Banca de DEFESA: MARCELO LUIZ DE FRANÇA

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
STUDENT : MARCELO LUIZ DE FRANÇA
DATE: 18/12/2020
TIME: 14:00
LOCAL: Remoto
TITLE:

TEDA-Guardian: Detecting DDoS Attacks on Internet Service Providers

KEY WORDS:

DDoS, TEDA, Network Security

PAGES: 73
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUBÁREA: Sistemas de Computação
SPECIALTY: Teleinformática
SUMMARY:

A DDoS (Distributed Denial of Service) attack is an organized technique of distributed packet sending with the aim of overloading network devices and the communication channels between them. In general, its main objective is to prevent legitimate users from accessing networks, servers, services or other resources of the network system. Although it is clear the importance of mechanisms to protect or mitigate the effects of this type of attack, its correct detection is still a challenge due to the dynamics and volume of current communications and network connections. Although the specific literature is abundant in proposed solutions to the problem, most of them are based on Artificial Intelligence algorithms that involve learning based on training or reinforcement, and it is necessary to extract traits of previously collected traffic. As a result, these techniques need to “look to the past” to understand network traffic. Because of this, many of these solutions are not applicable to more dynamic environments with high traffic volume, such as internet providers. In this dissertation, we propose an approach to detect DDoS attacks using the TEDA (Typicality and Eccentricity Data Analytics) algorithm, called TEDA-Guardian. TEDA is a recursive and non-parametric method, initially proposed for the general problem of detecting anomalies in data flows. With the use of TEDA-Guardian it is possible to analyze the current traffic on the network, reducing the detection delay, since it is based on the concept of data eccentricity, without the need for prior knowledge of the network traffic pattern. Thus, TEDA-Guardian allows you to "look at the present", that is, the data that is currently being transferred, thus guaranteeing a more punctual detection. This approach was tested on different datasets containing network traffic with moments of DDoS attacks. Its effectiveness was evaluated in terms of sensitivity, specificity, false positive rate and detection accuracy.

BANKING MEMBERS:
Presidente - 2266415 - SILVIO COSTA SAMPAIO
Interno - 2180207 - ITAMIR DE MORAIS BARROCA FILHO
Externo à Instituição - ERICO MENEZES LEAO - UFPI
Externo à Instituição - RODRIGO SIQUEIRA MARTINS - IFRN