Privacy Preserving in Blockchain Based on Partial Homomorphic Encryption System for Ai Applications

Abstract

The synergy between artificial intelligence and blockchain is increasing in the computing environment. To realize this blockchain technology making its way into applications such as healthcare, financial services, Internet of Things and much more., that use artificial intelligence making it more defendable to attacks. The current blockchain technology uses different encryption algorithms such as SHA256, MD5 etc. The blockchain attacks such as collision attack, primage attack and attacks on wallet motivated us to experiment on partial homomorphic encryption to enhance the strength of blockchain technology. This article considers i) Goldwasser- Micali and ii) Paillier encryption schemes for the comparative evaluation study with a focus on data privacy techniques. We believed and proved that the above two encryption schemes that were considered have less processing time and provide more strength to the possible attacks. While we present our preliminary results in this study, we discuss the pros and cons of the Goldwasser-Micali, Paillier and non-homomorphic encryption schemes that are expected to add value to blockchain technology to be used in Artificial Intelligence (AI) applications.