Distributed Machine Learning Architecture for Security Improvement in Computer Drafting and Writing in Art Asset Identification System

Abstract

Art asset identification service is becoming increasingly important in the art market, where the value of art assets is constantly changing. The service provides authentication, evaluation, and provenance research for artworks, which helps art collectors and institutions to protect their investments and ensure the authenticity of their collections. The effective management of big data is critical for the art asset identification service, and there are several big data management technologies that can be achieved. To improve security in the big data Management model uses Distributed Associative Rule Mining is implemented with Hashing based Symmetric Key Cryptography. The designed model comprises of Associate Rule Hashing Symmetric Key (ARHSK). The proposed ARHSK model comprises the symmetric key generated with the hashing model to secure art assets. With the ARHSK information is stored and processed for security features. The performance of the ARHSK model is implemented with the machine learning model for classification. Simulation analysis expressed that ARHSK exhibits an improved classification accuracy of 99.67% which is ~13% higher than the CNN and ANN models.