|
|
HTTP Application Anomaly Detection
Rádsetoulal, Vlastimil ; Homoliak, Ivan (referee) ; Očenášek, Pavel (advisor)
The goal of this work is to introduce anomaly detection principles and review its possibilities, as one of the intrusion detection methods in HTTP traffic. This work contains theoretical background crucial for performing an anomaly detection on HTTP traffic, and for utilising neural networks in achieving this goal. The work proposes tailored design of an anomaly detection model for concrete web server implementation, describes its implementation and evaluates the results. The result of this work is successful initial experiment, of modeling normal behavior of HTTP traffic and creation of the mechanism, capable of detection of anomalies within future traffic.
|
|
|
Detection of Boxes in Image
Soroka, Matej ; Bartl, Vojtěch (referee) ; Herout, Adam (advisor)
The aim of this work is to experiment and evaluate different approaches of computer vision with the aim of automatic detection of boxes-blocks in the image, for this purpose, approaches based on neural networks were used in the solution. Experiments were performed with classification using our own data set, classification using our own convolutional neural network, detection using a window, YOLO detector and in the last part a proposal for improvement using U-net and MirrorNet networks.
|
|
|
Detection of Blueborne Revealed Vulnerability
Janček, Matej ; Malinka, Kamil (referee) ; Hujňák, Ondřej (advisor)
Táto práca sa zaoberá tvorbou automatickej metódy na detekciu Blueborne zraniteľností v Android zariadeniach. V riešení bola použitá metóda, ktorej základné fungovanie je z vyvolania pretečenia pamäti na zariadení. Následne výsledný nástroj vyhodnotí či sa to podarilo a, či zariadenie je zraniteľné. Nástroj bol testovaný na viacerých zariadeniach, ktoré majú rôzne verzie systému. Testovanie tejto metódy detekcie potvrdilo funkčnosť nástroja.
|
|
|
Detection of Security Incidents in Bluetooth Networks
Bárteček, Bronislav ; Hujňák, Ondřej (referee) ; Kořenek, Jan (advisor)
The goal of this bachelor thesis is to detect security incidents in Bluetooth Low Energy(BLE) networks. It was necessary to create a tool that would detect security issues in devices and monitor the activity of devices that communicate using BLE. Ubertooth was used in the solution to sniff BLE communication. Ubertooth is used to capture BLE packets, which are then decoded by the created program and analyzed. The created tool determines the device security rate from these data. At the same time, it monitors network activity and, if necessary, informs the user of unwanted device activities, such as connecting foreign devices to user devices.
|
|
|
Automated Detection of Hate Speech and Offensive Language
Štajerová, Alžbeta ; Žmolíková, Kateřina (referee) ; Fajčík, Martin (advisor)
This thesis discusses hate speech and offensive language phenomenon, their respective definitions and their occurrence in natural language. It describes previously used methods of solving the detection. An evaluation of available data sets suitable for the problem of detection is provided. The thesis aims to provide additional methods of solving the detection of this issue and it compares the results of these methods. Five models were selected in total. Two of them are focused on feature extraction and the remaining three are neural network models. I have experimentally evaluated the success of the implemented models. The results of this thesis allow for comparison of the typical approaches with the methods leveraging the newest findings in terms of machine learning that are used for the classification of hate speech and offensive language.
|
|
|
Measurement of the properties of cells grown in hydrogel
Belák, Daniel ; Janoušek, Oto (referee) ; Čmiel, Vratislav (advisor)
Main subject of this work is to present the possibilities of cultivation of cells in cultivation medium – hydrogel. Topic of the following part is introduction to the problematics of processing of the pictures made by light field microscopy and fluorescence microscopy. It studies the influence of parametres used in the process of stacking the pictures to reach the highest depth of field as possible. Last part is dedicated to measurement of the properties of cell cultures, its statistical processing and analysis.
|
|
|
Deep Learning for Object Detection
Paníček, Andrej ; Herout, Adam (referee) ; Teuer, Lukáš (advisor)
This work deals with the object detection using deep neural networks. As part of the solution, I modified, implemented and trained the well-known model of cascade neural networks MTCNN so that it could perform the detection of traffic signs. The training data was generated from GTSRB and GTSDB data sets. MTCNN showed solid performance on the evaluation data, where the detection accuracy reached 97.8 %.
|
|
|
Malicious Tor Exit Node Detection
Firc, Anton ; Zobal, Lukáš (referee) ; Polčák, Libor (advisor)
The main goal of this bachelor's thesis is to study and implement detection for malicious Tor exit nodes. This work contains information about existing solutions for detecting malicious exit nodes and techniques used for Tor malicious exit nodes detection. This work also discusses design of system for detecting malicious Tor exit nodes tampering with encrypted HTTPS communication when accessing any of the worldwide most visited websites. It describes the process of implementation and testing of designed detection tool. It also deals with detection of malicious exit nodes using implemented tool and describes incident which led to the detection and reporting of a malicious exit node.
|
|
|
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.
|
|
|
Detection and Recognition of Diabetes Disease Impacts to the Human Eye Retina
Jausch, Andrej ; Semerád, Lukáš (referee) ; Drahanský, Martin (advisor)
This bachelor's thesis deals with the design of algorithms for the recognition of a diabetes disease impacts to the human eye retina. Diabetic retinopathy is one of the most common diseases aecting the retina and its consequences lead to partial or complete weakness. The basis of the algorithm for detection is to create candidate areas from dierent viewpoints of image processing - computer vision and their subsequent analysis. Core components of the retina have impacts to detection results - optical disc and blood vessels, which need to be properly detected and subsequently excluded from processing. Testing the implemented application took place in 68 images selected from two databases. One of the possible uses of the proposed methods in the future is in combination with the retinal scanning device for the automatic detection of diabetes symptoms during the retinal screening process.
|
guest ::
