Bc. Vladimír Kravčík

Bachelor's thesis

Attacks on censorship circumvention with intrusion detection systems

Attacks on censorship circumvention with intrusion detection system
Abstract:
V tejto práci skúmame nástroj Protozoa na obchádzanie cenzúry a hodnotíme jeho odhaliteľnosť pomocou klasifikácie založenej na strojovom učení. Najprv Protozou preskúmame a analyzujeme jej dizajn a architektúru. Ďalej ilustrujeme proces zhromažďovania datasetu s bežnými prenosmi a prenosmi vytvorenými pomocou Protozoi, ktoré obsahujú utajované údaje. Potom použijeme tento dataset na trénovanie binárneho …more
Abstract:
In this thesis, we study the censorship circumvention tool Protozoa and evaluate its detectability using classifiers based on machine learning. First, we examine Protozoa and analyze its design and architecture. Next, we describe the process of collecting a dataset of ordinary traffic and traffic created by Protozoa that contains covert data. We then use this dataset to train a binary classifier and …more
 

Keywords

censorship circumvention traffic classification covert channel machine learning XGBoost
 
Language used: English
Date on which the thesis was submitted / produced: 15. 12. 2022
Identifier: https://is.muni.cz/th/cvigq/

Thesis defence

  • Date of defence: 30. 1. 2023
  • Supervisor: RNDr. Adam Janovský
  • Reader: Mgr. et Mgr. Jan Krhovják, Ph.D.

Citation record

Cite this text

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky
Složka Reference to the local database directory of the institution