Mainak Chatterjee

Mehrdad Salimitari, Mohsen Joneidi, Mainak Chatterjee

A new framework for a secure and robust consensus in blockchain-based IoT networks is proposed using machine learning. Hyperledger fabric, which is a blockchain platform developed as part of the Hyperledger project, though looks very apt for IoT applications, has comparatively low tolerance for malicious activities in an untrustworthy environment. To that end, we propose AI-enabled blockchain (AIBC) with a 2-step consensus protocol that uses an outlier detection algorithm for consensus in an IoT network implemented on hyperledger fabric platform. The outlier-aware consensus protocol exploits a supervised machine learning algorithm which detects anomaly activities via a learned detector in the first step. Then, the data goes through the inherent Practical Byzantine Fault Tolerance (PBFT) consensus protocol in the hyperledger fabric for ledger update. We measure and report the performance of our framework with respect to the various delay components. Results reveal that our implemented AIBC network (2-step consensus protocol) improves hyperledger fabric performance in terms of fault tolerance by marginally compromising the delay performance.

Mehrdad Salimitari, Mainak Chatterjee

The success of blockchain as the underlying technology for cryptocurrencies has opened up possibilities for its use in other application domains as well. The main advantages of blockchain for its potential use in other domains are its inherent security mechanisms and immunity to different attacks. A blockchain relies on a consensus method for agreeing on any new data. Most of the consensus methods which are currently used for the blockchain of different cryptocurrencies require high computational power and thus are not apt for resource-constrained systems. In this article, we discuss and survey the various blockchain based consensus methods that are applicable to resource constrained IoT devices and networks. A typical IoT network consists of several devices which have limited computational and communications capabilities. Most often, these devices cannot perform intensive computations and are starved for bandwidth. Therefore, we discuss the possible measures that can be taken to reduce the computational power and convergence time for the underlying consensus methods. We also talk about some of the alternatives to the public blockchain like private blockchain and tangle, along with their potential adoption for IoT networks. Furthermore, we review the existing consensus methods that have been implemented and explore the possibility of utilizing them to realize a blockchain based IoT network. Some of the open research challenges are also put forward.