|
|
Fingerprinting Attacks on Anonymity Systems
Krajči, Martin ; Holop, Patrik (referee) ; Malinka, Kamil (advisor)
Táto diplomová práca sa zaoberá fingerprintigovými útokmi v anonymizačných systémoch, najmä v sieti Tor. Takýto útok bol navrhnutý a vykonaný v prostredí reálneho sveta s cieľom ukázať dopad chýb, ktoré sa nachádzali v predošlých štúdiách. Tri datasety zo zatvoreného sveta a jeden dataset z otvoreného sveta boli vytvorené a použité na trénovanie a testovanie N-shot learning klasifikátora. Prvý dataset bol získaný prehliadaním webových stránok webovým prehliadačom v predvolenej konfigurácii, druhý dataset bol získaný z rovnakej konfigurácie ale z inej krajiny a tretí dataset bol získaný prehliadaním webových stránok webovým prehliadačom so zapnutým rozšírením Adblock Plus a s nastaveným španielskym lokálom. V prípade, že bol klasifikátor trénovaný aj testovaný na prvom datasete, priemerná presnosť klasifikácie dosahovala 92%. Avšak ak bol klasifikátor trénovaný na prvom datasete a testovaný na druhom a treťom datasete, priemerná presnosť klasifikácie dosahovala 38,58% a 39,65% v danom poradí.
|
|
| |
|
|
Web visualization and demonstrator of anonymous credentials
Chwastková, Šárka ; Malina, Lukáš (referee) ; Dzurenda, Petr (advisor)
This thesis deals with the topic of attribute based credentials with revocable anonymous credentials. The main focus of this work is the implementation of this scheme through a web application. The web application serves primarily as a visualization, which shows the functionality of this scheme through animations, and also as a practical demonstrator. Data and cryptographic calculations for individual system protocols are provided by the given cryptographic C application that communicates with the created application. The web application is also able to communicate with the connected smart card reader and the MultOS smart card and thus create the transmission of APDU commands and responses between the smart card and provided C application.
|
|
|
Anonymization of PCAP Files
Navrátil, Petr ; Hynek, Jiří (referee) ; Holkovič, Martin (advisor)
This diploma thesis deals with the design and implementation of an application suitable for the anonymization of PCAP files. The thesis presents TCP/IP model and for each layer highlights attributes that can be used to identify real people or organizations. Some of the anonymization methods suitable to modify highlighted attributes and sensitive data are described. The implemented application uses TShark tool to parse byte data of PCAP format to JSON format that is used in the application. TShark supports lots of network protocols which allows the application to anonymize various attributes. Anonymization process is controlled by anonymization politics that can be customized by adding new attributes or anonymization methods.
|
|
|
Video Anonymization
Mokrý, Martin ; Bartl, Vojtěch (referee) ; Herout, Adam (advisor)
The goal of this thesis is to design and create an automatic system for video anonymization. This system makes use of various object detectors on an image to ensure functionality, as well as active tracking of objects detected in this manner. Adjustments are later applied to these detected objects which ensure sufficient level of anonymization. The main asset of this system is speeding up the anonymization process of videos that can be published after.
|
|
| |
|
|
Car Licence Plate Anonymization
Skřivánková, Barbora ; Zachariášová, Marcela (referee) ; Drahošová, Michaela (advisor)
While browsing an online map server, continuous photographs of certain places can be browsed as well. When the map service takes pictures of a public space, there are some personal data captured as well (i.e. faces, car licence plates). The goal of this thesis is the design of automated car licence plates anonymization system, optimized for the Panorama service provided by the Seznam.cz a.s. corporation. In this thesis, the process of car licence plate anonymization is divided into two parts: the first one solves a detection of cars and the second solves a car licence plate localization in the selected image. The car detection is based on the deep neural network approach, the car licence plate localization is solved by using a fully connected neural network performing a regression task. The goal of this thesis is to get over the disadvantages of commercial solution used nowadays. These are false posititive results and high computational complexity. Results of this thesis are not as good as expected. The reason could be a dataset provided by Seznam.cz a.s. corporation, which seemed to be robust enough in the beginning, but in the end it showed up to be not suffice enough to train the neural network.
|
|
|
Toolbox for neuronal datasets
Malý, Lukáš ; Harabiš, Vratislav (referee) ; Lamoš, Martin (advisor)
The aim of this bachelor's thesis was to create toolbox for functional magnetic resonance (fMRI) and electroencefalography (EEG) data processing in MATLAB enviroment using SPM software package. The first part describes the physiological origin of these data at neuronal level, basics of magnetic resonance imaging, principles of fMRI experiment, preprocessing and processing of fMRI data, their interpretation, then function and principles of EEG are described and at the end is simultaneous EEG-fMRI described. In the second part of the thesis features of each tool from Neural Data Toolbox (NDTb) are described.
|
|
|
Face Anonymizer
Peša, Jan ; Juránek, Roman (referee) ; Láník, Aleš (advisor)
In this bachelor thesis you can find an overview of classification algorithms and their usage especially for searching image data and face detection. First part contains a brief introduction to a pattern recognition, a theoretical background of these algorithms and ways of training them. Other used components are also presented (e.g. Kalman filter or OpenCV library). Second part covers an implementation of the application which uses these technologies for searching, tracking and anononymization of human faces in a video stream.
|
|
|
Application for Video Tracking
Borek, Martin ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
Předložená bakalářská práce pojednává o implementaci aplikace Video Anonymizer. Tato aplikace sleduje objekty ve videu a upravuje jejich vzhled. Práce se zabývá zpracováním videa s použitím knihovny FFmpeg, kde se zaměřuje především na vyhledávání snímků. Soustřeďuje se také na sledování více objektů, úpravu jejich trajektorií a na jejich anonymizaci; upřednostňovaný způsob anonymizace je rozmazání objektu. Dále je zde rozebráno vytváření vícejazyčného uživatelsky přívětivého grafického uživatelského rozhraní s pomocí knihovny QT. Při testování uživatelské přívětivosti tohoto grafického uživatelského rozhraní bylo zjištěno, že aplikace je snadno ovladatelná již při jejím prvním použití. Také bylo ověřeno, že uživatelská nápověda obsahuje všechny potřebné informace a je snadno dostupná přímo z aplikace.
|
guest ::
