AUTHOREA
Log in
Sign Up
Browse Preprints
LOG IN
SIGN UP
Essential Site Maintenance
: Authorea-powered sites will be updated circa 15:00-17:00 Eastern on Tuesday 5 November.
There should be no interruption to normal services, but please contact us at
[email protected]
in case you face any issues.
Daniel Lummen
Public Documents
1
Opcode-Based Ransomware Detection Using Hybrid Extreme Gradient Boosting and Recurren...
Daniel Lummen
and 4 more
October 22, 2024
Ransomware continues to pose a growing threat to global cybersecurity, with attackers leveraging increasingly sophisticated techniques to evade traditional detection mechanisms. A novel hybrid approach combining Extreme Gradient Boosting (XGBoost) with Recurrent Neural Networks (RNNs) introduces a powerful solution for detecting ransomware through the analysis of opcode sequences. XGBoost's capacity for efficient feature selection, coupled with the RNN's ability to model the temporal structure of sequential data, allows for a comprehensive detection framework capable of identifying ransomware with high accuracy. The proposed method achieves significant improvements over traditional machine learning algorithms, as demonstrated through rigorous experiments and evaluation metrics. By effectively addressing the complexities of opcode-based detection, this approach provides a scalable and adaptable solution for modern ransomware defense, offering enhanced detection performance and the potential for real-world application.