Home / Current Issue / Paper 1706612
Logfile-Driven Risk Assessment of Security Threats in LMSs Using Fuzzy Logic
Subject area: Science,Engineering and Technology · Area of research: Security Risk Assessment
Abstract
The rapid expansion of online Learning Management Systems (LMS) has heightened the need for robust security mechanisms to mitigate various risks. This paper presents a fuzzy logic-based framework for assessing security threats in online LMS environments, utilizing logfile data as input. The system extracts logfiles from the LMS server, preprocesses them into a structured CSV format, and identifies key risk factors, such as login failure attempts, suspicious IP addresses, brute force attacks, and unauthorized access attempts. These risk factors are then quantified to serve as crisp input values for a fuzzy inference system (FIS). The core of the proposed approach involves fuzzification of the identified risk factors, applying a set of 20 predefined fuzzy rules based on security principles. These rules are employed within a rule-based fuzzy method to classify the severity of risks. The system defuzzifies the output to generate a final risk assessment categorized into four levels: low, medium, high, and critical. This real-time risk classification enables administrators to quickly identify and respond to security threats in a proactive manner.
Keywords
Fuzzy Logic, Risk Assessment, Security, Learning Management System
How to cite this paper
@article{1706612,
author = {Moe Moe San, Khin May Win},
title = {Logfile-Driven Risk Assessment of Security Threats in LMSs Using Fuzzy Logic},
journal = {Iconic Research And Engineering Journals},
year = {2024},
volume = {8},
number = {5},
pages = {618-628},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1706612.pdf},
abstract = {The rapid expansion of online Learning Management Systems (LMS) has heightened the need for robust security mechanisms to mitigate various risks. This paper presents a fuzzy logic-based framework for assessing security threats in online LMS environments, utilizing logfile data as input. The system extracts logfiles from the LMS server, preprocesses them into a structured CSV format, and identifies key risk factors, such as login failure attempts, suspicious IP addresses, brute force attacks, and unauthorized access attempts. These risk factors are then quantified to serve as crisp input values for a fuzzy inference system (FIS). The core of the proposed approach involves fuzzification of the identified risk factors, applying a set of 20 predefined fuzzy rules based on security principles. These rules are employed within a rule-based fuzzy method to classify the severity of risks. The system defuzzifies the output to generate a final risk assessment categorized into four levels: low, medium, high, and critical. This real-time risk classification enables administrators to quickly identify and respond to security threats in a proactive manner.},
keywords = {Fuzzy Logic, Risk Assessment, Security, Learning Management System},
month = {November},
}