|
|
RQA System Anomaly Detection
Lorenc, Jan ; Jeřábek, Kamil (referee) ; Pluskal, Jan (advisor)
The aim of the theses is to design and implement a machine learning model for anomaly detection in Y Soft's RQA system. Owing to the microservice architecture, an anomaly is considered to be a recurring occurrence of outliers in durations of service requests or a considerable variance in error rate. The thesis outlines the current data collection process in the system and defines what kind of data describe the state of the system. It devises a suitable format of data storage for its subsequent analysis. It presents algorithms commonly used to solve anomaly detection problems. The anomaly detection is designed and implemented using cluster analysis and statistical methods. Finally, the thesis evaluates the quality of the detection and the achieved results.
|
|
|
Setup of Application-Computation On-Premise Mini-Cloud Based on Kubernetes
Stuchlý, Samuel ; Ryšavý, Ondřej (referee) ; Jeřábek, Kamil (advisor)
Kubernetes je platforma na orchestráciu kontajnerov, na nasadenie a správu aplikácií v klastri. Cieľom tejto práce je porozumieť kubernetes a jeho komponentom a následne navrhnúť a sprevádzkovať optimálnu architektúru kubernetes klastru pre malý mini-cloud založený na kubernetes v areáli univerzity VUT. Táto bakalárska práca rozoberá základy kontajnerov, runtime kontajnerov, nástroje na orchestráciu kontajnerov, architektúru Kubernetes a jej komponenty a automatizačnú platformu Ansible. Ďalej obsahuje popis navrhnutej architektúry klastra, ktorá bude implementovaná. Príspevok tejto práce spočíva v návrhu architektúry kubernetes klastra, ktorý bude neskôr nasadený na pôde univerzity, pripravený na použitie.
|
|
|
Low Energy GPS Tracker Using LoRa Network
Múčka, Milan ; Jeřábek, Kamil (referee) ; Pluskal, Jan (advisor)
This thesis deals with determine location using very low power consumption device. The main target was to design and construct device using right platform and sensors for localization, sending data using IoT LoRa network and than processing data on server's side. To solve the problem, it was used community network TheThingsNetwork. In thesis I created power efficient device, which can find current location using GPS system and deliver it to user using LoRaWAN network.
|
|
|
Extending NetFlow Records for Increasing Encrypted Traffic Classification Capabilities
Šuhaj, Peter ; Jeřábek, Kamil (referee) ; Holkovič, Martin (advisor)
Master's thesis deals with selection of attributes proper for classification of encrypted traffic, with the extension of NetFlow entries with these attributes and with creating a tool for classify encrypted TLS traffic. The following attributes were selected: size of packets, inter-packet arrival times, number of packets in flow and size of the flow. Selection of attributes was followed by design of extending NetFlow records with these attributes for classifying encrypted traffic. Extension of records was implemented in language C for exporter of the company Flowmon Networks a.s.. Classifier for collector was implemented in language Python. Classifier is based on a model, for which training data were needed. The exporter contains the classifying algorithm too, the place of the classification can be set. The implementation was followed by creation of testing data and evaluation of the accuracy. The speed of the classifier was tested too. In the best case scenario 47% accuracy was achieved.
|
|
|
Security Analysis of Home IoT Network
Čikel, Tomáš ; Jeřábek, Kamil (referee) ; Pluskal, Jan (advisor)
This work focuses on the issue of the security in home IoT network. Specifically, it focuses on the security issues of commercial IoT devices and their automation systems. In the work itself, it was firstly analyzed and identified specific threats specific for our network. To address these threats, the original automation systems and firmware on the devices were replaced by open-source implementations that were configured to address discovered threats. Although, there are still several security issues in a network with an open-source implementation, a large part of the security issues which were discovered has been eliminated. The results of this work allows to configure a home IoT network using an opens-source automation system and firmware and proves that such a network is more secure than the network where the original factory-supplied automation systems and firmware on devices are used.
|
|
|
Log Analysis Using TeskaLab Platform
Kocinec, Patrik ; Jeřábek, Kamil (referee) ; Ryšavý, Ondřej (advisor)
This work describes the usage of machine learning methods for processing logging information on LogMan.io system. The work includes a description of methods of processing logging information for the purposes of security monitoring, as well as machine learning methods and principles of data processing. Subsequently, the work focuses on the introduction of the LogMan.io system and its components. Then, an application for processing logging information is designed and implemented on LogMan.io system, which uses machine learning methods to detect malign domains. When implementing the application for model training, several methods were used focusing on the accuracy of detection.
|
|
|
BitTorrent Seedbox Detection
Grnáč, Martin ; Jeřábek, Kamil (referee) ; Polčák, Libor (advisor)
Bachelor's thesis is focused on issues with monitoring and detection of seedboxes in BitTorrent network with help of netflow technology. In the theoretical part of this thesis is introduced and described P2P architecture, basics and key terms of BitTorrent architecture and theoretical definition of seedbox. There are also described specific methods which can be used for detection of network communication and next there is described process of seedbox analysis in network and process of finding its characteristics. On base of this knowledge and observations is designed a set of tools,which help with detection of seedboxes. In the practical part of this work is presented implementation of these tools and results of testing these tools.
|
|
|
Application Data Extraction from Network Protocols
Januš, Filip ; Jeřábek, Kamil (referee) ; Holkovič, Martin (advisor)
This thesis is focused on design and implementation of tool for data extraction from captured network communication. The theoretical part deal with particular network protocols, its behavior, defines keywords and apprises with used tools. Second part is focused on design and implementation of extraction tool, design of declaration language for description of protocols. In the extractor are included third-party tools for analysis particular packets and reconstruction network flows. These tools together with designed declarative language are used due to requirement on easy extendability of designed tool. The end of this thesis is dedicated functional and performance testing of implemented tool.
|
|
| |
|
|
Recursive IPC Network Architecture: Analyze and Model of Enrollment
Jeřábek, Kamil ; Marek, Marcel (referee) ; Halfar, Patrik (advisor)
This thesis is focused on analysis of the Enrollment and integration of this phase to model of Recursive InterNetwork Architecture (RINA) that is developed in the OMNeT++ simulation environment. In this thesis is the RINA architecture described generally. Furthermore, there are listed cases of the Enrollment and the Common Application Connection Establishement Phase, and it is described when starts and ends. The thesis is especially focused on design and implemntation of these phases of communication in the OMNeT++ simulation environment within Pristine project.
|
guest ::
RSS feed.