Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/118047
Title: Detector de covert timing channels basat en machine learning
Author: Martínez Villamarín, Patrik
Director: Rifà-Pous, Helena  
Tutor: Lerch-Hostalot, Daniel  
Abstract: The main objective of this Master's Thesis is to design and implement a machine learning-based tool to detect covert network traffic according to the mechanism of alteration of the PDU order. A method not described in the literature that allows a message to be hidden using the RTP protocol PDUs to transmit video and audio has been designed and implemented. The resulting traffic distribution function meets the criteria to consider the method undetectable. From the data set obtained from the network traffic with both unaltered flow and one with a hidden message, the characteristics are extracted with an adaptation of the PPD method to train the classifier. The obtained features are used to train a classifier that is tested in different scenarios with 95,7% detection capacity for short messages.
Keywords: covert channel
machine learning
steganography
countermeasures
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 2-Jun-2020
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 

PatrikMartinez_Presentacio_TFM.mp4

Vídeo de la presentació del treball.319,98 MBMP4View/Open
pmartinezviTFM0620memòria.pdfMemòria del TFM2,13 MBAdobe PDFThumbnail
View/Open