DDoS Detection on Network Protocol Using Neural Network with Feature Extract Optimization
| Autor: | Kamaruddin Malik Mohammad, Sestri Novia Rizki, Feresa Binti Mohd Foozy, Andi Maslan |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Hypertext Transfer Protocol
business.industry Computer science computer.internet_protocol Network packet ComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS Denial-of-service attack Smurf attack computer.software_genre Flooding (computer networking) Ping of death Malware business Communications protocol computer Computer network |
| Zdroj: | 2019 2nd International Conference on Applied Information Technology and Innovation (ICAITI). |
| DOI: | 10.1109/icaiti48442.2019.8982136 |
| Popis: | Security of a system is a factor that needs to be considered in the operation of information systems, which are intended to prevent threats to the system and detect and correct due to any system damage. Various techniques used for hacking such as Attack Distribution Denial of Service. DDoS attacks are attacks carried out by an attacker by sending many packets to the server. Packages sent can contain malware so that the network that is attacked can experience out of bandwidth because the attacks run continuously. Security of a system is a factor that needs to be considered in the operation of information systems, which are intended to prevent threats to the system and detect and correct due to any system damage. The types of attacks can be Ping of Death, flooding, Remote controlled attacks, UDP floods, and Smurf Attack. This study aims to develop a new approach to detect DDoS attacks, based on packet data capture in network log forms and feature extract optimization that is statistically analyzed with neural network functions as a detection method. The method is done by adjusting the weight value of each connectivity from the input, neuron, and output. This method shows the journey of data that is on the network when exposed to a DDOS attack, so this method can help identify DDoS attacks with an accuracy of 88%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|