PPSF A Privacy-Preserving and Secure Framework using Blockchain-based Machine-Learning for IoT-driven Smart Cities

Abstract : With the evolution of the Internet of Things (IoT), smart cities have become the mainstream of urbanization. IoT networks allow distributed smart devices to collect and process data within smart city infrastructure using an open channel, the Internet. Thus, challenges such as centralization, security, privacy (e.g., performing data poisoning and inference attacks), transparency, scalability, and verifiability limits faster adaptations of smart cities. Motivated by the aforementioned discussions, we present a Privacy-Preserving and Secure Framework (PPSF) for IoT-driven smart cities. The proposed PPSF is based on two key mechanisms: a two-level privacy scheme and an intrusion detection scheme. First, in a two-level privacy scheme, a blockchain module is designed to securely transmit the IoT data and Principal Component Analysis (PCA) technique is applied to transform raw IoT information into a new shape. In the intrusion detection scheme, a Gradient Boosting Anomaly Detector (GBAD) is applied for training and evaluating the proposed two-level privacy scheme based on two IoT network datasets, namely ToN-IoT and BoT-IoT. We also suggest a blockchain-InterPlanetary File System (IPFS) integrated Fog-Cloud architecture to deploy the proposed PPSF framework. Experimental results demonstrate the superiority of the PPSF framework over some recent approaches in blockchain and non-blockchain systems.

 EXISTING SYSTEM :

 ? In addition, information leakage risks exist in the third party’s mobile edge computing (MEC) server. ? To address aforementioned security and privacy issues, we adopt blockchain and differential privacy. ? Therefore, customers and the requester can save high service fees while keeping the crowdsourcing system functional. ? Due to the limitation of the block size, we propose to use the InterPlanetary File System (IPFS) as the distributed storage solution when the model size is large. ? In particular, these advanced technologies enable manufacturers to maintain a seamless connection among their smart home appliances.

 DISADVANTAGE :

 ? One hardware solution to e-government security issues is the use of eID system for identification, authentication, confidentiality and integrity of users’ information. ? Another technical solution for security and privacy issues in e-government is an authentication framework proposed in. ? An ID for a user is issued and a new blockchain address is generated for the user containing public and private keys, allowing the identification of the owner. ? The proposed system also has the potential of solving the interoperability issues between governance departments which is one of the limitations of existing e-government systems.

 PROPOSED SYSTEM :

 • A hierarchical crowdsourcing FL system is proposed to build the machine learning model to help home appliance manufacturers improve their service quality and optimize functionalities of home appliances. • They proposed to leverage the sketch algorithms to build the sketching-based FL, which provides privacy guarantees while maintaining the accuracy. • To protect customers’ privacy and improve the test accuracy, we enforce differential privacy on the extracted features and propose a new normalization technique. • we propose a new normalization technique which delivers a higher test accuracy than batch normalization, while preserving the privacy of the extracted features of each participant’s data.

 ADVANTAGE :

 ? The network is able to offer the performances provided by the blockchain technology and DPoS consensus protocol such as scalability, speed, interoperability, and transparency, and it can handle a large number of transactions. ? Electronic government (e-government) uses information and communication technologies to deliver public services to individuals and organisations effectively, efficiently and transparently. ? E-government users enjoy the online services without leaving their comfortable homes, evading long queues in public offices whilst saving time and transportation costs, and at the same time the service providers can deliver services more effectively and efficiently. ? The DPoS is adopted here as the consensus algorithm due to its computational efficiency in adding transactions and sealing a block.