|
|
Application for collecting security event logs from computer infrastructure
Žernovič, Michal ; Dobiáš, Patrik (referee) ; Safonov, Yehor (advisor)
Computer infrastructure runs the world today, so it is necessary to ensure its security, and to prevent or detect cyber attacks. One of the key security activities is the collection and analysis of logs generated across the network. The goal of this bachelor thesis was to create an interface that can connect a neural network to itself to apply deep learning techniques. Embedding artificial intelligence into the logging process brings many benefits, such as log correlation, anonymization of logs to protect sensitive data, or log filtering for optimization a SIEM solution license. The main contribution is the creation of a platform that allows the neural network to enrich the logging process and thus increase the overall security of the network. The interface acts as an intermediary step to allow the neural network to receive logs. In the theoretical part, the thesis describes log files, their most common formats, standards and protocols, and the processing of log files. It also focuses on the working principles of SIEM platforms and an overview of current solutions. It further describes neural networks, especially those designed for natural language processing. In the practical part, the thesis explores possible solution paths and describes their advantages and disadvantages. It also analyzes popular log collectors (Fluentd, Logstash, NXLog) from aspects such as system load, configuration method, supported operating systems, or supported input log formats. Based on the analysis of the solutions and log collectors, an approach to application development was chosen. The interface was created based on the concept of a REST API that works in multiple modes. After receiving the records from the log collector, the application allows saving and sorting the records by origin and offers the user the possibility to specify the number of records that will be saved to the file. The collected logs can be used to train the neural network. In another mode, the interface forwards the logs directly to the AI model. The ingestion and prediction of the neural network are done using threads. The interface has been connected to five sources in an experimental network.
|
|
|
Word Sense Clustering
Haljuk, Petr ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This Bachelor's thesis deals with the semantic similarity of words . It describes the design and the implementation of a system, which searches for the most similar words and measures the semantic similarity of words . The system uses the Word2Vec model from GenSim library . It learns the relations among words from CommonCrawl corpus .
|
|
|
Data Mining in Social Networks
Raška, Jiří ; Očenášek, Pavel (referee) ; Bartík, Vladimír (advisor)
This thesis deals with knowledge discovery from social media. This thesis is focused on feature based opinion mining from user reviews. In theoretical part were described methods of opinion mining and natural language processing. Main parts of this thesis were design and implementation of library for opinion mining based on Stanford Parser and lexicon WordNet. For feature identi cation was used dependency grammar, implicit features were mined with method CoAR and opinions were classi ed with supervised algorithm. Finally were given experiments with implemented library and examples of usage.
|
|
|
Word Sense Clustering
Bárta, Jakub ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This bachelor's thesis deals with the design and implementation of a modular system focused on semantic similarity. System is able to stem the corpus and to analyze corpus in different ways - through coocurrence matrix or LSA.
|
|
|
Natural Language Processing: Analysis of Information Technology Students’ Spoken Language
Stanković, Aleksandar ; Šťastná, Dagmar (referee) ; Ellederová, Eva (advisor)
Tato bakalářská práce se zabývá problematikou nových technologií umělé inteligence při zpracování přirozeného jazyka. Práce je rozdělena na teoretickou a analytickou část. Teoretická část přistupuje k problému rozdělením do tří kapitol: umělá inteligence a statistika, zpracování přirozeného jazyka a IBM Watson Natural Language Understanding. Každá z těchto kapitol je rozpracována včetně uvedení alespoň jednoho příkladu z praxe. V první kapitole je hlavním cílem vymezit teoretický rámec umělé inteligence a jejích postupů, zatímco ve druhé kapitole je vysvětlena problematika zpracování přirozeného jazyka a jeho primární funkce včetně jeho vztahu k samotné umělé inteligenci. Cílem třetí kapitoly je představit porozumění přirozenému jazyku jako primární nástroj pro analýzu, která je realizována v analytické části práce. Analytická část se zabývá analýzou mluveného jazyka studentů prostřednictvím různých metod. Transkripce shromážděných vzorků videí je provedena strojovým překladem jako aplikací zpracování přirozeného jazyka, zatímco textový výstup je analyzován prostřednictvím nástroje porozumění přirozenému jazyku. V analytické části, která popisuje výzkumnou metodologii, prezentuje a interpretuje výsledky výzkumu, jsou využívány aplikované znalosti z teoretické části práce.
|
|
|
Machine Comprehension Using Commonsense Knowledge
Daniš, Tomáš ; Landini, Federico Nicolás (referee) ; Fajčík, Martin (advisor)
V tejto práci je skumaná schopnosť používať zdravý rozum v moderných systémoch založených na neurónových sieťach. Zdravým rozumom je myslená schopnosť extrahovať z textu fakty, ktoré nie sú priamo spomenuté, ale implikuje ich situácia v texte. Cieľom práce je poskytnúť náhľad na súčasný stav výskumu v tejto oblasti a nájsť sľubné výskumné smery do budúcnosti. V práci je implementovaný jeden z najmodernejších modelov na odpovedanie na otázky a je ďalej použitý na experimenty v rôznych situáciách. Narozdiel od starších prístupov, tento model dosahuje porovnateľné výsledky s najlepšími známymi modelmi aj keď jeho architektúra neobsahuje žiadne prvky zamerané konkrétne na zlepšenie schopnosti zdravo uvažovať. Taktiež boli nájdené štatistické artefakty v populárnej sade dát s otázkami vyžadujúcimi zdravé uvažovanie. Tieto artefakty môžu byť použité štatistickými modelmi na nájdenie správnej odpovede aj v prípadoch, kedy by to nemalo byť možné. Na základe týchto zistení sú v práci poskytnuté odporúčania a návrhy pre výskum do budúcnosti.
|
|
|
Query Answering over Wikipedia for Mobile Devices on the Android Platform
Kováč, Andrej ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
p { margin-bottom: 0.1in; direction: ltr; line-height: 120%; text-align: left; widows: 2; orphans: 2; }p.western { font-family: "Times New Roman",serif; }p.cjk { font-family: "Times New Roman"; }p.ctl { font-family: "Times New Roman"; font-size: 12pt; }a:link { color: rgb(0, 0, 255); } This bachelor thesis deals with the development of a system for query answering over Wikipedia for mobile devices running Android operating system. In this technical report theoretical knowledge related to this topic is described as well as the implementation process of a server system and client side application. Part of this thesis is dedicated to testing of the system and in the final part the potential for future development is drafted.
|
|
|
Authorship Identification
Fabiánek, Ondřej ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
This bachelor's thesis deals with authorship identification based on knowledge of author's previous texts. The aim is to analyze existing methods of authorship attribution and create a system, which is capable of highly successful authorship identification. The system is based on a multivariate analysis and specializes at English books. Part of the solution is also a graphic user interface.
|
|
|
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.
|
|
|
Automatic Humor Evaluation
Katrňák, Josef ; Ondřej, Karel (referee) ; Dočekal, Martin (advisor)
The aim of this thesis is to create a system for automatic humor evaluation. The system allow to predict humor and category for english input. The main essence is to create a classifier and train the model with the created datasets to get the best possible results. The classifier architecture is based on neural networks. The system also includes a web user interface for communication with the user. The result is a web application linked to a classifier that allows user input to be evaluated and user feedback to be provided.
|
guest ::
