|
|
Real-Time Detection of Malware Campaigns
Holop, Patrik ; Polčák, Libor (referee) ; Zobal, Lukáš (advisor)
Táto práca sa zaoberá detekciou kampaní škodlivého softwaru v reálnom čase na základe dostupných dát z interných nástrojov spoločnosti Avast Software. Jej cieľom je navrhnúť a implementovať systém, ktorý dokáže automatizovane zachytávať a spracovávať správy o vzniknutých udalostiach a incidentoch u klientov, získať z nich potrebné informácie a vyhodnotiť, či sa jedná o prebiehajúcu kampaň škodlivého softwaru na základe rôznych kritérií. Experimentovanie potvrdzuje, že detegovanie kampaní na základe podrobne vybratých parametrov a metrík je možné. Implementovaný systém je integrovaný pre spoluprácu s internými nástrojmi spoločnosti Avast Software. Táto práca taktiež navrhuje možné vylepšenia detekčného procesu.
|
|
|
Segmentation of arterial wall in high resolution retinal images
Polachová, Natálie ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
This thesis focuses on automatic segmentation of retinal arterial walls in images acquired using adaptive optics. Adaptive optics is a non-invasive imaging method that provides high lateral resolution and allows detailed observation of retinal microstructures, including arterial walls. This technology is crucial for early diagnosis of serious diseases such as arterial hypertension and diabetic retinopathy. The main objective of this work was to detect the arterial lumen and segment its walls. Morphological and filtration techniques were used for lumen detection. For arterial wall segmentation, brightness profiles along the detected lumen were analyzed and active contour and spline methods were used. The results show that the active contour segmentation method improves the accuracy of arterial wall detection, especially in high-contrast regions. This thesis summarizes the findings and proposes improvements in the detection of the inner side of the arterial wall, which reduces the segmentation success rate in this work.
|
|
|
Detection of parking space availability based on video
Kužela, Miloslav ; Zelený, Ondřej (referee) ; Frýza, Tomáš (advisor)
Detekování obsazenosti parkovacích míst je často řešeno použitím senzorů umístěných v blízké lokaci parkovacího místa. Se vzrůstem strojového učení je možnost využití této technologie za použití kamer a detekčních algoritmů. Práce se zabývá právě vytvořením a použitím takového modelu k detekci obsazenosti parkoviště. Probírá existující modely a detektory, vytvoření vlastního datasetu s konkrétní strukturou, vytvoření a naučení různých typů modelů a probrání vysledků při testování daných modelů na vlastních záznamech z parkovací plochy. Poté následné vytvoření webové aplikace na které můžou návštěvnící parkoviště pozorovat obsazenost parkoviště. Vše za použití programovacího jazyka Python s knihovnami Torchvision.
|
|
|
Segmentation of important structures in retinal images
Trojánek, Václav ; Mézl, Martin (referee) ; Odstrčilík, Jan (advisor)
This bachelor thesis focuses on the segmentation of significant structures in retinal image data to improve the diagnosis and treatment of ocular diseases. Methods of retinal image analysis are investigated and implemented in this thesis. The thesis begins with an overview of the anatomy of the eye and the principles of background eye imaging using a fundus camera and an experimental video ophthalmoscope. This is followed by a detailed literature search focusing on current methods for the detection and segmentation of diagnostically important structures such as the optic disc, macula and blood vessels. A key part of the work is the implementation and testing of selected algorithms, including Hough transform for optic disc detection and OTSU thresholding for blood vessel segmentation and yellow spot detection based on previous optic disc segmentation.
|
|
|
Denial of Service detection methods
Horský, Milan ; Zeman, Václav (referee) ; Sikora, Marek (advisor)
This bachelor thesis deals with a methodology for detecting and describing the Denial of Service (DoS) condition on a web server. The aim of the thesis is to develop and implement methods that enable effective detection of DoS attacks in an experimental network. The theoretical part focuses on the analysis of different types of DoS attacks, including their detection on the application server and network side, and discusses possible reasons for false positives. In the practical part, software tools for monitoring and analyzing server and network resources were developed and then tested against different types of DoS attacks. As a result of the work, the proposed methodology has been validated and implemented in an experimental network, which provides useful tools for improving the security and stability of web servers.
