AI-Driven F2N-ECC Framework for Secure, Real-Time E-Commerce Transactions

As e-commerce continues to expand rapidly, ensuring secure real-time transactions has become increasingly important. This paper introduces an innovative cryptographic framework powered by artificial intelligence, integrating a Long Short-Term Memory (LSTM) based prediction engine with a Field-to-Number enhanced Elliptic Curve Cryptography (F2N-ECC) module. Designed for adaptive and secure processing, the system dynamically adjusts encryption strength based on real-time fraud risk assessments, while blockchain-based logging ensures tamper-proof transaction verification. Tests using a labeled e-commerce dataset show promising results: 96.4% accuracy in fraud detection, a 50% reduction in latency thanks to F2N-ECC, and strong scalability for Internet of Things (IoT) environments. Additionally, a case study on anomaly detection in financial time-series data highlights the framework’s flexibility across different domains. Overall, this architecture paves the way for AI-driven, post-quantum resilient security solutions tailored for the future of digital commerce.