The next whooping revolution after the Internet is its scion, the Internet of Things (IoT), which has facilitated every entity the power to connect to the web. However, this magnifying depth of the digital pool oil the wheels for the attackers to penetrate. Thus, these threats and attacks have become a prime concern among researchers. With promising features, Machine Learning (ML) has been the solution throughout to detect these threats. But, the general ML-based solutions have been declining with the practical implementation to detect unknown threats due to changes in domains, different distributions, long training time, and lack of labelled data. To tackle the aforementioned issues, Transfer Learning (TL) has emerged as a viable solution. Motivated by the facts, this article aims to leverage TL-based strategies to get better the learning classifiers to detect known and unknown threats targeting IoT systems. TL transfers the knowledge attained while learning a task to expedite the learning of new similar tasks/problems. This article proposes a learning-based threat model for attack detection in the Smart Home environment (SALT). It uses the knowledge of known threats in the source domain (labelled data) to detect the unknown threats in the target domain (unlabelled data). The proposed scheme addresses the workable differences in feature space distribution or the ratio of attack instances to a normal one, or both. The proposed threat model would show the implying competence of ML with the TL scheme to improve the robustness of learning classifiers besides the threat variants to detect known and unknown threats. The performance analysis shows that traditional schemes underperform for unknown threat variants with accuracy dropping to 39% and recall to 56.

No abstract

No abstract

Our daily lives are significantly impacted by intelligent Internet of Things (IoT) application, services, IoT gadgets, and more intelligent industries. Artificial Intelligence (AI) is anticipated to have a substantial impact on training machine learning algorithms on IoT devices without sharing data. As data privacy has become a serious societal concern, Federated Learning (FL) has emerged as a hot research area for enabling the collaborative training of machine learning models across many smart IoT devices while adhering to privacy constraints. Although, FL is utilized for preserving privacy in IoT networks, but it is also facing some challenges such as privacy, effectiveness, and efficiency. In this article, a taxonomy of FL-based IoT systems is proposed and an analysis of related works on FL-based IoT systems is presented. Further, a comprehensive study of various types of threats, attacks, and frameworks is done. In addition to this, a taxonomy on privacy-preserving FL techniques for IoT networks is also devised. Finally, the study is concluded by highlighting the various open research challenges in FL-based IoT networks.