LAUSR

In recent years, network expansion has increased exponentially, making security a pressing issue for modern systems. Monitoring user activity for abnormalities is a useful fraud detection strategy. The ability of a system to efficiently discover new, previously unknown vulnerabilities and respond in a way that minimises damage and, ideally, removes the threat, is one of the most important open research topics in the field of cyber security. This research provides a blueprint for an intrusion detection system that employs pattern matching and self-replication among other methods. As the system detects potentially dangerous symptoms in the surroundings, it compares them to the events that have become apparent so far to find a pattern that may explain their occurrence. Once this happens, it alerts other nodes in the system to keep an eye out for harmful event sequences, and it initiates the defence mechanism that lessens the number of false intrusion alarms. Using natural intrusion detection and self-healing idea, this research outlines a novel method for network security. An Imperative Node Evaluator with Self Replication Code and Auto Triggering Mode (INE-SRC-ATM) is proposed in this research for auto healing of the network if intrusion occurs and also to perform auto triggering of nodes for securing the network and reducing the false alarms. To activate the self-healing mechanism, the IDS must first identify and assess the impact of hostile actions on the network. This means that the self-healing process begins when the damage caused by malevolent activity is identified. The proposed model self triggering model immediately triggers when there is a dissimilarity on attributes that improve the network security levels. The proposed model when contrasted with the traditional model performs high in intrusion detection in terms of self replication triggering accuracy and intrusion detection accuracy levels.