Machine learning techniques will contribution towards making Internet of Things (IoT) symmetric applications among the most significant sources of new data in the future. In this context, network systems are endowed with the capacity to access varieties of experimental symmetric data across a plethora of network devices, study the data information, obtain knowledge, and make informed decisions based on the dataset at its disposal. This study is limited to supervised and unsupervised machine learning (ML) techniques, regarded as the bedrock of the IoT smart data analysis. This study includes reviews and discussions of substantial issues related to supervised and unsupervised machine learning techniques, highlighting the advantages and limitations of each algorithm, and discusses the research trends and recommendations for further study.

Among other security concerns, the reliable device to device direct communication is an important research aspect in sensor cloud system application of Internet of things (IoT). The access control mechanism can ensure the reliability through secure communication among two IoT devices without mediation of intermediate agent. Mainly, it requires twofold strategy involving the authentication of each other and session key establishment. Quite recently, in 2019, Das et al. proposed a certificate based lightweight access control and key agreement scheme for IoT devices (LACKA-IoT) to ensure smooth and secure access control and claimed LACKA-IoT to withstand the several attacks. Specifically, it is claimed that LACKA-IoT can resist device impersonation and man in middle attacks. However, the proof in this article refutes their claim and it is shown here, that LACKA-IoT is insecure against both device impersonation and man in middle attacks. An adversary just by using public parameters and by listening the communication channel can impersonate any device. Moreover, the same can also launch successful man in middle attack using public parameters and listened messages from public channel. An improved protocol iLACKA-IoT is then proposed in the paper. The iLACKA-IoT provides resistance against various types of threats and provides the required level of security, for evidence both formal validation through random or real (ROR) model as well as the informal validation through discussion on attack resilience is provided. The iLACKA-IoT is not only better in security but also provides performance efficiency as compared with LACKA-IoT and related schemes.

No abstract

No abstract

No abstract