E-UDE Model Reduces Malware Propagation Prediction Errors by 66%
Original title: E-UDE: A Scientific Machine Learning Model for Malware Propagation Dynamics
The E-UDE framework achieves RMSE of 783.70 and MAE of 421.65 on real-world data while remaining robust to noise.
This study presents the Enhanced Universal Differential Equation (E-UDE) framework for malware propagation dynamics. It explicitly incorporates detailed key factors influencing spread. Evaluation on real-world data shows superior performance over classical ODE and UDE models. The model supports scenario analyses for cybersecurity control factors using the Code Red and Witty Worm datasets.
- E-UDE reduces RMSE by 66% versus Classical ODE and 39% versus UDE
- Test RMSE of 634.6, Test MAE of 419.3, Test Correlation of 0.964
- Stable predictive capability as noise level increases
- Assessed on Code Red and Witty Worm datasets
From the original article
1 min read at arxiv.orgUnderstanding the malware propagation dynamics over the Internet is crucial for effectively controlling its spread. Existing mechanistic and data-driven models in the context of malware propagation dynamics, have some issues with either interpretability or predictive accuracy.
By Vineet Kumar · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.