The ATTRIBUTE-BASED K-ANONYMITY AND SE-PSO-ENHANCED SIGMOID-LECUN-TCN FOR MITIGATING RANSOMWARE ATTACK WITH API PROTECTION FOR CLOUD APPLICATIONS

RANSOMWARE ATTACK WITH API PROTECTION FOR CLOUD APPLICATION

Abstract

The rapid proliferation of cloud services has heightened concerns about data security, particularly with ransomware exploiting API vulnerabilities to encrypt and compromise sensitive data. This study introduces a dual approach combining SE-PSO-enhanced Sigmoid-LeCun Temporal Convolutional Networks (TCN) for anomaly detection and Attribute-Based K-Anonymity (ABKA) for data anonymization in cloud environments. The SE-PSO optimization fine-tunes TCN parameters, achieving exceptional performance metrics—98.6% accuracy, 97.8% precision, and 98.1% recall. These results underscore the model's efficacy in detecting ransomware patterns while reducing false alarm rates. The integration of ABKA safeguards sensitive cloud data by preventing attribute disclosure, further strengthening privacy. By addressing both detection and prevention, this approach enhances API access management and provides a robust defence against ransomware attacks. This work marks a significant advancement in real-time cloud security solutions, offering scalability and cost-efficiency superior to existing methods.