National Repository of Grey Literature 246 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Machine Learning from Intrusion Detection Systems
Dostál, Michal ; Očenášek, Pavel (referee) ; Hranický, Radek (advisor)
The current state of intrusion detection tools is insufficient because they often operate based on static rules and fail to leverage the potential of artificial intelligence. The aim of this work is to enhance the open-source tool Snort with the capability to detect malicious network traffic using machine learning. To achieve a robust classifier, useful features of network traffic were choosed, extracted from the output data of the Snort application. Subsequently, these traffic features were enriched and labeled with corresponding events. Experiments demonstrate excellent results not only in classification accuracy on test data but also in processing speed. The proposed approach and the conducted experiments indicate that this new method could exhibit promising performance even when dealing with real-world data.
Centralized Cryptocurrency Exchange with Trusted Computing
Sasák, Tomáš ; Očenášek, Pavel (referee) ; Homoliak, Ivan (advisor)
Táto práca sa zaoberá návrhom, implementáciou a analýzou centralizovanej zmenárne kryptomien, ktorá pracuje na platforme trusted computing. Aktuálne centralizované zmenárne fungujú na základe plnej dôvery používateľa v operátorov zmenárne. Na opačnej strane, decentralizované zmenárne využívajú jeden blockchain a tým sú limitované iba na mince na danom blockchaine. Použitím trusted computing platformy Intel SGX je možné kód zverejniť (open source) a zákazník si dokáže overiť pomocou SGX atestácie (remote attestation) že tento kód beží na platforme zmenárne. Kombináciou so smart contract platformou na verejnom blockchaine zmenáreň dosahuje odolnosť voči nejednoznačnosti a vytvára lepšiu vrstvu bezpečnosti a transparentnosti pre používateľa. Zmenáreň bola implementovaná ako proof-of-concept pomocou programovacieho jazyka Go, za použitím frameworku EGo pre tvorbu SGX enkláv. Pre ukladanie dát bola použitá databáza PebbleDB a relačná databáza PostgreSQL. Smart contract zmenárne bol implementovaný v jazyku Solidity a nasadený na Ethereum. Implementácia je schopná vyhodnotiť približne 35 vkladov mincí za sekundu a 23 ponúk na výmenu mincí za sekundu. Aktualizácia poslednej verzie ledgeru na kontrakte stojí približne 0.00255 ETH, pri tendencií aktualizácie každú minútu deň behu zmenárne stojí približne 3.6742 ETH.
System for Agregation of Information from Public Databases
Pojsl, Jakub ; Rychlý, Marek (referee) ; Očenášek, Pavel (advisor)
The thesis focuses on the design and implementation of a system for law firms, designed to automatically retrieve relevant information from public databases. Initially, the reader is familiarized with the significance and accessibility of chosen public registers within the context of prevailing legislation. This is followed by an analysis of the processes within law firms and the existing information systems in their area. Subsequently, the focus shifts to the detailed specification and design of this system, encapsulating functionalities for client management, document organization, mail handling, and simplified billing procedures. The practical aspect of the thesis includes the actual implementation of the system, with a particular focus on user interface design, data accessibility from external sources, and the streamlining of law firm processes. The outcome of this work is a comprehensive system to aid the law firm’s operations. This includes aggregating data from selected public databases, monitoring changes in court and insolvency proceedings, and integrating with a government electronic mailbox system. Additionally, the system offers a publicly available interface for obtaining aggregated data from public registers. The system has been deployed in a testing environment, paving the way for further enhancements and demonstrating the potential for real-world application.
Application Firewall Anomaly Detection
Pospěch, Jan ; Homoliak, Ivan (referee) ; Očenášek, Pavel (advisor)
The goal of the presented bachelor thesis is to describe the process of anomaly detection in application firewalls. The thesis focuses on the principles and basics of anomaly detection, the reader is introduced to the techniques and methods of machine learning. The process of analyzing the requests and responses received from the web application protection system is described, and the system design is developed. The practical part describes the implementation of the system and testing on real datasets. Decision tree and Random forest algorithms show the best results with f1-score 0.9987. Among the unsupervised learning methods, the best results are shown by Autoencoder with an f1-score value of 0.8315.
Decentralized Application for Question/Answer Session Based on Blockchain
Čuhanič, Jakub ; Očenášek, Pavel (referee) ; Homoliak, Ivan (advisor)
This work focuses on creating a decentralized mobile application that offers a Q&A section. The problem of transparency process of the Q&A section, question censorship and spamming is solved by using blockchain technology and linking it to an identity management system. The resulting decentralized applications are the solution to all these problems. Their use can be anywhere where Q&A space is needed, especially in public media or on the Internet. Thanks to all the features of the applications resulting from the blockchain, a state should be achieved in which session moderators will not be able to manipulate or censor users and their questions.