|
|
|
RF monitor tool
Hűbl, Filip ; Petyovský, Petr (referee) ; Valach, Soběslav (advisor)
This bachelor thesis investigates the detection of active WiFi and Bluetooth devices via a Raspberry Pi mini computer using Kismet software. Monitoring is performed in the 2.4 GHz and 5 GHz bands. The thesis discusses in detail the principles of operation of these technologies and methods of their possible detection. The results obtained provide information on the total number of active devices identified during the measurements, the movement of these devices and these devices are further categorized according to their type.
|
|
|
Automatická kontrola dopravního značení
Čechmánek, Roman ; Klíma, Ondřej (referee) ; Musil, Petr (advisor)
The aim of this work is to create a cost-effective tool capable that would be able to automate the process of traffic sign control. This includes working with records of drives on land communications, created using inexpensive recording devices such as GoPro action cameras or certain dashcams. The control is based on the system localized traffic signs and historical traffic sign mapping data. The result of the work is a system whose input consists of drive records and historical data, and whose output is two files containing information about the inspection results. The first of these is a GEOJSON file, suitable for further processing of the collected data, and an HTML file that provides a simple user interface visualizing the inspection results on an interactive web map.
|
|
|
Optical and mechanical tracking of a moving object
Chaloupka, Radim ; Zemčík, Tomáš (referee) ; Honec, Peter (advisor)
The bachelor's thesis deals with the design of a pan-tilt platform with a camera, the design of controllers for its control, and the design and implementation of algorithms for the detection of predefined, moving objects. The task of the system is to find the object on the scene and maintain its position so that it is always in the center of the image sensor. The work uses the C++ programming language and Raspberry Pi hardware. PS and PSD controllers designed by the Ziegler-Nichols method are used for pan-tilt platform positioning, and interest point detection methods implemented in OpenCV libraries are used for optical tracing.
|
|
|
Analysis of Malware Behavior using Large Language Models
Rádsetoulal, Vlastimil ; Homoliak, Ivan (referee) ; Očenášek, Pavel (advisor)
Táto práca skúma využitie veľkých jazykových modelov (LLMs) vylepšených technikou Retrieval-Augmented Generation (RAG) pre efektívnu analýzu správania malvéru. Začína prehľadom metód analýzy malvéru, ako statických tak dynamických. Štúdia sa zameriava na využitie rámca MITRE ATT&CK na pochopenie správania malvéru veľkým jazykovým modelom. Jadro výskumu sa zameriava na architektúru a implementáciu nástroja na analýzu správania malvéru, ktorý implementuje RAG s využitím LLMs. Tento nástroj má za cieľ pomôcť profesionálom v oblasti bezpečnosti využívať možnosti generatívnej AI na interpretáciu komplexného správania malvéru. Okrem toho, výskum zahŕňa praktické nasadenie systému pre správu bezpečnostných informácií a udalostí (SIEM), pričom využíva platformu Wazuh na detekciu simulovaných útokov. Nasadenie a testovanie prebiehajú v kontrolovanom virtuálnom prostredí. Práca poukazuje na potenciál LLM modelov pri zlepšovaní opatrení v kybernetickej bezpečnosti. Práca končí diskusiou o možných vylepšeniach implementovaného nástroja.
|
|
|
Webová aplikace pro efektivní anotaci atributů objektů ve videu
Pernický, Michal ; Kohút, Jan (referee) ; Hradiš, Michal (advisor)
The goal of this work is to develop a web application for annotating video object attributes that combines an efficient user interface with an assistant classifier providing predictions. In contrast to currently available tools, the solution focuses directly on objects without assigning them to the original videos. The ability to filter objects according to their attributes and to confirm or reject predicted attribute values in bulk is important. Testing on users has been found to reduce the time spent working by up to half. This shows that further work with this annotation principle is worthwhile.
|
guest ::
