A Study on the Application of Distributed System Technology-Guided Machine Learning in Malware Detection.

Area of Science:

• Computer Science
• Cybersecurity
• Machine Learning

Background:

• The internet's expansion has led to a surge in sophisticated and rapidly spreading malware.
• Existing malware detection methods struggle to keep pace with the evolving threat landscape.
• Effective malware detection is crucial to mitigate network damage and societal impact.

Purpose of the Study:

• To propose a novel approach for effective malware detection in a distributed environment.
• To enhance the capability of detecting unknown and rapidly evolving malware threats.
• To integrate machine learning algorithms for robust malware classification and detection.

Main Methods:

• Implemented a distributed system where detection nodes perform anomaly detection and feature analysis.
• Developed a mechanism to update new malware features across all network nodes.
• Trained a random forest-based machine learning algorithm for malware classification.

Main Results:

• The proposed distributed framework enhances global malware detection capabilities.
• The system demonstrates robust real-time response to emerging malware threats.
• Experiments on Ember 2017 and Ember 2018 datasets show advanced performance.

Conclusions:

• The integrated approach of distributed systems and machine learning offers an effective solution for modern malware detection.
• The framework provides a scalable and robust method to combat the increasing complexity of cyber threats.
• This research contributes a significant advancement in the field of automated malware analysis and defense.