Abstract
This study designs and deploys zero-trust secure multiparty computation (SMPC) algorithms to enhance financial cybersecurity in small and medium-sized enterprises (SMEs) within the U.S. supply chain. Utilizing TensorFlow for machine learning, Apache Kafka for real-time data processing, and SMPC protocols, the proposed solution aims to provide robust, scalable, and economically viable cybersecurity measures. The research involved developing advanced machine learning-based zero-trust algorithms using TensorFlow, integrating SMPC protocols for secure data computation, and utilizing Apache Kafka for real-time data processing. The algorithms were tested and validated in both simulated and real-world SME environments to evaluate their effectiveness. The implementation of zero-trust SMPC algorithms led to significant improvements in various cybersecurity metrics. The true positive rate (TPR) increased from 85% to 98%, and the false positive rate (FPR) decreased from 5% to 1%. Average incident response time was reduced from 4 hours to 1 hour, and the average cost per incident decreased by 80%, with data loss per incident reduced by 90%. Compliance with GDPR and CCPA standards improved by 35.71% and 38.46%, respectively. User satisfaction increased by 41.67%, and system availability improved from 95% to 99%, with network latency decreasing by 60%. The results demonstrate that zero-trust SMPC algorithms significantly enhance financial cybersecurity for SMEs, reducing security incidents and financial impacts, improving regulatory compliance, and increasing user satisfaction and system performance. These advancements are crucial for strengthening the resilience and stability of the U.S. supply chain, supporting economic growth.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call