Enhancing Cybersecurity in IoT-Based Banking Systems Using Artificial Intelligence

Since the dawn of the Internet of Things (IoT) era, banking systems have been exposed to an ever growing cyber threat as more and more internet connected devices add to the number of connected devices and sensitive data in transit increasing each day. The contribution of this work is to develop a robust cybersecurity framework based on Artificial Intelligence (AI) to protect IoT supported banking infrastructure. Our approach to an anomaly detection by deep learning algorithms and deep learning algorithms which uses a tool like Tensor Flow for real time threat analysis and adaptive learning. Continuous monitoring and predictive analytics are used in this model which will detect the irregular patterns and proactively cuts potential threats. Moreover, it not only improves detection accuracy, but also lessens the number of false positives with the help of learning from the evolving threat, thus making IoT banking ecosystems more robust against the sophisticated cyberattacks. The model was experimentally found to significantly enhance threat identification and response likelihoods, which are proven by the experiment to improve the cybersecurity of IoT banking platforms.