Systems and methods for detecting malicious behavior in process chains

1. A method for malicious behavior detection in processing chains, the method comprising:

identifying and monitoring events generated by a first process executing on a computing device;

storing snapshots of data modified by any of the events;

determining a level of suspicion for the first process, wherein the level of suspicion is a likelihood of the first process being attributed to malware based on the data modified by any of the events;

determining whether the first process is trusted based on the determined level of suspicion;

in response to determining that the first process is not trusted, identifying at least one sub-process of the first process; and

restoring, from the snapshots, objects affected by the first process and the at least one sub-process.

2. The method of claim 1 , further comprising:

determining that the at least one sub-process is not trusted in response to determining that the first process is not trusted.

3. The method of claim 1 , wherein determining the level of suspicion comprises applying an artificial intelligence (AI) model to the snapshots of data, wherein the AI model is configured to determine the level of suspicion based on training data comprising historic events pre-classified by trustworthiness.

4. The method of claim 1 , wherein the first process and the at least one sub-process are comprised in a chain of related processes, wherein identifying the at least one sub-process further comprises:

identifying at least one process that relates to the first process in one or more of:

a parent-child relationship;

injector-injected relationship;

a software-component relationship; or

a process-thread relationship.

5. The method of claim 1 , wherein determining that the first process is not trusted comprises determining that the level of suspicion of the first process is greater than a predetermined threshold value.

6. The method of claim 5 , further comprising:

determining another level of suspicious of the at least one sub-process;

in response to determining that that another level of suspicion of the at least one sub-process is less than the predetermined threshold value:

determining that the at least one sub-process is trusted; and

isolating the at least one sub-process from the first process.

7. The method of claim 1 , further comprising:

in response to determining that the first process is trusted, deleting the snapshots and ceasing the monitoring.

8. The method of claim 1 , further comprising:

in response to determining that the first process is trusted, marking the first process as trusted; and

in response to determining that the first process is not trusted, marking the first process as untrusted.

9. The method of claim 1 , wherein the objects comprise one or more of files, records, system settings, task queues, or database records.

10. A system for malicious behavior detection in processing chains, the system comprising:

a hardware processor configured to:

identify and monitor events generated by a first process executing on a computing device;

store snapshots of data modified by any of the events;

determine a level of suspicion for the first process, wherein the level of suspicion is a likelihood of the first process being attributed to malware based on the data modified by any of the events;

determine whether the first process is trusted based on the determined level of suspicion;

in response to determining that the first process is not trusted, identify at least one sub-process of the first process; and

restore, from the snapshots, objects affected by the first process and the at least one sub-process.

11. The system of claim 10 , wherein the hardware processor is further configured to:

determine that the at least one sub-process is not trusted in response to determining that the first process is not trusted.

12. The system of claim 10 , wherein the hardware processor is further configured to determine the level of suspicion by applying an artificial intelligence (AI) model to the snapshots of data, wherein the AI model is configured to determine the level of suspicion based on training data comprising historic events pre-classified by trustworthiness.

13. The system of claim 10 , wherein the first process and the at least one sub-process are comprised in a chain of related processes, wherein the hardware processor is further configured to identify the at least one sub-process by:

identifying at least one process that relates to the first process in one or more of:

a parent-child relationship;

injector-injected relationship;

a software-component relationship; or

a process-thread relationship.

14. The system of claim 10 , wherein the hardware processor is further configured to determine that the first process is not trusted by determining that the level of suspicion of the first process is greater than a predetermined threshold value.

15. The system of claim 14 , wherein the hardware processor is further configured to:

determine another level of suspicious of the at least one sub-process;

in response to determining that that another level of suspicion of the at least one sub-process is less than the predetermined threshold value:

determine that the at least one sub-process is trusted; and

isolate the at least one sub-process from the first process.

16. The system of claim 10 , wherein the hardware processor is further configured to:

in response to determining that the first process is trusted, delete the snapshots and cease the monitoring.

17. The system of claim 10 , wherein the hardware processor is further configured to:

in response to determining that the first process is trusted, mark the first process as trusted; and

in response to determining that the first process is not trusted, mark the first process as untrusted.

18. The system of claim 10 , wherein the objects comprise one or more of files, records, system settings, task queues, or database records.

19. A non-transitory computer readable medium storing thereon computer executable instructions for malicious behavior detection in processing chains, including instructions for:

identifying and monitoring events generated by a first process executing on a computing device;

storing snapshots of data modified by any of the events;

determining a level of suspicion for the first process, wherein the level of suspicion is a likelihood of the first process being attributed to malware based on the data modified by any of the events;

determining whether the first process is trusted based on the determined level of suspicion;

in response to determining that the first process is not trusted, identifying at least one sub-process of the first process; and

restoring, from the snapshots, objects affected by the first process and the at least one sub-process.