Grayware analysis
Methods and systems for grayware analysis include running a software application in a sandbox. Activity information is collected from the software application that represents actions performed by the software application within an environment of the sandbox. The collected activity information is matched to a grayware activity description to identify the software application as performing a grayware activity. A corrective action is performed on the software application.
1 . A computer-implemented method for grayware analysis, comprising:
mapping a set of grayware activity descriptions to grayware categories using linguistic vector analysis;
running a software application in a sandbox;
collecting activity information from the software application that represents actions performed by the software application within an environment of the sandbox;
matching the collected activity information to a grayware activity description to identify the software application as performing a grayware activity; and
performing a corrective action on the software application that is tailored to the grayware activity, to limit an impact of the grayware activity without stopping the software application from running otherwise.
2 . The method of claim 1 , wherein mapping includes forming a document-term matrix from the set of grayware activity descriptions, with rows of the document-term matrix representing respective grayware activity descriptions and with columns of the document-term matrix representing individual terms.
3 . The method of claim 2 , wherein a category is selected based on the similarity score to determine information about the grayware activity.
4 . The method of claim 1 , wherein mapping includes determining a similarity score between a vector representing a grayware activity description and a vector representing a category of grayware behavior.
5 . The method of claim 1 , further comprising downloading the software application from a remote app store prior to running.
6 . The method of claim 5 , wherein performing the corrective action includes disabling access to the software application on the remote app store.
7 . The method of claim 1 , wherein collecting activity information includes monitoring system event logs, network activities, file operations, registry operations, notification activities, and peripheral accesses, and further includes taking periodic screenshots.
8 . The method of claim 1 , wherein matching the collected activity information to a grayware activity description includes comparing the collected activity information to behaviors in an ontology that has descriptions for a plurality of different grayware behavior types to identify a relevant grayware behavior.
9 . A computer program product for grayware analysis, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a hardware processor to cause the hardware processor to:
run a software application in a sandbox;
collect activity information from the software application that represents actions performed by the software application within an environment of the sandbox;
match the collected activity information to a grayware activity description to identify the software application as performing a grayware activity; and
perform a corrective action on the software application that is tailored to the grayware activity, to limit an impact of the grayware activity without stopping the software application from running otherwise.
10 . A system for grayware analysis, comprising:
a hardware processor; and
a memory that stores a computer program which, when executed by the hardware processor, causes the hardware processor to:
wherein the computer program further causes the hardware processor to map a set of grayware activity descriptions to grayware categories using linguistic vector analysis;
ran a software application in a sandbox;
collect activity information from the software, application that represents actions performed by the software application within an environment of the sandbox;
match the collected activity information to a grayware activity description te identify the software application as performing a grayware activity; and
perform a corrective action on the software application that is tailored ta the grayware activity, to limit an impact of the grayware activity without stopping the software application from running otherwise.
11 . The system of claim 10 , wherein the computer program further causes the hardware processor to form a document-term matrix from the set of grayware activity descriptions, with rows of the document-term matrix representing respective gray ware activity descriptions and with columns of the document-term matrix representing individual terms.
12 . The system of claim 11 , wherein a category is selected based on the similarity score to determine information about the grayware activity.
13 . The system of claim 10 , wherein the computer program further causes the hardware processor to determine a similarity score between a vector representing a gray ware activity description and a vector representing a category of grayware behavior.
14 . The system of claim 10 , wherein the computer program further causes the hardware processor to download the software application from a remote app store prior to running.
15 . The system of claim 14 , wherein the computer program further causes the hardware processor to disable access to the software application on the remote app store.
16 . The system of claim 10 , wherein the computer program further causes the hardware processor to monitor system event logs, network activities, file operations, registry operations, notification activities, and peripheral accesses, and further includes taking periodic screenshots.