Privacy preserved data sharing using blockchain and support vector machine for industrial IOT applications
Arvind Kumar Pandey, Rini Saxena, Aishwary Awasthi, M P Sunil
Abstract
The Industrial Internet of Things (IIoT) paradigm's fast expansion in the amount of information created from linked devices creates new opportunities for improving the service quality and applications through sharing of data. Data security is a significant problem since training and Support Vector Machine (SVM) classifier often involves compiling tagged IoT data from several organizations. Beyond causing the suppliers to lose money, disclosing sensitive information might cause significant problems. To solve these issues, introduced a secure SVM, which is a Privacy-Preserving SVM (PP-SVM) training method using block chain-based encoded IoT data, to fill the void between ideal assumptions and practical restrictions. IoT messages are encrypted before being stored on a decentralized system because Block chain offers safe and dependable data exchange platforms across several data sources. Using a homomorphic cryptographic algorithm, Paillier, reliable modules have been developed, such as protected algebraic multiplying and protected comparison. Furthermore, a protected SVM learning algorithm that only needs two conversations during a single step has been created. According to stringent security assessment, proposed approach guarantees SVM model parameters for data professionals and secrecy of sensitive information for each data source. Extensive testing backs up effectiveness of the suggested plan.