|
|
Anti-Drone Perimeter Protection
Janík, Roman ; Dvořák, Michal (referee) ; Drahanský, Martin (advisor)
Developement of drone technology brings opportunities for many fields of human activity, but simultaneously brings security threats. A need to effectively face these threats arises. In this work is described the problematics and state-of-the-art methods for object detection in a video captured by moving camera. A system for detecting and locating a drone or a flock of drones has been proposed. Algorithm for detection is based on convolutional neural network, specifically on SSD algorithm. The convolutional neural network was trained on self-made dataset. The system was implemented using OpenCV library with possible algorithm acceleration on GPU using OpenCL. Created solution was tested on video.
|
|
|
Network Protection Using NetFlow Data
Sedlář, Petr ; Žádník, Martin (referee) ; Tobola, Jiří (advisor)
This document provides information about Cisco NetFlow technology and its usage to protect networks from different types of attacks. Part of the document is a summary of common security risks in term of their detection on network and transport layer. There are specified characteristics of NetFlow data containing samples of security risks. On the basis of these characteristics, an application for detection these risks is designed and implemented.
|
|
|
Computer Identification Based on Its Network Behaviour
Myška, Michal ; Halfar, Patrik (referee) ; Polčák, Libor (advisor)
This diploma thesis deals with computer identification using network behavioral patterns. Security functions providing privacy are described together with user privacy threats. Then, several approaches to the computer identification based on network behaviour are described. The proposed tool is based on data mining method Multinomial Naive Bayes. Then, the implementation of proposed tool is described and the experiments recognizing success in the identification are performed.
|
|
|
Anti-Drone Perimeter Protection
Janík, Roman ; Dvořák, Michal (referee) ; Drahanský, Martin (advisor)
Developement of drone technology brings opportunities for many fields of human activity, but simultaneously brings security threats. A need to effectively face these threats arises. In this work, problematics and state-of-the-art methods for object detection in a video captured by moving camera. Further I proposed a system for a drone or a flock of drones detection and localization. Algorithm for detection is based on convolutional neural network, specifically on SSD algorithm. I implemented the system with library OpenCV with possible acceleration of algorithm with GPU via OpenCL. I tested the created solution on both a video and a video camera output.
|
|
|
Network Protection Using NetFlow Data
Hlavatý, Ivo ; Žádník, Martin (referee) ; Tobola, Jiří (advisor)
This document focuses on Cisco Netflow technology and its possible usage in monitoring networks and detecting network anomalies. Based on the analysis of attacks at the network and transport layer is designed an application for selected security threats which detects its presence. The implementation section provides a system for predicting network traffic and related detecting deviations from the baseline on the basis of statistical data. Use of NetFlow technolgy is demonstrated on examples where the results of other current security and monitoring techniques have failed or did not provide sufficiently good results.
|
|
|
Thematization of Security Issue in Election Campaign: Election to Chamber of Deputies of the Parliament of the Czech Republic 2017
Rendla, Michal ; Křeček, Jan (advisor) ; Nečas, Vlastimil (referee)
Abstrakt_aj The thesis deals with the issue of security in the pre-election campaign to the Chamber of Deputies of the Parliament of the Czech Republic 2017, specifically in the election programmes of relevant political parties. In the theoretical part of the thesis is first discussed security, its concept, and basic security terminology. Afterward, the socio-constructivist Copenhagen school's securitization theory is presented, which provides also a suitable analytical tool, as well as election programmes, their position in the pre-election campaign and relevance for this paper. The analytical part of the thesis is divided into two levels. Using a quantitative content analysis of programmes, based on the method of the Comparative Manifesto research group, although heavily modified for the purposes of the work, the thematic content of security is mapped, the representation of specific themes across the programmes, as well as the amount of space and, hence, the attention devoted by individual parties to security topics. The analysis found that the dominant security issues in the programmes of the observed parties were Army and Defense, Migration, Migration Crisis and Asylum Policy, and finally Internal Order and Security. The second level of the content analysis is of qualitative nature and through the lens...
|
|
|
Anti-Drone Perimeter Protection
Janík, Roman ; Dvořák, Michal (referee) ; Drahanský, Martin (advisor)
Developement of drone technology brings opportunities for many fields of human activity, but simultaneously brings security threats. A need to effectively face these threats arises. In this work is described the problematics and state-of-the-art methods for object detection in a video captured by moving camera. A system for detecting and locating a drone or a flock of drones has been proposed. Algorithm for detection is based on convolutional neural network, specifically on SSD algorithm. The convolutional neural network was trained on self-made dataset. The system was implemented using OpenCV library with possible algorithm acceleration on GPU using OpenCL. Created solution was tested on video.
|
|
|
Anti-Drone Perimeter Protection
Janík, Roman ; Dvořák, Michal (referee) ; Drahanský, Martin (advisor)
Developement of drone technology brings opportunities for many fields of human activity, but simultaneously brings security threats. A need to effectively face these threats arises. In this work, problematics and state-of-the-art methods for object detection in a video captured by moving camera. Further I proposed a system for a drone or a flock of drones detection and localization. Algorithm for detection is based on convolutional neural network, specifically on SSD algorithm. I implemented the system with library OpenCV with possible acceleration of algorithm with GPU via OpenCL. I tested the created solution on both a video and a video camera output.
|
|
|
Thematization of Security Issue in Election Campaign: Election to Chamber of Deputies of the Parliament of the Czech Republic 2017
Rendla, Michal ; Křeček, Jan (advisor) ; Nečas, Vlastimil (referee)
Abstrakt_aj The thesis deals with the issue of security in the pre-election campaign to the Chamber of Deputies of the Parliament of the Czech Republic 2017, specifically in the election programmes of relevant political parties. In the theoretical part of the thesis is first discussed security, its concept, and basic security terminology. Afterward, the socio-constructivist Copenhagen school's securitization theory is presented, which provides also a suitable analytical tool, as well as election programmes, their position in the pre-election campaign and relevance for this paper. The analytical part of the thesis is divided into two levels. Using a quantitative content analysis of programmes, based on the method of the Comparative Manifesto research group, although heavily modified for the purposes of the work, the thematic content of security is mapped, the representation of specific themes across the programmes, as well as the amount of space and, hence, the attention devoted by individual parties to security topics. The analysis found that the dominant security issues in the programmes of the observed parties were Army and Defense, Migration, Migration Crisis and Asylum Policy, and finally Internal Order and Security. The second level of the content analysis is of qualitative nature and through the lens...
|
|
|
Network Protection Using NetFlow Data
Sedlář, Petr ; Žádník, Martin (referee) ; Tobola, Jiří (advisor)
This document provides information about Cisco NetFlow technology and its usage to protect networks from different types of attacks. Part of the document is a summary of common security risks in term of their detection on network and transport layer. There are specified characteristics of NetFlow data containing samples of security risks. On the basis of these characteristics, an application for detection these risks is designed and implemented.
|
guest ::
