ML-ACID: a Modified Machine Learning Algorithm Coupled With a Novel Ant Colony Approach for Intrusion Detection in IOT

Abstract

Software Defined Networks is becoming increasingly important in IoT because it allows devices to communicate more easily it provides the flexibility and centralized management, however in recent years these networks have witnessed a widespread spread of cyber-attacks that has a significant and negative impact on the availability of services. In this paper, we propose a novel approach for intrusion detection in Software Defined Networks for IoT. our work inspired by the self-defense mechanism of ant colonies. The approach uses a self-adaptable colony fingerprint and based on multiple parameters, it makes the detection of intrusions easy and filters out every other legitimate communication within the network. A machine learning model is used to provide basic predictions about the communication that later drives the evolution of the colony in terms of self-defence. The whole approach is implemented in a simple switch using Ryu-controller and analyses OpenFlow datagrams. The meta-heuristic implication of using ant colony optimization improved approach provides the system with reliability and high performance of detecting and blocking threats. in the end interesting results based on several scenarios shows the usability of our approach.