Optimizing IoT Threat Mitigation with Artificial Intelligence in Banking: A Multi-Objective Approach

This research introduces a novel AI-based mechanism for optimizing threat mitigation in IoT banking systems, addressing the growing vulnerabilities in this critical sector. The proposed mechanism, characterized by a precision of 0.88 and a balanced recall of 0.79, offers a robust defense against cyber threats. Leveraging a Deep Neural Architecture known as Pointer Networks, the mechanism adapts dynamically, ensuring high accuracy in threat identification (precision) while comprehensively covering potential threats (recall), resulting in a harmonious F1 score of 0.83. Through extensive threat-specific evaluations, the mechanism proves versatile, exhibiting high performance in scenarios involving malware (precision: 0.89, recall: 0.82, F1 score: 0.85), denial of service (DoS) attacks (precision: 0.87, recall: 0.78, F1 score: 0.82), and unauthorized access attempts (precision: 0.90, recall: 0.81, F1 score: 0.85). Scalability testing further validates its practical applicability, maintaining precision and F1 score values across varying sizes of IoT ecosystems. This research establishes the proposed mechanism as a potent and adaptable cybersecurity tool, poised to fortify the resilience of IoT banking systems against the dynamic landscape of cyber threats.