Cloud Forensics Analysis Framework for Secure and Efficient Data Retrieval

Cloud Forensics Analysis Framework for Secure and Efficient Data Retrieval

연구 분야: Safety

학회: 2024 OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 4.0

This study’s Cloud Forensics Analysis Framework seeks secure and effective data recovery methods. The framework’s five strategies make digital evidence retrieval methodical and versatile. These include adaptive evidence collecting, secure data retrieval, machine learning-based anomaly detection, intelligent automation, and context-aware metadata analysis. Each approach targets a distinct forensic process step. This makes cloud forensics investigations seem difficult. The customizable Evidence gathering Algorithm adapts to cloud characteristics to collect evidence. This allows contextually aware and flexible digital evidence retrieval. The secure Data Retrieval Techniques Algorithm protects data privacy and chain of custody with advanced encryption and validation. The Machine Learning-Based Anomaly Detection Algorithm checks protected data for anomalies before sending it, making the system safer. Investigators may focus on more complex cases by simplifying and sorting basic forensic activities with the Intelligent Automation Algorithm. The Context-Aware Metadata study Algorithm weights and prioritizes cloud metadata. This completes metadata analysis. Compared to other approaches, the framework has greater Precision, Recall, F1 Score, Processing Time, Resource Utilization, and Compatibility Score. Charts convey system operation in a simple manner. This powerful and adaptable Cloud Forensics Analysis Framework improves cloud forensics by providing a thorough and effective solution to recover and safeguard data. The Cloud Forensics, This paper discusses context-aware metadata analysis, data retrieval, intelligent automation, machine learning-based anomaly detection, performance metrics, secure data retrieval techniques, support vector machines, and visual representation.