National Repository of Grey Literature 6 records found  Search took 0.01 seconds. 
Detection of Malicious Websites using Machine Learning
Šulák, Ladislav ; Černocký, Jan (referee) ; Beneš, Karel (advisor)
Táto práca sa zaoberá problematikou škodlivého kódu na webe so zameraním na analýzu a detekciu škodlivého JavaScriptu umiestneného na strane klienta s využitím strojového učenia. Navrhnutý prístup využíva známe i nové pozorovania s ohľadom na rozdiely medzi škodlivými a legitímnymi vzorkami. Tento prístup má potenciál detekovať nové exploity i zero-day útoky. Systém pre takúto detekciu bol implementovaný a využíva modely strojového učenia. Výkon modelov bol evaluovaný pomocou F1-skóre na základe niekoľkých experimentov. Použitie rozhodovacích stromov sa podľa experimentov ukázalo ako najefektívnejšia možnosť. Najefektívnejším modelom sa ukázal byť Adaboost klasifikátor s dosiahnutým F1-skóre až 99.16 %. Tento model pracoval s 200 inštanciami randomizovaného rozhodovacieho stromu založeného na algoritme Extra-Trees. Viacvrstvový perceptrón bol druhým najlepším modelom s dosiahnutým F1-skóre 97.94 %.
Metrics for Buffer Overflow Attacks Detection of UDP Network Services
Šulák, Ladislav ; Ovšonka, Daniel (referee) ; Homoliak, Ivan (advisor)
This bachelor thesis deals with problematic of network attacks and their detection in network traffic. The aim is to propose such collection of metric, that will describe network traffic according to its behaviour, and will be capable of detection of Zero-Day attacks as well. Following part of this thesis is to implement a tool for metric extraction.
The crime of fraud, insurance fraud, loan fraud and subsidies fraud under ss. 209, 210, 211 and 212 of the Criminal Code
Šulák, Ladislav ; Říha, Jiří (advisor) ; Gřivna, Tomáš (referee)
The crimes of fraud, insurance fraud, credit fraud and grant fraud under s. 209, 210, 211 and 212 of the Czech criminal code This thesis presents the criminal offence of fraud under s. 209 of the Czech criminal code and its special forms - insurance fraud, credit fraud and grant fraud under s. 209, 210, 211 and 212 of the Czech criminal code. In my opinion a fraud in ist very essence represents a classic crime against property. After Velvet revolution the relevance of crimes against property has raised considerably and therefore the regulation of these crimes requires particular attention. This applies above all to the insuranec fraud and credit fraud. The insurance fraud and credit fraud were brought together with grant fraud into the Czech criminal code through an amandement in 1997. The aim of this thesis is to provide an presentation of legal regulation of fraud and its special forms and some issues related to it. I would like also to presentate controversies, which were caused by the amandement of the Czech criminal code in 1997. This thesis consist of three chapters. The first one deals with the crimes against property. The second one deals with the fraud in its general form, the other ones with its special forms. In every chapter I folow the same pattern - which means elements of the fact of...
Detection of Malicious Websites using Machine Learning
Šulák, Ladislav ; Černocký, Jan (referee) ; Beneš, Karel (advisor)
Táto práca sa zaoberá problematikou škodlivého kódu na webe so zameraním na analýzu a detekciu škodlivého JavaScriptu umiestneného na strane klienta s využitím strojového učenia. Navrhnutý prístup využíva známe i nové pozorovania s ohľadom na rozdiely medzi škodlivými a legitímnymi vzorkami. Tento prístup má potenciál detekovať nové exploity i zero-day útoky. Systém pre takúto detekciu bol implementovaný a využíva modely strojového učenia. Výkon modelov bol evaluovaný pomocou F1-skóre na základe niekoľkých experimentov. Použitie rozhodovacích stromov sa podľa experimentov ukázalo ako najefektívnejšia možnosť. Najefektívnejším modelom sa ukázal byť Adaboost klasifikátor s dosiahnutým F1-skóre až 99.16 %. Tento model pracoval s 200 inštanciami randomizovaného rozhodovacieho stromu založeného na algoritme Extra-Trees. Viacvrstvový perceptrón bol druhým najlepším modelom s dosiahnutým F1-skóre 97.94 %.
The crime of fraud, insurance fraud, loan fraud and subsidies fraud under ss. 209, 210, 211 and 212 of the Criminal Code
Šulák, Ladislav ; Říha, Jiří (advisor) ; Gřivna, Tomáš (referee)
The crimes of fraud, insurance fraud, credit fraud and grant fraud under s. 209, 210, 211 and 212 of the Czech criminal code This thesis presents the criminal offence of fraud under s. 209 of the Czech criminal code and its special forms - insurance fraud, credit fraud and grant fraud under s. 209, 210, 211 and 212 of the Czech criminal code. In my opinion a fraud in ist very essence represents a classic crime against property. After Velvet revolution the relevance of crimes against property has raised considerably and therefore the regulation of these crimes requires particular attention. This applies above all to the insuranec fraud and credit fraud. The insurance fraud and credit fraud were brought together with grant fraud into the Czech criminal code through an amandement in 1997. The aim of this thesis is to provide an presentation of legal regulation of fraud and its special forms and some issues related to it. I would like also to presentate controversies, which were caused by the amandement of the Czech criminal code in 1997. This thesis consist of three chapters. The first one deals with the crimes against property. The second one deals with the fraud in its general form, the other ones with its special forms. In every chapter I folow the same pattern - which means elements of the fact of...
Metrics for Buffer Overflow Attacks Detection of UDP Network Services
Šulák, Ladislav ; Ovšonka, Daniel (referee) ; Homoliak, Ivan (advisor)
This bachelor thesis deals with problematic of network attacks and their detection in network traffic. The aim is to propose such collection of metric, that will describe network traffic according to its behaviour, and will be capable of detection of Zero-Day attacks as well. Following part of this thesis is to implement a tool for metric extraction.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.