System, method, and computer program product for preventing image-related data loss
View Patent ↗A system, method, and computer program product are provided for preventing data loss associated with an image. In use, an image is identified, and it is determined whether the image includes predetermined data. In addition, an action is performed based on the determination, for preventing data loss.
1. At least one non-transitory computer readable medium having instructions stored thereon, the instructions when executed on a machine cause the machine to:
identify an image included within a communication;
extract textual data from the image;
determine whether the image includes predetermined data by comparing a representation of a portion of the textual data with the predetermined data, wherein the predetermined data includes data determined to be associated with confidential information, and wherein the image is determined to include the predetermined data if a number of predetermined keywords within the portion of the textual data matches a predefined threshold of predetermined keywords within the predetermined data known to be indicative of confidential data; and
perform an action based on the determination, wherein the action includes preventing a subsequent communication of the image based on determining that the image includes the predetermined data; wherein the predefined threshold of predetermined keywords is equal to or greater than two.
2. The non-transitory computer readable medium of claim 1 , wherein the action further includes quarantining the image based on determining that the image includes the predetermined data.
3. The non-transitory computer readable medium of claim 1 , wherein extracting textual data from the image comprises performing an optical character recognition (OCR) procedure on the image.
4. The non-transitory computer readable medium of claim 1 , wherein extracting textual data from the image comprises performing an intelligent character recognition (ICR) procedure on the image.
5. The non-transitory computer readable medium of claim 1 , wherein the extracting of the textual data from the image is performed utilizing at least one neural network.
6. The non-transitory computer readable medium of claim 1 , wherein preventing subsequent communication of the image includes preventing a subsequent electronic mail message, which attaches the image, from propagating in a network.
7. The non-transitory computer readable medium of claim 1 , wherein the image is a screenshot.
8. The non-transitory computer readable medium of claim 1 , wherein the image is identified in response to communication of the image over a network.
9. The non-transitory computer readable medium of claim 1 , wherein the image is stored on a device.
10. The non-transitory computer readable medium of claim 1 , wherein the image is identified during a system scan.
11. The non-transitory computer readable medium of claim 1 , wherein the image is included as an attachment in an electronic mail message.
12. The non-transitory computer readable medium of claim 1 , wherein the action further includes at least one of:
notifying an administrator;
notifying a management team;
notifying a sender of the image; and
notifying a recipient of the image.
13. The non-transitory computer readable medium of claim 1 , wherein the representation of the portion of the textual data is generated by fingerprinting at least a portion of the textual data extracted from the image.
14. The non-transitory computer readable medium of claim 13 , wherein fingerprinting the portion of the textual data includes hashing of the at least a portion of the textual data.
15. The non-transitory computer readable medium of claim 13 , wherein the image is determined to include the predetermined data, if the fingerprinted textual data matches the predetermined data.
16. The non-transitory computer readable medium of claim 1 , wherein the identifying, determining, and performing are performed at one or more of a gateway, a mail server, a web server, and a file transfer protocol server.
17. The non-transitory computer readable medium of claim 1 , further comprising allowing communication of the image, if it is determined that the image does not include the predetermined data.
18. A computer-implemented method, comprising:
identifying an image included within a communication;
extracting textual data from the image;
determining whether the image includes predetermined data by comparing a representation of a portion of the textual data with the predetermined data, wherein the predetermined data includes data determined to be associated with confidential information, and wherein the image is determined to include the predetermined data if a number of predetermined keywords within the portion of the textual data matches a predefined threshold of predetermined keywords within the predetermined data known to be indicative of confidential data; and
performing an action based on the determination, wherein the action includes preventing a subsequent communication of the image based on determining that the image includes the predetermined data; wherein the predefined threshold of predetermined keywords is equal to or greater than two.
19. A system, comprising:
a processor, wherein the system is configured for:
identifying an image included within a communication;
extracting textual data from the image;
determining whether the image includes predetermined data by comparing a representation of a portion of the textual data with the predetermined data, wherein the predetermined data includes data determined to be associated with confidential information, and wherein the image is determined to include the predetermined data if a number of predetermined keywords within the portion of the textual data matches a predefined threshold of predetermined keywords within the predetermined data known to be indicative of confidential data; and
performing an action based on the determination, wherein the action includes preventing a subsequent communication of the image based on determining that the image includes the predetermined data; wherein the predefined threshold of predetermined keywords is equal to or greater than two.
20. The system of claim 16 , further comprising memory coupled to the processor via a bus.