Network Attacks Anomaly Detection Using SNMP MIB Interface Parameters
This work addresses network security for intrusion detection systems by improving efficiency, but it appears incremental as it builds on existing machine learning approaches with specific parameter optimizations.
The paper tackled the problem of network attack anomaly detection by proposing a model using Lazy.IBk classifier and Correlation and ReliefF attribute evaluators on SNMP-MIB interface parameters, achieving 100% accuracy with minimal hardware resource consumption.
Many approaches have evolved to enhance network attacks detection anomaly using SNMP-MIBs. Most of these approaches focus on machine learning algorithms with a lot of SNMP-MIB database parameters, which may consume most of hardware resources (CPU, memory, and bandwidth). In this paper we introduce an efficient detection model to detect network attacks anomaly using Lazy.IBk as a machine learning classifier and Correlation, and ReliefF as attribute evaluators on SNMP-MIB interface parameters. This model achieved accurate results (100%) with minimal hardware resources consumption. Thus, this model can be adopted in intrusion detection system (IDS) to increase its performance and efficiency.