Delivery of an electronic message using a machine learning policy

1. A method, comprising:

receiving a first electronic message without an express indication of a sender that a classification applies to the electronic message;

determining that the classification applies to the first electronic message by applying a classification scanner to the first electronic message, wherein the classification scanner utilizes a machine learning scanner including a machine learning policy trained based on a set of electronic messages, each of the set of electronic messages including the express indication from an associated user that the classification applies to that electronic message, and wherein the classification scanner provides an identifier associated with the received first email message to the machine learning scanner and the machine learning scanner selects the machine learning policy based on the identifier; and

taking an action for the first electronic message associated with the classification.

2. The method of claim 1 , wherein the machine leaning policy was provided from a remote email gateway.

3. The method of claim 2 , wherein the set of electronic messages are electronic messages processed by the remote email gateway and the machine learning policy was trained at the remote email gateway.

4. The method of claim 1 , wherein the classification includes an encryption, quarantine, archive or brand classification.

5. The method of claim 1 , wherein the identifier is associated with the sender or a group associated with the sender.

6. The method of claim 1 , further comprising:

receiving a second electronic message with the express indication of the sender that the classification applies to the electronic message;

bypassing the classification scanner; and

taking the action for the second electronic message associated with the classification.

7. An electronic message delivery system, comprising:

a processor; and

a non-transitory computer readable medium, comprising instructions for:

receiving a first electronic message without an express indication of a sender that a classification applies to the electronic message;

determining that the classification applies to the first electronic message by applying a classification scanner to the first electronic message, wherein the classification scanner utilizes a machine learning scanner including a machine learning policy trained based on a set of electronic messages, each of the set of electronic messages including the express indication from an associated user that the classification applies to that electronic message, and wherein the classification scanner provides an identifier associated with the received first email message to the machine learning scanner and the machine learning scanner selects the machine learning policy based on the identifier; and

taking an action for the first electronic message associated with the classification.

8. The electronic message delivery system of claim 7 , wherein the machine leaning policy was provided from a remote email gateway.

9. The electronic message delivery system of claim 8 , wherein the set of electronic messages are electronic messages processed by the remote email gateway and the machine learning policy was trained at the remote email gateway.

10. The electronic message delivery system of claim 7 , wherein the classification includes an encryption, quarantine, archive or brand classification.

11. The electronic message delivery system of claim 7 , wherein the identifier is associated with the sender or a group associated with the sender.

12. The electronic message delivery system of claim 7 , wherein the instructions are further for:

receiving a second electronic message with the express indication of the sender that the classification applies to the electronic message;

bypassing the classification scanner; and

taking the action for the second electronic message associated with the classification.

13. A non-transitory computer readable medium, comprising instructions for:

receiving a first electronic message without an express indication of a sender that a classification applies to the electronic message;

determining that the classification applies to the first electronic message by applying a classification scanner to the first electronic message, wherein the classification scanner utilizes a machine learning scanner including a machine learning policy trained based on a set of electronic messages, each of the set of electronic messages including the express indication from an associated user that the classification applies to that electronic message, and wherein the classification scanner provides an identifier associated with the received first email message to the machine learning scanner and the machine learning scanner selects the machine learning policy based on the identifier; and

taking an action for the first electronic message associated with the classification.

14. The non-transitory computer readable medium of claim 13 , wherein the machine leaning policy was provided from a remote email gateway.

15. The non-transitory computer readable medium of claim 14 , wherein the set of electronic messages are electronic messages processed by the remote email gateway and the machine learning policy was trained at the remote email gateway.

16. The non-transitory computer readable medium of claim 13 , wherein the classification includes an encryption, quarantine, archive or brand classification.

17. The non-transitory computer readable medium of claim 13 , wherein the identifier is associated with the sender or a group associated with the sender.

18. The non-transitory computer readable medium of claim 13 , wherein the instructions are further for:

receiving a second electronic message with the express indication of the sender that the classification applies to the electronic message;

bypassing the classification scanner; and

taking the action for the second electronic message associated with the classification.