An Integration of SIP Voice Calls into an IRC Client or Gateway
Kocman, David ; Očenášek, Pavel (referee) ; Rychlý, Marek (advisor)
Tato práce popisuje návrh, implementaci a testování Session Initiation Protocol uživatelského agenta, který používá Internet Relay Chat klienta či bránu jako jeho grafické rozhraní. Pro implementaci volání je použita open-source knihovna třetí strany, nazývána liblinphone, a samotný program je napsán v jazyce C/C++. Program je schopen jak volání, tak i zákládních SIP vlastností, jako je registrace u ústředny, překlad čísel na adresy pomocí ENUM a přímé zprávy. Také je k dispozici adresář pro ukládání kontaktů a identit, napsán pomocí knihovny SQLite3 pro C/C++. Výsledek této práce zavádí možnost volání z IRC.
Anomaly Recognition in Advanced Detection Systems
Poposki, Vasil ; Homoliak, Ivan (referee) ; Očenášek, Pavel (advisor)
Cílem této práce je implementovat systém detekce anomálií využívající techniky umělé inteligence, který dokáže detekovat anomálie učením chování systému. Navrhovaný přístup je účinný při identifikaci nových nebo neznámých anomálií, které tradiční metody založené na pravidlech mohou postrádat v datech síťového provozu. Implementace takového systému však zahrnuje i řešení problémů, jako je zpracování dat a extrakce charakteristických rysů. Tato práce pojednává o různých metodách analýzy dat a přístupech k odhalení průniků v systémech Extended Detection and Response a výzvách, kterým čelíme v dnešních rozšiřujících se bezpečnostních technologiích.
Anomaly Detection by IDS Systems
Gawron, Johann Adam ; Homoliak, Ivan (referee) ; Očenášek, Pavel (advisor)
The goal of this thesis is to familiarize myself, and the reader, with the issues surrounding anomaly detection in network traffic using artificial inteligence. To propose and subsequently implement a methodology for creating an anomaly classifier for network communication profiles. The classification method should be able to efficiently and accurately identify anomalies in network traffic to avoid generating false outputs. During the research of the issue, IDS systems, various types of attacks, and approaches to anomaly detection and classification were examined. In evaluating the effectiveness, several standard methods were examined and used to express the quality of classifiers.
Wi-Fi Communication Anomaly Detection
Lička, Zbyněk ; Homoliak, Ivan (referee) ; Očenášek, Pavel (advisor)
This thesis deals with anomaly detection in communication using the IEEE 802.11 technology (Wi-Fi) at the data link layer of OSI. The neural network method, specifically LSTM recurrent neural network, has been chosen for anomaly detection purposes. Initially, the focus area and motivation for anomaly detection in a computer network environment is described. Then, various methods for anomaly detection in computer networking are described. Thesis continues with analysis of the requirements for the system and a draft of the final system, including the chosen method, continuing with implementation of the system and model. Testing and evaluation of results takes place before the theses' conclusion.
Decentralized E-Voting on Solana Blockchain
Hošala, Martin ; Očenášek, Pavel (referee) ; Homoliak, Ivan (advisor)
Táto práca bola zameraná na zistenie využiteľnosti Solana blockchainu pre hlasovací systém BBB-Voting a vytvorenie prototypu tohto systému na základe poskytnutých riešení pre Ethereum. Problém s Ethereom je jeho výkon - väčšie voľby by trvali týždne. Solana sľubuje omnoho vyššý výkon. Na vytvorenie výsledného riešenia bolo potrebné analyzovať systém Solana, BBB-Voting, navrhnúť BBB-Voting pre Solanu, implementovať a otestovať ho. Výsledný prototyp je implementovaný v jazyku Rust pomocou frameworku Anchor. Počas vývoja bolo zistené, že algoritmus, ktorý vrámci protokolu BBB-Voting slúži pre overovanie hlasov je príliš výpočetne náročný a preto kôli súčastnému limitu na Solane nie je možné systém nasadiť na mainnet. Avšak očakáva sa, že tento limit sa bude meniť a systém bude v budúcnosti môcť byť nasadený. V takom prípade sa hrubý odhad zrýchlenia oproti Etherovým náprotivkom pohybuje okolo 3000%. Cena hlasovania na Solane je taktiež rádovo nižšia. Vrámci práce bol vyvinutý aj front-end pre hlasovanie - single-page webová aplikácia vytvorená pomocou ReactJS.

National Repository of Grey Literature : 246 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.