UMP Institutional Repository

SAIRF: A similarity approach for attack intention recognition using fuzzy min-max neural network

Ahmed, Abdulghani Ali and Mohammed, Mohammed Falah (2018) SAIRF: A similarity approach for attack intention recognition using fuzzy min-max neural network. Journal of Computational Science, 25. pp. 467-473. ISSN 1877-7503

[img]
Preview
Pdf
SAIRF A similarity approach for attack intention recognition.pdf

Download (85kB) | Preview

Abstract

The ability of cybercriminals tohide their intentionto attack obstructs existingprotectionsystems causing the system to be unable to prevent any possible sabotage in network systems. In this paper, we propose a Similarity approach for Attack Intention Recognition using Fuzzy Min-Max Neural Network (SAIRF). In particular, the proposed SAIRF approach aims to recognize attack intention in real time. This approach classifies attacks according to their characteristics and uses similar metric method to identify motives of attacks and predict their intentions. In this study, network attack intentions are categorized into specific and general intentions. General intentions are recognized by investigating violations against the security metrics of confidentiality, integrity, availability, and authenticity. Specific intentions are recognized by investigating the network attacks used to achieve a violation. The obtained results demonstrate the capability of the proposed approach to investigate similarity of network attack evidence and recognize the intentions of the attack being investigated

Item Type: Article
Uncontrolled Keywords: Network forensics; attack intention; similarity of evidence; FMM neural network
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > T Technology (General)
Faculty/Division: Faculty of Computer System And Software Engineering
Depositing User: Ms. Ratna Wilis Haryati Mustapa
Date Deposited: 17 Jan 2019 01:21
Last Modified: 17 Jan 2019 01:21
URI: http://umpir.ump.edu.my/id/eprint/23820
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item