05726ecdf0100009d","5e5e61c85f9e7bee010001b2","5e5ecf0f8c261adf010000e3","5e60f44831c7d3de0100009c","5e610d751cc34ede01000001","5e63cd1278da4fdf01000009","5e64eac85fc0b7de01000024","5e657177de41b9df01000190","5e666d8f46e828de010002c0","5e66782c152d6bde010000ad","5e66bc684b4a62de01000140","5e671b0e0355fddf0100001a","5e67421e4d24a6df0100009a","5e680874c1fce0de01000287","5e6902b38457bade0100024c","5e69eebe3aab3cdf0100027c","5e6b02dd69285ede010000d4","6dtSpmYM2v5HiJ9ko","7PYozaA4XxD8TMSWu","7v67D8gAyyrYcYL8n","8FAeKWJrSQzGoH9xE","92btiJpxxLrqAXgMn","9RzNnQ6CDTvwDBvLk","9xFPbGnxzbTckjz9c","AKtnLn9iXuKfsKnvb","BFbxJdJp2sdQE6jab","C42bg96aJPxALZDMj","DtNfHaeJrKpfNoJ6Y","EjCF3Z7mromd37b46","FAdZj59doyPG95Ft6","FS3CaSTZahuktxKRK","FSHFxTSeaaMHc8JFN","FjBPfgDjAs9qKbrk5","FsZDw63cXDZGCg8cM","FyuCzEsmg5eZwps34","G7Zffx7BGjho2AJZF","GWQKt32StcKocqn5B","GkmLPhgRgdfPyWMpr","GuCyBeEq4CLqBYY4e","HEsiueufKRKp7GbNg","HeDJuNtADqRvbfrNq","HjfA3eJtFSPtgMBym","Jqijff5rjodf97X53","KtL6LDN8YAwLxHa65","Mkn8H8agB7ogrFqWN","NzXzmqRTuu45HnK2v","PrcWsJASY7LaFZhBB","PwRjbkKnSWC6H3n5k","R7kWfTSiqEYweDNJJ","RnYAzvE3YT6XCvYbL","RzmZwHWjFC9KDceD6","S2grxY7kvZtXmkWaz","SFyHCv2aSe3LSrsig","T24gLu9jAvzXQKDdi","TetaaoYbFZFGavtxb","TrJkGmeXPf45TAc2W","WtXExMgBkc2WjYBJt","XA7WBWWEgKAXwNJCd","Xx5DKm38fz55YJDuS","YAHhHms8w9X3eEygF","YkX9xP5ow83tk9puf","YxYksTSKXdNyMqJsi","ZL6Dbz49T8BDz5vKk","aFMaT3CuDYnbfTuK2","aYh8WXnpTgutjdTMd","appbKSaMFf3DMDdyh","bPre4gjTqMby95fE9","bwBtZ44dECqBAqL6B","byXTwmgkSDjBepE6s","dQHw4Zt3JvgfJe4LH","fRHmMjA45atDn2XE2","fswYidNG7RDWyDvav","gGhwKTHH8tmmv276q","h2nvFJ6oT6Ts8LGw8","iWm4sAET4pyRiymhf","ij4rWKxtaweP2mmoQ","j399RSNqBHhuysXLG","jBsGo5nSsKF9Aswd7","jE5oX3AQSLtsnWFq5","jQhrZRo2jakTNZXE2","jXnTqkWvn2uys2LvQ","jYoTKtmcqmnjxyeYG","nCcpY7DvabFtejfsb","nmJWcKmR9YysKb2rn","pDgAmdf6bhwdtM7xi","pmYukAPu4EpuZAnZm","qGrsAHNkXL2yfxqju","qsecNeipc9bA8BJCt","r9c22nKBKGFJSB2La","srLPnyAzJWoRtHW8E","tN3iZEGhSw5dfH6Xz","tkFNTSf2DZXQJ2S68","uhtv8BNREAX7LsJYP","uokAikkyvYZZBbmbj","v2nSToyinuWzoQD4m","vhEMZTdeqfxeNkLCx","vve5WiBtmQqb2NB9Z","vwrt7tPuWdGZn9rfW","wbMcKHXZfdcWNjsvh","xBPtJ8k7YjPfQvS3C","xnzKrBDzkkPg97c7S","y8abYWAnJv92KiDwR","ycjRe3yAeg8atdvL6","ycyAerqYNXsBXxcPX","ykErHr8DwXQjFCSFG","zyNiT5NQSkPSNGs43"],"author_short":["Auld, T.","Moore, A. W.","Gull, S. F."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Auld"],"firstnames":["Tom"],"suffixes":[]},{"propositions":[],"lastnames":["Moore"],"firstnames":["Andrew","W."],"suffixes":[]},{"propositions":[],"lastnames":["Gull"],"firstnames":["Stephen","F."],"suffixes":[]}],"journal":"IEEE Transactions on neural networks","title":"Bayesian neural networks for internet traffic classification","year":"2007","issn":"1941-0093","number":"1","pages":"223–239","volume":"18","abstract":"Internet traffic identification is an important tool for network management. It allows operators to better predict future traffic matrices and demands, security personnel to detect anomalous behavior, and researchers to develop more realistic traffic models. We present here a traffic classifier that can achieve a high accuracy across a range of application types without any source or destination host-address or port information. We use supervised machine learning based on a Bayesian trained neural network. Though our technique uses training data with categories derived from packet content, training and testing were done using features derived from packet streams consisting of one or more packet headers. By providing classification without access to the contents of packets, our technique offers wider application than methods that require full packet/payloads for classification. This is a powerful advantage, using samples of classified traffic to permit the categorization of traffic based only upon commonly available information","date":"Jan. 