Detection of malicious code by applying machine learning classifiers on static features: A state-of-the-art survey

Keyphrases

• State of the Art Survey 100%
• Malicious Code 100%
• Machine Learning Classifiers 100%
• Static Features 100%
• Active Learning 66%
• Imbalance Problem 66%
• Classification Methods 33%
• Detection Accuracy 33%
• Detection Method 33%
• Multiple Classifier System 33%
• Classification Results 33%
• Machine Learning Techniques 33%
• Feature Selection Methods 33%
• Classification Algorithms 33%
• Byte 33%
• Learning Performance 33%
• Realistic Scenario 33%
• Executable File 33%
• Emerging Threats 33%
• Learning Mechanisms 33%
• Feature Extracting 33%
• Chronological Evaluation 33%
• Opcode 33%
• N-gram 33%
• Individual Classifiers 33%
• Representation Selection 33%
• Weighting Algorithm 33%
• Open Research Issues 33%
• Portable Executable 33%
• Malicious Files 33%

Computer Science

• Malicious Code 100%
• Machine Learning 100%
• Learning System 100%
• Active Learning 66%
• Feature Selection 33%
• Classification Algorithm 33%
• Life Situation 33%
• Detection Method 33%
• classification result 33%
• Executable File 33%
• Extracted Feature 33%
• False Positive 33%
• Learning Mechanism 33%
• multiple classifier 33%
• Detection Accuracy 33%
• Individual Classifier 33%
• Open Research 33%
• Emerging Threat 33%