Mobile malware detection through analysis of deviations in application network behavior

Keyphrases

• Malware 100%
• Network Applications 100%
• Deviation Analysis 100%
• Network Traffic Patterns 100%
• Mobile Malware Detection 100%
• Network Behavior 100%
• Mobile Devices 66%
• Self-updating 66%
• Popular 33%
• Low Performance 33%
• Malicious Attacks 33%
• Behavior-based 33%
• Behavioral Patterns 33%
• Supervised Machine Learning 33%
• Expected Behaviour 33%
• Network Pattern 33%
• Anomaly Detection System 33%
• Masquerade 33%
• Normal Behavior 33%
• Mobile Users 33%
• New Behaviors 33%
• Low False Alarm Rate 33%
• Static Analysis Method 33%
• Dynamic Analysis Method 33%
• Malicious Applications 33%
• Malicious Code 33%
• Android Devices 33%
• Semi-supervised Machine Learning 33%
• Google Android 33%
• Evaluation Experiment 33%
• Cellular Infrastructure 33%
• Application Category 33%
• Traffic Pattern 33%
• Mobile Malware 33%
• Infrastructure Companies 33%
• Mobile Application 33%
• Performance Overhead 33%
• Local Learning 33%

Computer Science

• Malware Detection 100%
• Network Application 100%
• Mobile Malware 100%
• Traffic Pattern 100%
• Mobile Device 75%
• Malware 75%
• Network Traffic 75%
• Android 50%
• Machine Learning 25%
• Malicious Attack 25%
• Normal Behavior 25%
• False Alarm Rate 25%
• Dynamic Analysis 25%
• Malicious Application 25%
• Behavioral Pattern 25%
• Installed Application 25%
• Malicious Code 25%
• Mobile Application 25%
• Lower Performance 25%
• Anomaly-Based Detection 25%