An Attribute Extraction for Automated Malware Attack Classification and Detection Using Soft Computing Techniques.

Area of Science:

• Computer Science
• Cybersecurity
• Machine Learning

Background:

• Malware is increasingly sophisticated, posing significant threats to networks and data.
• Timely detection of malware is crucial for preserving information and intelligence.
• Existing detection methods require enhancement to combat evolving cyber threats.

Purpose of the Study:

• To compare various attribute extraction techniques with machine learning algorithms for static malware classification and detection.
• To identify the most effective combination for accurate and efficient malware identification.
• To discuss advanced malware, detection strategies, and defense mechanisms.

Main Methods:

• Evaluation of diverse attribute extraction techniques.
• Comparison of distinct machine learning algorithms for classification.
• Implementation of Principal Component Analysis (PCA) for attribute extraction and Support Vector Machine (SVM) for classification.

Main Results:

• The integration of PCA attribute extraction with the SVM classifier yielded the highest accuracy rate.
• This combined approach required the fewest attributes for effective malware detection.
• The proposed method achieved an overall accuracy of 96%, outperforming existing techniques.

Conclusions:

• The PCA-SVM combination is a highly effective method for static malware classification and detection.
• This approach offers improved accuracy and efficiency in identifying malicious software.
• Findings provide insights into defending systems and data against sophisticated malware attacks.