A Hybrid Machine Learning Framework for Real-Time Malware Detection Using PE Feature Analysis

Key Points

• The aim is to assess a hybrid machine learning framework for enhancing real-time malware detection effectiveness.
• Evaluated a hybrid machine learning framework combining multiple algorithms for malware detection.
• Used PE (Portable Executable) feature analysis for identifying malware characteristics.
• Conducted simulations to test the framework's detection speed and accuracy.
• Achieved a detection rate of 95% using the hybrid framework with an average processing time of 0.5 seconds per sample.
• Demonstrated an improvement in detection accuracy of 15% compared to traditional methods.
• Indicated reduced false positive rates by 10% when deploying the new framework.