Mona Jaber

With the expansion of the digital world, the number of Internet of things (IoT) devices is evolving dramatically. IoT devices have limited computational power and a small memory. Consequently, existing and complex security methods are not suitable to detect unknown malware attacks in IoT networks. This has become a major concern in the advent of increasingly unpredictable and innovative cyberattacks. In this context, artificial immune systems (AISs) have emerged as an effective malware detection mechanism with low requirements for computation and memory. In this research, we first validate the malware detection results of a recent AIS solution using multiple datasets with different types of malware attacks. Next, we examine the potential gains and limitations of promising AIS solutions under realistic implementation scenarios. We design a realistic IoT framework mimicking real-life IoT system architectures. The objective is to evaluate the AIS solutions’ performance with regard to the system constraints. We demonstrate that AIS solutions succeed in detecting unknown malware in the most challenging conditions. Furthermore, the systemic results with different system architectures reveal the AIS solutions’ ability to transfer learning between IoT devices. Transfer learning is a pivotal feature in the presence of highly constrained devices in the network. More importantly, this work highlights that previously published AIS performance results, which were obtained in a simulation environment, cannot be taken at face value. In reality, AIS’s malware detection accuracy for IoT systems is 91% in the most restricted designed system compared to the 99% accuracy rate reported in the simulation experiment.