Systems and methods for monitoring malicious software engaging in online advertising fraud or other form of deceit
Systems and methods for monitoring malicious software engaging in online advertising fraud or other form of deceit are disclosed herein. An example method for automated categorization of binary code for identifying malicious software engaging in online advertising fraud disclosed herein includes collecting data defining behavior of the binary code using sensors from a plurality of sandboxes, categorizing the binary code using a behavior signature, the behavior signature including a selector and a filter, the behavior signature defining a signature category based on actions associated with the binary code, wherein a match with the filter removes the binary code from the signature category, and wherein a match with the selector adds the binary code to the signature category, identifying the binary code as malicious software engaging in online advertising targeted behavior based on the signature category, and mimicking a communication associated with the binary code to identify a control server associated the binary code in response to identifying the binary code as malicious software.
1. A method for automated categorization of binary code for identifying malicious software engaging in online advertising fraud, the method comprising:
collecting via an instruction executed by a processor, data defining behavior of the binary code using sensors from a plurality of sandboxes, the binary code accessing a first server providing advertising services;
categorizing, via an instruction executed by the processor, the binary code using a behavior signature, the behavior signature including a selector and a filter, the behavior signature defining a signature category based on actions associated with the binary code, wherein a first match with the filter removes the binary code from the signature category, and wherein a second match with the selector adds the binary code to the signature category;
tuning, via an instruction executed by the processor, the selector and the filter based on information provided by an automated review of the categorized binary code, the automated review including a feedback loop to tune the selector and the filter over a period of time;
identifying, via an instruction executed by the processor, the binary code as malicious software engaging in online advertising targeted behavior based on the signature category;
identifying a control server associated the binary code in response to identifying the binary code as malicious software; and
in response to identifying the control server, initiating, by executing an instruction for the processor, monitoring of the control server by mimicking a communication associated with the binary code.
2. The method of claim 1 , wherein the plurality of sandboxes is controlled by a management controller configured to operate at least two of the plurality of sandboxes in parallel.
3. The method of claim 1 , wherein the sensors include at least one of keystroke loggers, instruction loggers, interaction loggers, interface loggers, access loggers, file system loggers, web query loggers, network traffic loggers, registry loggers, or code execution loggers.
4. The method of claim 3 , wherein the sensors are configured to sense at least one of: programmatic calls to one or more operating system kernel interfaces, names of files created, deleted, or accessed, registry keys created, deleted, or accessed, mutex creation, network traffic information, domain name service requests, web query events, or HTTP traffic.
5. The method of claim 1 , wherein the actions associated with the binary code include at least one of: writing strings to memory, generating network traffic, conducting API calls related to network protocols, or conducting API calls related to cryptography.
6. The method of claim 1 , wherein the behavior signature includes at least one of: writing strings to memory, altering or creating of registry keys and/or configuration files for a web browser, invoking an API call to suppress audio or visual messaging, invoking an API call associated with creation and control of an instance of a web browser, invoking an API call that hides one or more windows when created, or invoking an API call that can be used to create at least one of multiple desktops and mobile screens.
7. The method of claim 1 , wherein the behavior signature includes at least one behavior signature related to malware, said at least one behavior signature related to malware including at least one of writing strings to memory, altering or creating of registry keys or configuration files for web browsers other than Internet Explorer, or invoking one or more API calls associated with installation of a web browser plugin or extension.
8. The method of claim 1 , further including:
polling, via an instruction executed by the processor, binary sample feeds to download additional binary code for execution by at least one of the plurality of sandboxes; and
observing, via an instruction executed by the processor, the behavior of the binary code using the sensors.
9. The method of claim 8 , wherein the binary sample feeds include malware submissions to third party servers.
10. A non-transitory computer readable medium comprising instructions, which when executed, cause a processor to at least:
collect data defining behavior of binary code using sensors from a plurality of sandboxes, the binary code accessing a first server providing advertising services;
categorize the binary code using a behavior signature, the behavior signature including a selector and a filter, the behavior signature defining a signature category based on actions associated with the binary code, wherein a first match with the filter removes the binary code from the signature category, and wherein a second match with the selector adds the binary code to the signature category;
tune the selector and the filter based on information provided by an automated review of the categorized binary code, the automated review including a feedback loop to tune the selector and the filter over a period of time;
identify the binary code as malicious software engaging in online advertising targeted behavior based on the signature category;
identify a control server associated the binary code in response to identifying the binary code as malicious software; and
in response to identifying the control server, initiate monitoring of the control server by mimicking a communication associated with the binary code.
11. The non-transitory computer readable medium of claim 10 , wherein the behavior signature includes at least one of: writing strings to memory, altering or creating of registry keys and/or configuration files for a web browser, invoking an API call to suppress audio or visual messaging, invoking an API call associated with creation and control of an instance of a web browser, invoking an API call that hides one or more windows when created, or invoking an API call that can be used to create at least one of multiple desktops and mobile screens.
12. The non-transitory computer readable medium of claim 10 , wherein the instructions, when executed, further cause the processor to:
poll binary sample feeds to download additional binary code for execution by at least one of the plurality of sandboxes; and
observe the behavior of the binary code using the sensors.
13. The non-transitory computer readable medium of claim 10 , wherein the plurality of sandboxes is controlled by a management controller configured to operate at least two of the plurality of sandboxes in parallel.
14. An apparatus comprising:
memory including instructions; and
a processor to execute the instructions to:
collect data defining behavior of binary code using sensors from a plurality of sandboxes, the binary code accessing a first server providing advertising services;
categorize the binary code using a behavior signature, the behavior signature including a selector and a filter, the behavior signature defining a signature category based on actions associated with the binary code, wherein a first match with the filter removes the binary code from the signature category, and wherein a second match with the selector adds the binary code to the signature category;
tune the selector and the filter based on information provided by an automated review of the categorized binary code, the automated review including a feedback loop to tune the selector and the filter over a period of time;
identify the binary code as malicious software engaging in online advertising targeted behavior based on the signature category;
identify a control server associated the binary code in response to identifying the binary code as malicious software; and
in response to identifying the control server, initiate monitoring of the control server by mimicking a communication associated with the binary code.
15. The apparatus of claim 14 , wherein the behavior signature includes at least one of: writing strings to memory, altering or creating of registry keys and/or configuration files for a web browser, invoking an API call to suppress audio or visual messaging, invoking an API call associated with creation and control of an instance of a web browser, invoking an API call that hides one or more windows when created, or invoking an API call that can be used to create at least one of multiple desktops and mobile screens.
16. The apparatus of claim 14 , wherein the instructions, when executed, further cause the processor to:
poll binary sample feeds to download additional binary code for execution by at least one of the plurality of sandboxes; and
observe the behavior of the binary code using the sensors.
17. The apparatus of claim 14 , wherein the plurality of sandboxes is controlled by a management controller configured to operate at least two of the plurality of sandboxes in parallel.