Delivery of an electronic message using a machine learning policy

1. A method performed by a classification scanner, the method comprising:

receiving an electronic message from a user;

determining whether the electronic message includes an express indication from the user indicating that a classification applies to the electronic message; and

in response to determining that the electronic message does not include the express indication that the classification applies to the electronic message, sending the electronic message to a machine learning scanner, the machine learning scanner adapted to identify a machine learning policy based upon preferences of the user as to which characteristics of the electronic message should cause the electronic message to be handled in a particular way; and

in response to identifying the machine learning policy, using the machine learning policy to determine whether the classification applies to the electronic message,

wherein sending the electronic message to the machine learning scanner is further in response to determining that at least a threshold number of electronic messages have been provided to a machine learning trainer adapted to determine the machine learning policy used by the machine learning scanner.

2. The method of claim 1 , wherein the machine learning scanner is adapted to send the electronic message to an enforcer adapted to apply the classification if the classification applies to the electronic message and to bypass the enforcer if the classification does not apply to the electronic message.

3. The method of claim 1 , further comprising:

receiving a second electronic message;

determining whether the second electronic message includes an express indication from the user indicating that a classification applies to the second electronic message; and

in response to determining that the second electronic message includes the express indication that the classification applies to the second electronic message, sending the second electronic message to an enforcer adapted to apply the classification.

4. The method of claim 1 , further comprising, in response to determining that one or more characteristics associated with a second user match one or more characteristics associated with the user, instructing the machine learning scanner to apply the machine learning policy to electronic messages associated with the second user.

5. The method of claim 1 , wherein the express indication comprises a flag configured by the user.

6. The method of claim 1 , wherein the express indication comprises a keyword that the classification scanner associates with enabling the classification.

7. The method of claim 1 , wherein the express indication comprises administrator feedback.

8. One or more non-transitory computer-readable media comprising logic that, when executed by processing circuitry, causes the processing circuitry to:

receive an electronic message from a user;

determine whether the electronic message includes an express indication from the user indicating that a classification applies to the electronic message; and

in response to determining that the electronic message does not include the express indication that the classification applies to the electronic message, send the electronic message to a machine learning scanner, the machine learning scanner adapted to identify a machine learning policy based upon preferences of the user as to which characteristics of the electronic message should cause the electronic message to be handled in a particular way; and

in response to identifying the machine learning policy, using the machine learning policy to determine whether the classification applies to the electronic message,

wherein sending the electronic message to the machine learning scanner is further in response to determining that at least a threshold number of electronic messages have been provided to a machine learning trainer adapted to determine the machine learning policy used by the machine learning scanner.

9. The non-transitory computer-readable media of claim 8 , wherein the machine learning scanner is adapted to send the electronic message to an enforcer adapted to apply the classification if the classification applies to the electronic message and to bypass the enforcer if the classification does not apply to the electronic message.

10. The non-transitory computer-readable media of claim 8 , the processing circuitry further operable to:

receive a second electronic message; determine whether the second electronic message includes an express indication from the user indicating that a classification applies to the second electronic message; and

in response to determining that the second electronic message includes the express indication that the classification applies to the second electronic message, send the second electronic message to an enforcer adapted to apply the classification.

11. The non-transitory computer-readable media of claim 8 , the logic further operable to, in response to determining that one or more characteristics associated with a second user match one or more characteristics associated with the user, instruct the machine learning scanner to apply the machine learning policy to electronic messages associated with the second user.

12. The non-transitory computer-readable media of claim 8 , wherein the express indication comprises at least one of: a flag configured by the user, a keyword that the classification scanner associates with enabling the classification, or administrator feedback.

13. An apparatus, comprising:

one or more interfaces; and

processing circuitry operable to:

receive an electronic message;

determine whether the electronic message includes an express indication from a user indicating that a classification applies to the electronic message; and

in response to determining that the electronic message does not include the express indication that the classification applies to the electronic message, send the electronic message to a machine learning scanner via the one or more interfaces, the machine learning scanner adapted to identify a machine learning policy based upon preferences of the user as to which characteristics of the electronic message should cause the electronic message to be handled in a particular way; and

in response to identifying the machine learning policy, using the machine learning policy to determine whether the classification applies to the electronic message,

wherein the electronic message is sent to the machine learning scanner further in response to determining that at least a threshold number of electronic messages have been provided to a machine learning trainer adapted to determine the machine learning policy used by the machine learning scanner.

14. The apparatus of claim 13 , wherein the machine learning scanner is adapted to send the electronic message to an enforcer adapted to apply the classification if the classification applies to the electronic message and to bypass the enforcer if the classification does not apply to the electronic message.

15. The apparatus of claim 13 , the processing circuitry further operable to:

receive a second electronic message;

determine whether the second electronic message includes an express indication from the user indicating that a classification applies to the second electronic message; and

in response to determining that the second electronic message includes the express indication that the classification applies to the second electronic message, send the second electronic message to an enforcer adapted to apply the classification.

16. The apparatus of claim 13 , the processing circuitry further operable to, in response to determining that one or more characteristics associated with a second user match one or more characteristics associated with the user, instruct the machine learning scanner to apply the machine learning policy to electronic messages associated with the second user.

17. The apparatus of claim 13 , wherein the express indication comprises at least one of: a flag configured by the user, a keyword that the classification scanner associates with enabling the classification, or administrator feedback.