International Journal of Applied Engineering Research ISSN 0973-4562 Volume 13, Number 14 (2018) pp. 11648-11652 © Research India Publications. http://www.ripublication.com 11648 Security and Privacy Measures on Data Mining for Internet of Things Sung Woon Lee 1 , Thokozani Vallent 2 , Hyunsung Kim 3 1 Department of Information Security, Tongmyong University, Korea. 2 Department of Mathematical Sciences, University of Malawi, Malawi. 3 Department of Cyber Security, Kyungil University, Korea. & Department of Mathematical Sciences, University of Malawi, Malawi (Corresponding author) Abstract Although Internet of things (IoT) bring in a great development in the ubiquitous computing world by virtue of connecting intelligent collaborative objects to the Internet anywhere and anytime, there are still security and privacy concerns on its operations. As IoT is expanding, organizations need to move quickly to building in security and privacy measures in its designed architecture. This study defines security requirements and challenges that are common in IoT and their solutions, ranging from simple things like authentication to trust management. Protecting data during network transit is also very important concern in the measures. Keywords: Internet of things; Security; Privacy; Data Mining INTRODUCTION The emergent growth of technology based on the Internet has led to the booming Internet of things (IoT) concept [1-3]. IoT is a technology where objects around us will be able to connect to each other and communicate via Internet. With the increasing number of applications to the use of IoT, there is a necessity for protecting the security and privacy of various entities involved in the system. In general the term IoT generally refers to scenarios where network connectivity and computing capability extends to objects, sensors and everyday items not resembling the normally computers, allowing these devices to generate exchange and consume data with minimal human intervention [4]. The term IoTs is used interchangeably with cyber physical systems (CPS) which refers to the combination of closely integrated physical processes, networking and computation. Thus the potential realization of IoT result into a hyper- connected world which take advantage of advancements and interoperability in: ubiquitous connectivity, widespread adoption of IP-based networking, smart grid, miniaturization, big data and the rise of cloud computing to offer new capabilities previously not possible. It is no secret to expect major transformation in many aspect of the way we live by virtue of adoption and implementation of the new technology. As such IoT is an emerging topic of technical, social, and economic significance for the upcoming technological era. Since IoT is based on network of intelligent devices, it faces the same cyber threat associated with CPS. The main barriers for expansion of the IoT are privacy, security and trust in spite of its myriad benefits. Thus the hyper connectivity of IoT raises the important issues of security and privacy [5-6]. Thus there is an imperative need to achieve the required state of security and privacy to convince consumers into utilizing the technology [7]. The attempt to address the threats would take varied approach including distributed approach designed for IoT environment in which the smart devices themselves are making context-aware authorization decisions. This brings in scenario where the smart device communication would be coupled with an end-to-end authentication, integrity and non-repudiation. Thus the proposed study will seek to provide solutions to the questions. IoT SCOPE AND ARCHITECTURE IoT enables things to be connected anywhere and anytime using any service or network. An easy to implement an IoT system mainly depends on identifying the proper discovery, identification, configuration and manipulation of interconnected devices and sensors [8]. A classification of IoT elements is proposed in [9] from a higher level perspective; - Hardware: This level includes sensors, central units and built-in communication hardware. Due to the limited resources in sensors, they are usually utilized in sensor networks where multiple sensors are linked together. A central unit in IoTs has ability of storing, processing, and delivering data to users. - Middleware: It consists of storage and computation tools for data analyses. Cloud computing is the integrity of several traditional technologies such as hardware virtualization, service-oriented architecture, load- balancing, distributed computing, grid computing, utility computing and autonomic computing. It can be considered as a natural step forward from the grid-utility model. - Presentation: There are visualization and interpretation tools in this level. These tools are designed for various applications and can be accessed from any platform.