2007","doi":"10.1109/TNN.2006.883010","file":":https\\://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4049810:PDF","issue":"1","journaltitle":"IEEE Transactions on Neural Networks","keywords":"Bayesian methods, Neural networks, IP networks, Telecommunication traffic, Traffic control, Information security, Personnel, Predictive models, Machine learning, Training data, Internet traffic, network operations, neural network applications, pattern recognition, traffic identification","publisher":"IEEE","bibtex":"@Article{Auld2007Bayesian,\n author = {Auld, Tom and Moore, Andrew W. and Gull, Stephen F.},\n journal = {IEEE Transactions on neural networks},\n title = {Bayesian neural networks for internet traffic classification},\n year = {2007},\n issn = {1941-0093},\n number = {1},\n pages = {223--239},\n volume = {18},\n abstract = {Internet traffic identification is an important tool for network management. It allows operators to better predict future traffic matrices and demands, security personnel to detect anomalous behavior, and researchers to develop more realistic traffic models. We present here a traffic classifier that can achieve a high accuracy across a range of application types without any source or destination host-address or port information. We use supervised machine learning based on a Bayesian trained neural network. Though our technique uses training data with categories derived from packet content, training and testing were done using features derived from packet streams consisting of one or more packet headers. By providing classification without access to the contents of packets, our technique offers wider application than methods that require full packet/payloads for classification. This is a powerful advantage, using samples of classified traffic to permit the categorization of traffic based only upon commonly available information},\n date = {Jan. 2007},\n doi = {10.1109/TNN.2006.883010},\n file = {:https\\://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4049810:PDF},\n issue = {1},\n journaltitle = {IEEE Transactions on Neural Networks},\n keywords = {Bayesian methods, Neural networks, IP networks, Telecommunication traffic, Traffic control, Information security, Personnel, Predictive models, Machine learning, Training data, Internet traffic, network operations, neural network applications, pattern recognition, traffic identification},\n publisher = {IEEE},\n}\n\n","author_short":["Auld, T.","Moore, A. W.","Gull, S. F."],"key":"Auld2007Bayesian","id":"Auld2007Bayesian","bibbaseid":"auld-moore-gull-bayesianneuralnetworksforinternettrafficclassification-2007","role":"author","urls":{},"keyword":["Bayesian methods","Neural networks","IP networks","Telecommunication traffic","Traffic control","Information security","Personnel","Predictive models","Machine learning","Training data","Internet traffic","network operations","neural network applications","pattern recognition","traffic identification"],"metadata":{"authorlinks":{"moore, a":"https://www.cl.cam.ac.uk/~awm22/publications/index.html"}},"downloads":0,"html":""},"bibtype":"article","biburl":"www.cl.cam.ac.uk/~awm22/tmp/jabref-master.bib","creationDate":"2020-02-24T22:29:03.689Z","downloads":0,"keywords":["bayesian methods","neural networks","ip networks","telecommunication traffic","traffic control","information security","personnel","predictive models","machine learning","training data","internet traffic","network operations","neural network applications","pattern recognition","traffic identification"],"search_terms":["bayesian","neural","networks","internet","traffic","classification","auld","moore","gull"],"title":"Bayesian neural networks for internet traffic classification","year":2007,"dataSources":["P4oCWtW2FaLzS5ueC","Z2XGYjE5q4GTmpP4E","LoreFsEEN9tXGMfht","d8e849HkrdPEWFP7g"]}