Techniques for detecting malicious behavior using an accomplice model
The present disclosure generally relates to web page analysis, and more particularly to detecting malicious behavior using an accomplice model. In certain embodiments, the accomplice model may determine that a URI is associated with malicious behavior based upon the URI being associated with an attribute determined to be related to malicious behavior. Examples of an attribute include a host system, a domain, or an element of a document used to render the web page. Examples of an element of a document used to render the web page may include an active/dynamic element (e.g., a function, a script, etc.) or an inactive/static element (e.g., a string, a number, a frame, a tracking username, a social networking username, etc.).
1. A method, executed on a computing device, comprising:
creating a list of Uniform Resource Identifiers (URIs) used to render a web page;
comparing each URI in the URI list to an accomplice list, the accomplice list is comprised of a plurality of URIs determined to be associated with malicious content or behavior along with an associated reputation score for each URI in the plurality of URIs;
upon identifying that a particular URI in the URI list is also in the accomplice list and that a reputation score associated with the particular URI exceeds a threshold value:
creating a blacklist incident for the particular URI; and
outputting that the particular URI is associated with malicious behavior;
identifying an attribute that recurs in at least one URI in different sequences of blacklist incidents;
generating a score for the attribute based upon a number of times the attribute recurs; and
based on the score, determining that the attribute is associated with malicious behavior.
2. The method of claim 1 , wherein a statistical model is used to assign a reputation score to each URI in the accomplice list.
3. The method of claim 1 , wherein outputting that the particular URI is associated with malicious behavior includes informing a user that the URI is malicious.
4. The method of claim 1 , wherein outputting that the particular URI is associated with malicious behavior includes sending the URI to a system that removes code that causes the URI to be called.
5. The method of claim 1 , further comprising:
identifying indirect connections from one-time-use hosts to a malicious web page using the accomplice list.
6. The method of claim 1 , wherein the accomplice list is segmented based on profiles of blacklist incidents.
7. The method of claim 1 , further comprising:
identifying a social media username that is malicious by identifying URIs in one or more sequences of blacklist incidents that are associated with the social media username.
8. The method of claim 1 , further comprising:
outputting one or more URIs associated with the attribute.
9. The method of claim 1 , further comprising:
removing the attribute from a document used to render a web page that causes one or more URIs associated with the attribute to be called.
10. One or more non-transitory computer-readable media, storing one or more sequences of instructions, wherein execution of the one or more sequences of instructions by one or more processors causes the one or more processors to perform:
creating a list of Uniform Resource Identifiers (URIs) used to render a web page;
comparing each URI in the URI list to an accomplice list, the accomplice list is comprised of a plurality of URIs determined to be associated with malicious content or behavior along with an associated reputation score for each URI in the plurality of URIs;
upon identifying that a particular URI in the URI list is also in the accomplice list and that a reputation score associated with the particular URI exceeds a threshold value:
creating a blacklist incident for the particular URI; and
outputting that the particular URI is associated with malicious behavior;
identifying an attribute that recurs in at least one URI in different sequences of blacklist incidents;
generating a score for the attribute based upon a number of times the attribute recurs; and
based on the score, determining that the attribute is associated with malicious behavior.
11. The one or more non-transitory computer-readable media of claim 10 , wherein a statistical model is used to assign a reputation score to each URI in the accomplice list.
12. The one or more non-transitory computer-readable media of claim 10 , wherein outputting that the particular URI is associated with malicious behavior includes informing a user that the URI is malicious.
13. The one or more non-transitory computer-readable media of claim 10 , wherein outputting that the particular URI is associated with malicious behavior includes sending the URI to a system that removes code that causes the URI to be called.
14. The one or more non-transitory computer-readable media of claim 10 , further comprising:
identifying indirect connections from one-time-use hosts to a malicious web page using the accomplice list.
15. The one or more non-transitory computer-readable media of claim 10 , wherein the accomplice list is segmented based on profiles of blacklist incidents.
16. The one or more non-transitory computer-readable media of claim 10 , further comprising:
identifying a social media username that is malicious by identifying URIs in one or more sequences of blacklist incidents that are associated with the social media username.
17. The one or more non-transitory computer-readable media of claim 10 , further comprising:
outputting one or more URIs associated with the attribute.
18. The one or more non-transitory computer-readable media of claim 10 , further comprising:
removing the attribute from a document used to render a web page that causes one or more URIs associated with the attribute to be called.