An Innovative Strategy for Efficiently Retrieving Data from Ransomware Attacks

An Innovative Strategy for Efficiently Retrieving Data from Ransomware Attacks

The frequency of ransomware attacks has surged, disrupting regular business operations and
resulting in data theft and loss, which has raised significant concerns about brand reputation and information
security. This study scrutinizes existing methodologies for recovering data post-ransomware attacks across
diverse industries. It also presents an innovative framework aimed at securing critical data stored in servers
through network segmentation, the utilization and deployment of a honeypot device for log collection, and
machine learning-driven devices. The proposed network architecture targets early detection of ransomware
attacks and automated response, reducing reliance on manual intervention. Validation of the framework is
conducted using ransomware attack datasets, with machine learning algorithms compared for their efficacy in
detecting attacks based on behavioural analysis of network traffic. Performance evaluation metrics measure
the effectiveness of the deployed machine learning algorithms, revealing that the XGBoost technique surpasses
others in early ransomware attack detection.