System and method of synthesizing potential malware for predicting a cyberattack
A system and method for malware classification using machine learning models trained using synthesized feature sets based on features extracted from samples of known malicious objects and known safe objects. The synthesized feature sets act as virtual samples for training a machine learning classifier to recognize new objects in the wild that are likely to be malicious.
1. A method for malware detection in a computer system comprising the following steps:
extracting static and dynamic features of a known malware sample;
extracting static and dynamic features of a known clean object sample;
preparing a synthetic malware feature dataset and a clean objects feature dataset by grouping features in datasets by the type of feature; and
synthesizing new feature sets in the synthetic malware feature dataset,
wherein each new feature set is a combination of the extracted feature sets related to a first known malware sample and the result of a substitution of at least one feature related to a first known malware sample with a least one feature related to a second known malware sample;
training a malware classification machine learning model based on the synthetic malware feature dataset and the clean objects feature dataset;
obtaining an unknown system object for malware analysis; and
classifying the unknown system object, wherein the result of classification includes one or more of the following: a rate of conformity with at least one class of objects, a determination if the file is malicious or not, and a determination of malware type.
2. The method of claim 1 , wherein the substitution of at least one feature is performed for features from the same group.
3. The method of claim 2 , wherein the step of synthesizing new feature sets further comprises the step of selecting feature sets related to malware samples of one class of objects.
4. The method of claim 3 , wherein the one class of objects is defined using at least one of static analysis, dynamic analysis, sample execution log analysis, and malware classification based on static and dynamic analysis.
5. The method of claim 4 , wherein the step of synthesizing new feature sets in the malware feature dataset further comprises filtering out features corresponding to known clean object samples.
6. A system for malware detection in a networked computer system comprising:
a microprocessor, coupled with a first nontransitory storage medium;
a known malware sample comprising a plurality of features;
a known clean object sample comprising a plurality of features;
a first software module, under program control of the microprocessor,
configured for static and dynamic feature extraction by identifying vectors of the plurality of features in the known malware sample;
a second software module, under program control of the microprocessor, configured for static and dynamic feature extraction by identifying vectors of the plurality of features of a known clean object sample;
a synthetic malware feature dataset and a clean objects feature dataset coupled to a second nontransitory storage medium, prepared from the features extracted by the static and dynamic feature extractors;
a malware classification machine learning model, under program control of the microprocessor, trained on the synthetic malware feature dataset and the clean objects feature dataset;
wherein the synthetic malware feature dataset and clean objects feature dataset includes grouped features in datasets by the type of feature;
wherein the synthetic malware feature dataset and clean objects feature dataset includes grouped features in datasets by the type of feature; and
wherein the synthetic malware feature dataset is a combination of the extracted feature sets related to a first known malware sample and the result of a substitution of at least one feature related to a first known malware sample with a least one feature related to a second known malware sample.
7. The system of claim 6 , wherein the substitution of at least one feature is performed for features from the same group.
8. The system of claim 7 , wherein the synthetic malware dataset comprises feature sets related to malware samples of one class of objects.
9. The system of claim 8 , wherein the one class of objects is defined using at least one of static analysis, dynamic analysis, sample execution log analysis, and malware classification based on static and dynamic analysis.
10. The system of claim 9 , wherein the synthetic malware feature dataset has been filtered to remove feature vectors corresponding to known clean object samples.
11. A method for malware detection in a computer system, the method comprising:
loading a malware feature dataset and a clean objects feature dataset,
wherein the datasets include static and dynamic feature sets;
grouping features in datasets by the type of features;
selecting feature sets related to malware samples of one class of objects;
synthesizing new feature sets in the malware feature dataset;
training a malware classification machine learning model based on the static and dynamic features from the malware feature dataset extended with the new feature sets and the clean objects feature dataset;
preparing a synthetic malware feature dataset and a clean objects feature dataset;
obtaining an unknown system object for malware analysis; and
classifying the unknown system object, wherein the result of classification includes one or more of the following: a rate of conformity with at least one class of objects, a determination if the file is malicious or not, and a determination of malware type;
wherein the one class of objects is defined using at least one of static analysis, dynamic analysis, sample execution log analysis, and malware classification based on static and dynamic analysis; and
wherein each new feature set is a combination of the feature set from a selected feature set related to a first known malware sample and a result of substitution of at least one feature from the selected feature set related to the first known malware sample with at least one feature from the selected feature set related to a second known malware sample.
12. The method of claim 11 , wherein the substitution of at least one feature is performed for features from the same group.
13. The method of claim 11 , wherein the step of synthesizing new feature sets further comprises filtering out features corresponding to known clean object samples.