Information security technology for computer networks through classification of cyber-attacks using soft computing algorithms

The Internet is the global platform which revolutionized the computer and communications domain. Although it becomes one of the most useful tools in people's lives, the presence of cyber-attacks that can cause damage, modification, and theft of vital data and information over this platform has...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:HNICEM : 2017 IEEE 9th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management : 1-3 December 2017 s. 1 - 6
Hlavní autoři: Villaluna, Jason A., Cruz, Febus Reidj G.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.12.2017
Témata:
Artificial neural network
Artificial neural networks
Classification algorithms
cyber-attacks
Fuzzy logic
fuzzy neural network
Information security
Internet
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The Internet is the global platform which revolutionized the computer and communications domain. Although it becomes one of the most useful tools in people's lives, the presence of cyber-attacks that can cause damage, modification, and theft of vital data and information over this platform has increased. Utilization of soft-computing based on the behavior of the network may detect new or modified old attacks. An information security system is developed for the recognition the network infrastructure's behavior. This is limited to Normal, DoS, Probe, U2R, and R2L. The packets on the network are processed in MATLAB and analyze using Fuzzy Logic, Artificial Neural Network, and Fuzzy-Neural Network. Different tests are done with different datasets of varied parameters. The best model for each algorithm, which is rendered from the tests, is used for the information security system. The cyber-attacks were identified within a short period: 51.64us for Fuzzy Logic, 1.34us for Artificial Neural Network, and 14.23us for the Fuzzy Neural Network. The detection rate and accuracy of the three algorithms are 94.84%, 98.51%, 98.60% and 89.74%, 96.09%, 96.19% respectively. The Fuzzy Neural Network has the best performance which used the advantage of Fuzzy Logic and Artificial Neural Network.
DOI:10.1109/HNICEM.2017.8269430