21 February 2023 in Future Generation Computer Systems
1 January 2022 in SSRN Electronic Journal
As the internet becomes intertwined into every aspect of human lives, security of the Internet of Things (IoT) becomes increasingly critical. IoT devices become the data source for variety of smart cities applications, where critical decisions are based on this collected data. If malicious actors control or tampered with the the data being transmitted, the integrity of an entire smart city will be compromised. Therefore, through monitoring the IoT devices’ behavior, anomalies can be detected and isolated to avoid any negative impact on decision making. This behavioral monitoring process will complement traditional trust management approaches, as more accurate trust value can be calculated without the need to rely on a majority consensus. In this work we present a behavior as a service methodology that implements a deep learning based behavioral model to accurately classify IoT devices’ interactions in the system. Through the Elo rating system, these classifications will be presented as a vector of behaviors per device, which dynamically reflects on the device’s trust in the system. This work presents an analysis of our methodology as well as a threat model. Using simulation, a real-world use-case is presented showing the interactions between IoT based devices. Our results show that our behavior as a service model is able to dynamically evaluate each IoT device’s trust as well as capture and mitigate multiple threats targeting the trust in the system.