Dynamic Access Control Policy based on Blockchain and Machine Learning for the Internet of Things

Abstract

Abstract-The Internet of Things (IoT) is now destroying the barriers between the real and digital worlds. However, one of the huge problems that can slow down the development of this global wave, or even stop it, concerns security and privacy requirements. The criticality of these latter comes especially from the fact that the smart objects may contain very intimate information or even may be responsible for protecting people's lives. In this paper, the focus is on access control in the IoT context by proposing a dynamic and fully distributed security policy. Our proposal will be based, on one hand, on the concept of the blockchain to ensure the distributed aspect strongly recommended in the IoT; and on the other hand on machine learning algorithms, particularly on reinforcement learning category, in order to provide a dynamic, optimized and selfadjusted security policy.

Machine Learning based Access Control Framework for the Internet of Things

“…Many researchers focus on the application of RL to IoT security; for instance, the work in [28] opted for an RL approach to learn a sub-band selection policy so that it could avoid both jammer signals as well as interference from other radios in wideband autonomous cognitive radios (WACRs). Two of our previous works [1,29] tackled the Access Control (AC) in IoT scenarios, the two building blocks were: first taking into account the smart devices' context while making an AC decision; and proposing AC policies that can be improved and optimized over time. However, given the enormous and heterogeneous amount of data generated by IoT devices, the proposition benefits from the power of RL, to accomplish this task.…”

“…Zero-day attacks Good results in time-based environments Data augmentation [25], [27] Security policy improvements RL Policy optimization Policy efficiency [1], [28], [29] New and unprecedented attacks K-means, RL Zero-day & Sybil attacks detection Avoid jammer signals [1], [20], [28], [29] www.ijacsa.thesai.org…”

“…First thing to consider when treating AC in IoT is the overall architecture, whether it is distributed (like blockchain based solutions [40]) or centralized as long as it is equipped with the collaboration aspect. In fact, each of these two architectures has its advantages and drawbacks [29]; however, without loss of generality, this paper mainly focus on the second one for the following reasons: (i) IoT, at least as we know it today, requires that each device has an owner, whether a person, in the case of a smart home for example or an organization in industry or in smart cities. So practically an approach that takes this aspect into consideration will be closer to reality.…”

SoK of Used Cryptography in Blockchain

“…OrBAC consists of three entities (subject, action, object) which define that some subject has the permission to realize some action on some object. OrBAC has already been used in blockchain for IoT in a fair access blockchain model [92] and in dynamic access control model on blockchain [145].…”

Towards Blockchain-Based Identity and Access Management for Internet of Things in Enterprises

“…Even though several works propose blockchain technology for access control (e.g. [19,22]), research has put little emphasis on whether and how blockchain can be applied to the more fundamental concept of IAM in enterprises. The question whether the blockchain technology can deal with the mentioned IAM challenges as a whole in context of enterprise IoT has not been entirely addressed in research yet.…”