|
|
Mitigation of DoS Attacks Using Machine Learning
Goldschmidt, Patrik ; Kekely, Lukáš (referee) ; Kučera, Jan (advisor)
Útoky typu odoprenia služby (DDoS) sú v dnešných počítačových sieťach stále frekventovanejším bezpečnostným incidentom. Táto práca sa zameriava na detekciu týchto útokov a poskytnutie relevantných informácii za účelom ich mitigácie v reálnom čase. Spomínaná funkcionalita je dosiahnutá s využitím techník prúdového dolovania z dát a strojového učenia. Výsledkom práce je sada nástrojov zastrešujúca celý proces strojového učenia - od vlastnej extrakcie príznakov cez predspracovanie dát až po export natrénovaného modelu pripraveného na nasadenie v produkcii. Experimentálne výsledky vyhodnotené na viacerých reálnych a syntetických dátových sadách poukazujú na presnosť systému väčšiu ako 99% s možnosťou spoľahlivej detekcie prebiehajúceho útoku do 4 sekúnd od jeho začiatku.
|
|
|
Profiling of Network Traffic for DDoS Mitigation
Ligocká, Alexandra ; Tisovčík, Peter (referee) ; Žádník, Martin (advisor)
The aim of this work is to propose metrics for \gls{ddos} attacks detection and setting the thresholds of normal network traffic in a given computer network at different levels of detail. Based on the selected metrics and network flow data, a network profile is extracted and afterwards stored in memory. Within the implementation part, this work deals with the implementation of program for the collection and calculation of specified metrics, their processing, storage and provides a simple interface providing access to stored data.
|
|
|
Mitigation of DDoS Attacks Using IDS/IPS
Litwora, Martin ; Tisovčík, Peter (referee) ; Kučera, Jan (advisor)
This This bachelor's thesis focuses on the detection and mitigation of DDoS attacks (Distributed Denial of Service). The main goal is to analyze and practically verify the capabilities of various IDS/IPS, especially the open-source tool Suircata, to mitigate DDoS attacks. Three main DDoS attack groups are analyzed in this thesis. These groups are flood attacks, amplification attacks, and slow attacks. A set of rules has to be created for each attack type from these groups in order for Suricata to mitigate those DDoS attacks. This thesis also implements a set of tools and scripts to check the functionality and effectiveness of the created rules. These tools are used to generate selected DDoS attacks with different parameters. Testing took place in a virtual environment where special nodes had to be created which represent real subjects during a real DDoS attack. The set of tools and scripts was designed in a way that it can easily be used outside this virtual environment where it is possible to have larger network loads, various variants and combinations of systems, and more.
|
|
|
Mitigation of DDoS Attacks Exploiting Packet Fragmentation
Nešpor, Patrik ; Vrána, Roman (referee) ; Kučera, Jan (advisor)
This bachelor's thesis deals with the development of new mitigation strategies that are designed to suppress DDoS attacks that exploit packet fragmentation. It analyses fragmented traffic primarily emphasizing the order of fragmented packets. Based on the result of the analysis, it implements a new heuristic method for port numbers inference. The work also measures the latency and throughput of newly implemented functionalities. All new methods are integrated in a project developed by the CESNET association.
|
|
|
Heuristic Methods for the Mitigation of DDoS Attacks that Abuse TCP Protocol
Goldschmidt, Patrik ; Wrona, Jan (referee) ; Kučera, Jan (advisor)
TCP SYN Flood is one of the most wide-spread DoS attack types used on computer networks nowadays. As a possible countermeasure, this thesis proposes a network-based mitigation method TCP Reset Cookies. The method utilizes the TCP three-way-handshake mechanism to establish a security association with a client before forwarding its SYN data. The algorithm can effectively mitigate even more sophisticated SYN flood attacks at the cost of 1-second delay for the first established connection. However, the method may not be suitable for all the scenarios, so decision-making algorithm to switch between different SYN Flood mitigation methods according to discovered traffic patterns was also developed. The project was conducted as a part of security research by CESNET. The discussed implementation of TCP Reset Cookies is already integrated into a DDoS protection solution deployed in CESNET's backbone network and Czech Internet exchange point at NIX.CZ.
|
guest ::
