Method and product for providing a predictive security product and evaluating existing security products
A method, product and computer program product for building a malware detector, the method including the steps of: receiving at least one characteristic for each of a plurality of malware variants; categorizing each of the characteristics as a malicious characteristic or a non-malicious characteristic; generating a detector; training the detector to distinguish between the malicious characteristic and the non-malicious characteristic; and rating the detector based on an accuracy of detection of an amount of malicious characteristics for each malware variant.
1. A detector builder system, comprising:
a non-transitory memory storing at least one characteristic for each of a plurality of malware variants; and
one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:
categorizing each of the characteristics as a malicious characteristic or a non-malicious characteristic;
generating a detector that includes a set of symbols;
training the detector to distinguish between the malicious characteristic and the non-malicious characteristic;
determining a rating of the detector based on a length of the set of symbols and an accuracy of detection of an amount of malicious characteristics for each malware variant: and based on the rating, selecting the detector for mutation.
2. The system of claim 1 , wherein the detector includes at least one of an expression, a grammar, and or a rule.
3. The system of claim 1 , wherein the es set of symbols are matched to a trace to detect the malicious characteristic.
4. The system of claim 3 , wherein the trace includes at least one of network traffic data, code, one or more operating system calls, one or more application programming interface (API) calls, central processing unit (CPU) activity data, or a memory footprint.
5. The system of claim 1 , wherein the detector is rated based on the amount of malicious characteristics that are detected, an amount of non-malicious characteristics that are incorrectly detected as malicious characteristics, and a shortness of length of the detector.
6. The system of claim 1 , wherein the operations further comprise: scoring and selecting a mutation of the detector for further mutation.
7. The system of claim 1 , wherein training the detector comprises at least one of syntax learning and or grammar induction.
8. A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising:
receiving at least one characteristic for each of a plurality of malware variants; categorizing each of the characteristics as a malicious characteristic or a non-malicious characteristic;
generating a detector that includes a set of symbols;
training the detector to distinguish between the malicious characteristic and the non-malicious characteristic;
determining a rating of the detector based on a length of the set of symbols and an accuracy of detection of an amount of malicious characteristics for each malware variant; and based on the rating, selecting the detector for mutation.
9. The non-transitory machine-readable medium of claim 8 , wherein the set of symbols are matched to a trace to detect the malicious characteristic.
10. The non-transitory machine-readable medium of claim 9 , wherein the trace includes at least one of network traffic data, code, one or more operating system calls, one or more application programming interface (API) calls, central processing unit (CPU) activity data, or a memory footprint.
11. The non-transitory machine-readable medium of claim 8 , wherein the detector is rated based on the amount of malicious characteristics that are detected, an amount of non-malicious characteristics that are incorrectly detected as malicious characteristics, and a shortness of length of the detector.
12. The non-transitory machine-readable medium of claim 8 , wherein the operations further comprise:
based scoring and selecting a mutation of the detector for further mutation.
13. The non-transitory machine-readable medium of claim 8 , wherein training the detector includes at least one of syntax learning or grammar induction.
14. A method for building a malware detector comprising: receiving at least one characteristic for each of a plurality of malware variants; categorizing each of the characteristics as a malicious characteristic or a non-malicious characteristic;
generating a detector that includes a set of symbols;
training the detector to distinguish between the malicious characteristic and the non-malicious characteristic;
determining a rating of the detector based on a length of the set of symbols and an accuracy of detection of an amount of malicious characteristics for each malware variant: and based on the rating, selecting the detector for mutation.
15. The method of claim 14 , wherein the detector includes at least one of an expression, a grammar, or a rule.
16. The method of claim 14 , wherein the set of symbols are matched to a trace to detect the malicious characteristic.
17. The method of claim 16 , wherein the trace includes at least one of network traffic data, code, one or more operating system calls, one or more application programming interface (API) calls, central processing unit (CPU) activity data, or a memory footprint.
18. The method of claim 14 , wherein the detector is rated based on the amount of malicious characteristics that are detected, an amount of non-malicious characteristics that are incorrectly detected as malicious characteristics, and a shortness of length of the detector.
19. The method of claim 14 , further comprising:
scoring and selecting a mutation of the detector for further mutation.
20. The method of claim 14 , wherein training the detector includes at least one of syntax learning or grammar induction.