The Industrial Internet of Things (IIoT) has led to the growth and expansion of various new opportunities in the new Industrial Transformation. There have been notable challenges regarding the security of data and challenges related to privacy when collecting real-time and automatic data while observing applications in the industry. This paper proposes an Federated Transfer Learning for Authentication and Privacy Preservation Using Novel Supportive Twin Delayed DDPG (S-TD3) Algorithm for IIoT. In FT-Block (Federated transfer learning blockchain), several blockchains are applied to preserve privacy and security for all types of industrial applications. Additionally, by introducing the authentication mechanism based on transfer learning, blockchains can enhance the preservation and security standards for industrial applications. Specifically, Novel Supportive Twin Delayed DDPG trains the user model to authenticate specific regions. As it is considered one of the most open and scalable interacting platforms of information, it successfully helps in the positive transfer of different kinds of data between devices in more significant and local operations of the industry. It is mainly due to a single authentication factor, and the poor adaptation to regular increases in the number of users and different requirements that make the current authentication mechanism suffer a lot in IIoT. As a result, it has been very clearly observed that the given solutions are very useful.

Online banking transaction fraud occurs when fraudulent activity is initiated by a criminal. Such as seizing accounts and hacking points to execute online fund transfer mechanisms. This scenario is a main challenge for the upcoming data processing that is traveling only online. In today’s scenario, most of the work has become digital. In such cases, machine learning algorithms must be ex-traordinary to take stringent security measures to transfer such funds over a public channel. The paper analyzes some machine learning techniques such as naive Bayes and support vector machines to prevent loss. The machine has been used based on real data and can reduce losses manifold. After processing, the optimization reached 95 percent in terms of accuracy. The implementation can improve business operations to move the funds online while reducing overall risk.