Security and Identification of Internal Intrusions by Self-Monitoring

Abstract

The increasing reliance on the internet by billions worldwide has made cyber security a vital concern. Among emerging security solutions, intrusion detection technologies have gained importance for their ability to monitor systems and prevent unauthorized activities. These systems use localized network mechanisms to continuously observe user behaviors and identify potential threats over time. To enhance system security, this project introduces a novel framework known as the Call-Level Intrusion Detection and Protection System, which creates and updates user behavior profiles to detect anomalies effectively. The performance of the proposed model has been validated through the use of forensic analysis and established intrusion detection methodologies. Additionally, this research reviews prior studies focused on Intrusion Detection Systems (IDS) and Internal Intrusion Detection Systems (IIDS). Building upon this foundation, a new IIDS model was developed, utilizing advanced algorithms to differentiate between legitimate and malicious activities within network infrastructures.