Rohit Sharma

Bio: Rohit Sharma is an academic researcher from Indian Institutes of Information Technology. The author has contributed to research in topics: Access control & Service provider. The author has an hindex of 2, co-authored 2 publications receiving 28 citations.

BlockAPP: Using Blockchain for Authentication and Privacy Preservation in IoV

Abstract: Recent proliferation in disruptive technologies has opened up a new horizon for Internet of Vehicles (IoV). The success of IoV highly depends on the robustness of vehicular information system as a dispute among the service providers on data rights or any kind of security violation could disrupt the transport services altogether. In this work we propose a blockchain based novel architecture for vehicle authentication and privacy preservation with seamless access control for IoV. Proposed architecture is decentralized, robust and scalable. Along with privacy preserving authentication and conflict-free access-log maintenance, the proposed BlockAPP protocol also supports an optional traceability feature. Performance evaluation using smart contact over Ethereum Blockchain validates the effectiveness of the proposed architecture.

B2VDM: Blockchain Based Vehicular Data Management

Abstract: Smart interconnected vehicles generate a huge amount of data to be used by a wide range of applications. Although cloud based data management is currently in practice, for many applications serving road safety or traffic regulation, it is utmost important that applications access these data at the site itself for improved quality of service. Road side units (RSUs) play a crucial role in handling these vast amount of vehicular data and serving the running applications in turn. In this current era of edge computing, in-place data access is also proven to be advantageous from cost point of view. As multiple applications from different service providers are interested to access different fragments of these data, a robust access control mechanism is needed to ensure desired level of security as well as reliability for these data. In this paper, we introduce B2VDM, a novel architecture for vehicular data management at RSUs, that provides a seamless access control using Blockchain technology. The proposed B2VDM framework also implements a simple load distribution module, which maintains the reliability by minimizing the number of packet drops at a heavily loaded RSU during peak hours. An extensive evaluation using Etherium Blockchain validates the effectiveness of the proposed architecture.

Blockchain-Enabled Cross-Domain Object Detection for Autonomous Driving: A Model Sharing Approach

Abstract: Object detection for autonomous driving is a huge challenge in the cross-domain adaptation scenario, especially for the time- and resource-consuming task. Distributed deep learning (DDL) has demonstrated a considerably good balance between efficiency and computation complexity. However, the reliability of DDL is low. Moreover, the cost of training data and model is not priced well. In this article, a novel blockchain-enabled model sharing approach is proposed to improve the performance of object detection with cross-domain adaptation for autonomous driving systems. Based on the blockchain and mobile-edge computing (MEC) technology, a domain-adaptive you-only-look-once (YOLOv2) model is trained across nodes, which can reduce significantly the domain discrepancy for different object categories. Furthermore, smart contracts are developed to perform data storage and model sharing tasks efficiently. The reliability of model sharing is ensured with blockchain consensus. We evaluate the proposed method under public data sets. The simulation results demonstrate that the efficiency and reliability of the proposed approach are better than the reference model.