A review of privacy-preserving federated learning, deep learning, and machine learning IIoT and IoTs solutions

Internet of Things (IoT) is a growing computing trend that encompasses every connected thing. Over the recent years, IoT has recorded an exponential growth, leading to billions of smart devices, and still increasing. In contrast to other computing devices, some IoTs generate large amount of data, however, this has become a source of concern as data could contain users’ privacy which should be protected at all costs against any potential security breach incident. Securing IoT is very significant with its continuous adoption and use, hence, researchers have proposed several security mechanisms and techniques to safeguard and protect IoT systems and devices. Notwithstanding, there are some research gaps that are yet to be addressed irrespective of the relevant contributions made in protection of users’ privacy and confidentiality using IoTs. In this paper, the researcher solely focused on a review of AI approaches leveraged by researchers in protecting the device and data security aspects of privacy specifically for de-centralised architecture based industrial IoT systems (IIOTs) as they are generating large amount of data and are safety critical. The results achieved, unresolved issues and recommendations for future research are contained in this review.