November 14, 2018 Thesis Open Access

tewodros hailu

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.20372/nadre:4488</identifier>
  <creators>
    <creator>
      <creatorName>tewodros hailu</creatorName>
    </creator>
  </creators>
  <titles>
    <title>Network Traffic Classification Using Machine Learning: A Step Towards Over-the-Top Bypass Fraud Detection</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2018</publicationYear>
  <dates>
    <date dateType="Issued">2018-11-14</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Thesis</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://nadre.ethernet.edu.et/record/4488</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.20372/nadre:4487</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://nadre.ethernet.edu.et/communities/aau</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://nadre.ethernet.edu.et/communities/zenodo</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="http://www.opendefinition.org/licenses/cc-by">Creative Commons Attribution</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Over-the-Top (OTT) bypass is a type of Interconnect Bypass fraud where regular&lt;br&gt;
voice calls are rerouted through OTT network and terminated as an OTT call. These&lt;br&gt;
calls are terminated using OTT applications which need user&amp;rsquo;s Mobile Station International&lt;br&gt;
Subscriber Directory Number (MSISDN) for authentication. Detecting&lt;br&gt;
OTT voice call packets through different network traffic classification techniques is&lt;br&gt;
one subtask in the detection of this fraud.&lt;br&gt;
In this thesis, performance of three machine learning algorithms; Adaptive Booster&lt;br&gt;
(AdaBoost) + J48, Repeated Incremental Pruning to Produce Error Reduction (RIPPER),&lt;br&gt;
and Support Vector Machine (SVM) is evaluated in detecting MSISDN-based OTT&lt;br&gt;
packets taking Viber, Tango, and Telegram as a sample. Detection of OTT traffic&lt;br&gt;
and voice call packets from the OTT traffic have been treated separately as classification&lt;br&gt;
tasks. Ten cross-fold and separate test data validation techniques together&lt;br&gt;
with 1.7 million labeled packets generated and captured in controlled laboratory&lt;br&gt;
environment are used in the evaluation process.&lt;br&gt;
AdaBoost + J48 achieved the best accuracy on both classification tasks compared to&lt;br&gt;
the others while using ten cross-fold validation. However, an accuracy of 48.4%&lt;br&gt;
obtained in detecting voice call packets while using separate test data validation&lt;br&gt;
makes it less preferable in the classification task. Even if it takes longer time to&lt;br&gt;
train SVM, it was the best performer (95.35% accurate) in detecting voice call packets&lt;br&gt;
in separate test data validation. Considering accuracy attained by the algorithms&lt;br&gt;
in separate test data validation technique together with the detection rate&lt;br&gt;
of OTT voice call packets, SVM is preferable than the other two algorithms&lt;/p&gt;</description>
  </descriptions>
</resource>