TU Darmstadt / ULB / TUbiblio

Discriminating if a network flow could have been created from a given sequence of network packets

Keim, Jens (2022)
Discriminating if a network flow could have been created from a given sequence of network packets.
Technische Universität Darmstadt
doi: 10.26083/tuprints-00020630
Bachelorarbeit, Erstveröffentlichung, Verlagsversion

Kurzbeschreibung (Abstract)

This thesis aims to design a neural network (NN), that is capable of discriminating if a network flow could have been created based on a sequence of packets and can be used as a discriminative network (DN) for a Generative Adversarial Network (GAN) in future work.

For this, we first determined the features of network flows and packets alike, which are relevant to this task. We then created a dataset by extracting the relevant features from well-known network traffic datasets from the field of network intrusion detection (NID), as well as falsifying said datapoints to provide negative samples. We also provide a pipeline for the process of creating such datasets.

For our NN model we compared available architectures of recurrent neural networks (RNNs): simple RNN (simpleRNN), Long Short Term Memory (LSTM), and Gated Recurrent Units (GRUs). Furthermore our model uses a special kind of RNN called a conditional RNN (condRNN), which already has provided good results for a mixture of conditional and sequential input in the field of image region classification. This is necessary as a flow is the conditional counterpart to a sequence of packets. We aim to test the effectiveness of the different RNN architectures in regards to our problem and in the context of condRNNs.

Typ des Eintrags: Bachelorarbeit
Erschienen: 2022
Autor(en): Keim, Jens
Art des Eintrags: Erstveröffentlichung
Titel: Discriminating if a network flow could have been created from a given sequence of network packets
Sprache: Englisch
Referenten: Mühlhäuser, Prof. Dr. Max ; Garcia Cordero, Dr. Carlos ; Wainakh, Aidmar
Publikationsjahr: 2022
Ort: Darmstadt
Kollation: 71 Seiten
Datum der mündlichen Prüfung: 11 September 2020
DOI: 10.26083/tuprints-00020630
URL / URN: https://tuprints.ulb.tu-darmstadt.de/20630
Zugehörige Links:
Kurzbeschreibung (Abstract):

This thesis aims to design a neural network (NN), that is capable of discriminating if a network flow could have been created based on a sequence of packets and can be used as a discriminative network (DN) for a Generative Adversarial Network (GAN) in future work.

For this, we first determined the features of network flows and packets alike, which are relevant to this task. We then created a dataset by extracting the relevant features from well-known network traffic datasets from the field of network intrusion detection (NID), as well as falsifying said datapoints to provide negative samples. We also provide a pipeline for the process of creating such datasets.

For our NN model we compared available architectures of recurrent neural networks (RNNs): simple RNN (simpleRNN), Long Short Term Memory (LSTM), and Gated Recurrent Units (GRUs). Furthermore our model uses a special kind of RNN called a conditional RNN (condRNN), which already has provided good results for a mixture of conditional and sequential input in the field of image region classification. This is necessary as a flow is the conditional counterpart to a sequence of packets. We aim to test the effectiveness of the different RNN architectures in regards to our problem and in the context of condRNNs.

Status: Verlagsversion
URN: urn:nbn:de:tuda-tuprints-206306
Sachgruppe der Dewey Dezimalklassifikatin (DDC): 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Telekooperation
Hinterlegungsdatum: 09 Mai 2022 12:01
Letzte Änderung: 10 Mai 2022 06:49
PPN:
Referenten: Mühlhäuser, Prof. Dr. Max ; Garcia Cordero, Dr. Carlos ; Wainakh, Aidmar
Datum der mündlichen Prüfung / Verteidigung / mdl. Prüfung: 11 September 2020
Zugehörige Links:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen