Behavioral Modeling Intrusion Detection System (BMIDS) Using Internet of Things (IoT) Behavior-Based Anomaly Detection via Immunity-Inspired Algorithms

Abstract

In this research, a real-world simulation service uses Internet of Things (IoT) capable objects to detect behavioral-based anomalies within a simulated smart home/vicinity. In the simulation, the smart home and the surrounding world are monitored with a behavioral modeling intrusion detection system (BMIDS). The BMIDS uses immunity-inspired algorithms to distinguish whether behavioral patterns extracted match a desired behavior or indicate deviation from the desired behavior. The simulation is used to monitor and scale all relevant activity in order to verify construction of accurate behavioral models. The BMIDS demonstrates how the capture of IoT sensor data activity concatenated as a set of event sequences along with the simulated world state provide the components to establish a numerical representation for behavioral identity. Creating behavioral models via pervasive system monitoring prior to and alongside cyber-physical system experimentation with the BMIDS simulation is cost efficient, easily verifiable and promotes autonomous monitoring for an autonomic monitoring mechanism. Also, performance measurements can be scaled more accurately during qualitative and quantitative analysis, thus producing the desired behavior model as depicted by the specified scripted or non-scripted behavior.