US Patent Application 18447928. SYSTEMS AND METHODS FOR CLASSIFYING MALWARE BASED ON FEATURE REUSE simplified abstract

From WikiPatents
Jump to navigation Jump to search

SYSTEMS AND METHODS FOR CLASSIFYING MALWARE BASED ON FEATURE REUSE

Organization Name

VMware, Inc.

Inventor(s)

Roman Vasilenko of Oceanside CA (US)

Corrado Raimondo of London (GB)

SYSTEMS AND METHODS FOR CLASSIFYING MALWARE BASED ON FEATURE REUSE - A simplified explanation of the abstract

This abstract first appeared for US patent application 18447928 titled 'SYSTEMS AND METHODS FOR CLASSIFYING MALWARE BASED ON FEATURE REUSE

Simplified Explanation

- The patent application describes systems and methods for classifying malware based on the frequency of feature reuse. - The system can identify a malicious feature frequency, a benign feature frequency, and a first weight value. - It can generate a first reuse vector based on the malicious feature frequency and the benign feature frequency. - The system can determine if a training binary (a file used for training) includes a first feature and a second feature. - The second feature is associated with a second reuse vector and a second weight value. - If the first binary includes both features, the system constructs a reuse tensor using the first and second reuse vectors, and the first and second weight values. - The system then trains a malware classification model using the reuse tensor and the known classification associated with the training binary.


Original Abstract Submitted

Systems and methods for classifying malware based on the frequency of feature reuse are provided. The system can identify a malicious feature frequency, a benign feature frequency, and a first weight value. The system can generate a first reuse vector based on the malicious feature frequency and the benign feature frequency. The system can determine that a training binary associated with a known classification includes the first feature and a second feature, the second feature associated with a second reuse vector and a second weight value. The system can construct, responsive to the determination that the first binary includes the first feature and the second feature, a reuse tensor using the first reuse vector, the second reuse vector, the first weight value, and the second weight value. The system can train a malware classification model using the reuse tensor and the known classification associated with the training binary.

Retrieved from "http://wikipatents.org/index.php?title=US_Patent_Application_18447928._SYSTEMS_AND_METHODS_FOR_CLASSIFYING_MALWARE_BASED_ON_FEATURE_REUSE_simplified_abstract&oldid=12695"