System and method for identifying and controlling polymorphic malware
The present system and method pertain to the detection of malicious software and processes such as malware. A cloud security policy system receives hashes and behavioral information about applications and/or processes executing on user devices. The cloud security policy system records this information and then evaluates the trustworthiness of the hashes based on the information received from the user devices to provide a security policy for the applications and/or processes. The security policy is sent from the cloud security policy system to user devices to be applied by the user devices.
1. A method for identifying polymorphic malware on user devices, the method comprising:
monitoring behaviors of one or more applications executing on one or more user devices to determine behavioral fingerprints of the one or more applications, wherein the behaviors of an application represent actions performed by the application;
determining behavioral fingerprints of known malware based on observed behaviors of the known malware, wherein the observed behaviors of the known malware represent actions performed by the known malware;
comparing the behavioral fingerprints of the one or more applications to the behavioral fingerprints of the known malware;
determining if any behavioral fingerprints of at least one of the one or more applications are similar to the behavioral fingerprints of the known malware;
applying security policies to the at least one of the one or more applications based on a similarity of the behavioral fingerprints of the at least one of the one or more applications with the behavioral fingerprints of the known malware and an age of the at least one of the one or more applications; and
calculating a trust score of the at least one of the one or more applications based on the age of the at least one of the one or more applications.
2. The method of claim 1 , further comprising identifying the one or more applications as polymorphic variations of specific instances of the known malware based on behaviors exhibited by the specific instances of the known malware and the monitored behaviors of the one or more applications.
3. The method of claim 1 , further comprising identifying polymorphic viruses based on whether the one or more applications with different file hashes than the known malware exhibit similar observed behaviors as the known malware.
4. The method of claim 1 , further comprising identifying a unique application that only occurs on a single device as a malware based on whether the unique application exhibits similar observed behaviors as the malware.
5. The method of claim 1 , wherein the polymorphic malware is a malware that mutates to change contents of files containing the malware and behavior of the malware with respect to previous versions of the malware.
6. The method of claim 1 , further comprising receiving, by a security policy system, behavioral information from the one or more user devices, the behavioral information indicating behaviors of the one or more applications executing on the one or more user devices.
7. The method of claim 6 , wherein the security policy system stores the behavioral information from the one or more user devices in a behavioral history database.
8. The method of claim 6 , wherein applying security policies to the at least one of the one or more applications comprises the security policy system updating the security policies based on the behavioral information, sending the updated security policies to the one or more user devices, and a security agent software executing on each of the one or more user devices enforcing the updated security policies.
9. The method of claim 1 , wherein the monitored behaviors include one or more of forming network connections, making system application programming interface (API) calls, accessing, creating and loading files, changing system configurations including modifying system registry values, and monitoring user inputs including turning on microphones or monitoring keystrokes of the user devices.
10. The method of claim 1 , wherein the at least one of the one or more applications executing on the one or more user devices is an unknown application.
11. A system for identifying polymorphic malware on user devices, the system comprising:
at least one processor and memory, wherein the processor is programmed to:
monitor behaviors of one or more applications executing on one or more user devices to determine behavioral fingerprints of the one or more applications, wherein the behaviors of an application represent actions performed by the application;
determine behavioral fingerprints of known malware based on observed behaviors of the known malware, wherein the observed behaviors of the known malware represent actions performed by the known malware;
compare the behavioral fingerprints of the one or more applications to the behavioral fingerprints of the known malware;
determine if any behavioral fingerprints of at least one of the one or more applications are similar to the behavioral fingerprints of the known malware;
apply security policies to the at least one of the one or more applications based on a similarity of the behavioral fingerprints of the at least one of the one or more applications with the behavioral fingerprints of the known malware and an age of the at least one of the one or more applications; and
calculate a trust score of the at least one of the one or more applications based on the age of the at least one of the one or more applications.
12. The system of claim 11 , further comprising identifying the one or more applications as polymorphic variations of specific instances of the known malware based on behaviors exhibited by the specific instances of the known malware and the monitored behaviors of the one or more applications.
13. The system of claim 11 , further comprising identifying polymorphic viruses based on whether the one or more applications with different file hashes than the known malware exhibit similar observed behaviors as the known malware.
14. The system of claim 11 , further comprising identifying a unique application that only occurs on a single device as a malware based on whether the unique application exhibits similar observed behaviors as the malware.
15. The system of claim 11 , wherein the polymorphic malware is a malware that mutates to change contents of files containing the malware and behavior of the malware with respect to previous versions of the malware.
16. The system of claim 11 , further comprising receiving, by a security policy system, behavioral information from the one or more user devices, the behavioral information indicating behaviors of the one or more applications executing on the one or more user devices.
17. The system of claim 16 , wherein the security policy system comprises a behavioral history database storing the behavioral information from the one or more user devices.
18. The system of claim 16 , wherein applying the security policies to the at least one of the one or more applications comprises the security policy system updating the security policies based on the behavioral information, sending the updated security policies to the one or more user devices, and a security agent software executing on the one or more user devices enforcing the updated security policies.
19. The system of claim 11 , wherein the monitored behaviors include one or more of forming network connections, making system application programming interface (API) calls, accessing, creating and loading files, changing system configurations including modifying system registry values, and monitoring user inputs including turning on microphones or monitoring keystrokes of the user devices.
20. The system of claim 11 , wherein the at least one of the one or more applications executing on the one or more user devices is an unknown application.
21. One or more non-transitory computer readable media storing instructions that upon execution by a computing device perform a method comprising:
monitoring behaviors of one or more applications executing on one or more user devices to determine behavioral fingerprints of the one or more applications, wherein the behaviors of an application represent actions performed by the application;
determining behavioral fingerprints of known malware based on observed behaviors of the known malware, wherein the observed behaviors of the known malware represent actions performed by the known malware;
comparing the behavioral fingerprints of the one or more applications to the behavioral fingerprints of the known malware;
determining if any behavioral fingerprints of at least one of the one or more applications are similar to the behavioral fingerprints of the known malware;
applying security policies to the at least one of the one or more applications based on a similarity of the behavioral fingerprints of the at least one of the one or more applications with the behavioral fingerprints of the known malware and an age of the at least one of the one or more applications; and
calculating a trust score of the at least one of the one or more applications based on the age of the at least one of the one or more applications.
22. The one or more non-transitory computer readable media of claim 21 , wherein the at least one of the one or more applications executing on the one or more user devices is an unknown application, wherein the security policies are applied to the unknown application based on determining whether the unknown application displayed a visible window.