Authors: Peace Azugo, Hein Venter, Mike Wa Nkongolo

Published on: April 19, 2024

Impact Score: 7.8

Arxiv code: Arxiv:2404.12855

Summary

• What is new: Introduction of UGRansome2024, an optimized dataset specifically tailored for the detection of ransomware in network traffic using an intuitionistic feature engineering approach.
• Why this is important: The development of proactive detection strategies against ransomware is hindered by the lack of datasets distinguishing normal from abnormal network behavior.
• What the research proposes: Using an intuitionistic feature engineering approach to create UGRansome2024, a dataset that facilitates the detection of ransomware in network traffic.
• Results: With the UGRansome2024 dataset and the Random Forest algorithm, an accuracy of 96% was achieved in classifying ransomware transactions, particularly highlighting the financial impact of Encrypt Decrypt Algorithms (EDA) and Globe ransomware variants.

Technical Details

Technological frameworks used: nan

Models used: Random Forest algorithm

Data used: UGRansome2024 dataset

Potential Impact

Cybersecurity vendors, IT service providers, and industries dependent on network security could significantly benefit or need to adapt due to the insights and methodologies presented.

Want to implement this idea in a business?

We have generated a startup concept here: GuardifyAI.