Comprehensive Framework for Implementing Blockchain-enabled Federated Learning and Full Homomorphic Encryption for Chatbot security System

Abstract

Chatbot is an artificial intelligence application that can provide a conversational environment between human and machine. Most organizations and industries are willing to lay out their services through chatbot because it can provide 24/7 customer support. Meanwhile it raises security and privacy challenges like access control, data leakage during transmission, SQL injection attack, language model attack which make the users concerned about their data, performance and accuracy. Therefore this research paper proposed a comprehensive framework integrated blockchain, federated learning and fully homomorphic encryption algorithm with face recognition to solve above mentioned chatbot’s challenges. The experimental result shows that distributed system improves chatbot accuracy (90%) and more transaction in less time with more clients do not affect the performance. In contrast, more iteration and clients will decrease the accuracy, performance and transactions in centralized system. In addition, fully homomorphic encryption improve and speed up data encryption process. It encrypted more data (1792 MB) in a small amount of 1240 time/sec and conversation/transactions can be transferred via a secure network to ensure the confidentiality, integrity and authenticity of users’ data. The implementation of such comprehensive framework in real-life can improve chatbot security that is actively work as a customer agent in organization.