Deep learning for malicious URL classification (URLC) with the innocent until proven guilty (IUPG) learning framework
Techniques for providing deep learning for malicious URL classification (URLC) using the innocent until proven guilty (IUPG) learning framework are disclosed. In some embodiments, a system, process, and/or computer program product includes storing a set comprising one or more innocent until proven guilty (IUPG) models for static analysis of a sample; performing a static analysis of one or more URLs associated with the sample, wherein performing the static analysis includes using at least one stored IUPG model; and determining that the sample is malicious based at least in part on the static analysis of the one or more URLs associated with the sample, and in response to determining that the sample is malicious, performing an action based on a security policy.
1. A system, comprising:
a processor configured to:
store on a networked device a set comprising one or more innocent until proven guilty (IUPG) models for static analysis of a sample, wherein the one or more stored IUPG model is generated by:
receiving training data for training an IUPG model used to classify malicious content and benign content, wherein the training data includes a set of input files;
extracting a set of tokens from the set of input files to generate a character encoding and a token encoding;
generating an IUPG convolutional neural network (CNN) feature extractor based on the character encoding and the token encoding; and
combining the IUPG CNN feature extractor with another CNN-based feature extractor to generate the IUPG model;
perform a static analysis of one or more uniform resource locators (URLs) associated with the sample, wherein performing the static analysis of the one or more URLs associated with the sample includes using at least one stored IUPG model; and
determine that the sample is malicious based at least in part on the static analysis of the one or more URLs associated with the sample, and in response to determining that the sample is malicious, perform an action based on a security policy; and
a memory coupled to the processor and configured to provide the processor with instructions.
2. The system of claim 1 , wherein the processor is configured to preprocess the one or more URLs associated with the sample.
3. The system of claim 1 , wherein the processor is configured to enumerate the one or more URLs associated with the sample into a set of characters.
4. The system of claim 1 , wherein the processor is configured to enumerate the one or more URLs associated with the sample into a set of characters and a set of tokens.
5. The system of claim 1 , wherein the processor is further configured to perform token encoding that includes at least three channels.
6. The system of claim 1 , wherein the processor is further configured to receive at least one updated IUPG for URLC model.
7. The system of claim 6 , wherein the processor is further configured to perform the static analysis of the sample using the IUPG for URLC model and another type of CNN-based classifier.
8. A method, comprising:
storing on a networked device a set comprising one or more innocent until proven guilty (IUPG) models for static analysis of a sample, wherein the one or more stored IUPG model is generated by:
receiving training data for training an IUPG model used to classify malicious content and benign content, wherein the training data includes a set of input files;
extracting a set of tokens from the set of input files to generate a character encoding and a token encoding;
generating an IUPG convolutional neural network (CNN) feature extractor based on the character encoding and the token encoding; and
combining the IUPG CNN feature extractor with another CNN-based feature extractor to generate the IUPG model;
performing a static analysis of one or more uniform resource locators (URLs) associated with the sample, wherein performing the static analysis of the one or more URLs associated with the sample includes using at least one stored IUPG model; and
determining that the sample is malicious based at least in part on the static analysis of the one or more URLs associated with the sample, and in response to determining that the sample is malicious, performing an action based on a security policy.
9. The method of claim 8 , further comprising:
preprocessing the one or more URLs associated with the sample.
10. The method of claim 8 , further comprising:
enumerating the one or more URLs associated with the sample into a set of characters.
11. The method of claim 8 , further comprising:
enumerating the one or more URLs associated with the sample into a set of characters and a set of tokens.
12. The method of claim 8 , further comprising:
performing token encoding that includes at least three channels.
13. The method of claim 8 , further comprising:
receiving at least one updated IUPG for URLC model.
14. The method of claim 13 , further comprising:
performing the static analysis of the sample using the IUPG for URLC model and another type of CNN-based classifier.
15. A computer program product embodied in a tangible non-transitory computer readable storage medium and comprising computer instructions for:
storing on a networked device a set comprising one or more innocent until proven guilty (IUPG) models for static analysis of a sample, wherein the one or more stored IUPG model is generated by:
receiving training data for training an IUPG model used to classify malicious content and benign content, wherein the training data includes a set of input files;
extracting a set of tokens from the set of input files to generate a character encoding and a token encoding;
generating an IUPG convolutional neural network (CNN) feature extractor based on the character encoding and the token encoding; and
combining the IUPG CNN feature extractor with another CNN-based feature extractor to generate the IUPG model;
performing a static analysis of one or more uniform resource locators (URLs) associated with the sample, wherein performing the static analysis of the sample includes using at least one stored IUPG model; and
determining that the sample is malicious based at least in part on the static analysis of the one or more URLs associated with the one or more URLs associated with the sample, and in response to determining that the sample is malicious, performing an action based on a security policy.
16. The computer program product recited in claim 15 , further comprising computer instructions for:
preprocessing the one or more URLs associated with the sample.
17. The computer program product recited in claim 15 , further comprising computer instructions for:
enumerating the one or more URLs associated with the sample into a set of characters.
18. The computer program product recited in claim 15 , further comprising computer instructions for:
enumerating the one or more URLs associated with the sample into a set of characters and a set of tokens.
19. The computer program product recited in claim 15 , further comprising computer instructions for:
performing token encoding that includes at least three channels.
20. The computer program product recited in claim 15 , further comprising computer instructions for:
receiving at least one updated IUPG for URLC model.