Detection and prevention of external fraud
Techniques for detecting instances of external fraud by monitoring digital activities that are performed with accounts associated with an enterprise are disclosed. In one example, a threat detection platform determines the likelihood that an incoming email is indicative of external fraud based on the context and content of the incoming email. To understand the risk posed by an incoming email, the threat detection platform may seek to determine not only whether the sender normally communicates with the recipient, but also whether the topic is one normally discussed by the sender and recipient. In this way, the threat detection platform can establish whether the incoming email deviates from past emails exchanged between the sender and recipient.
1. A system, comprising:
a processor configured to:
obtain an email that is addressed to a first email account associated with a first enterprise;
establish, at least in part by examining content of the email, that the email was sent by a second email account associated with a vendor;
access a database to identify a digital profile associated with the vendor, wherein the digital profile includes a record of a set of past emails sent by the second email account, wherein the digital profile is a first digital profile included in a set of digital profiles collectively associated with a plurality of vendors, and wherein at least one email included in the set of past emails is addressed to an email account associated with a second enterprise that is different from the first enterprise; and
determine, based on the digital profile, whether the email differs from the set of past emails in terms of context and/or content to such a degree that compromise of the second email account is likely, wherein the determining includes examining whether the first email account was a recipient of any of the set of past emails; and
a memory coupled to the processor and configured to provide the processor with instructions.
2. The system of claim 1 , wherein said determining comprises examining whether the first email account was the recipient of any of the set of past emails, and examining whether a topic of the email was discussed in any of the set of past emails.
3. The system of claim 1 , wherein the email is representative of a request for payment of an invoice by the first enterprise.
4. The system of claim 3 , wherein determining whether the email differs to the degree includes determining whether a mechanism for referencing the invoice has changed.
5. The system of claim 1 , wherein the email is representative of a request to alter payment information used to process payments to the vendor.
6. The system of claim 1 , wherein said establishing comprises applying a model to the email that examines (i) a subject, (ii) a body, and (iii) any attachments to a source of the email.
7. The system of claim 1 , wherein the digital profile further includes a classification indicative of risk in communicating with the vendor.
8. The system of claim 1 , wherein determining whether the email differs to the degree includes determining whether a sender domain has changed.
9. The system of claim 1 , wherein determining whether the email differs to the degree includes determining whether a sender address has changed.
10. The system of claim 1 , wherein determining whether the email differs to the degree includes determining whether a geographical location of a sender has changed.
11. The system of claim 1 , wherein determining whether the email differs to the degree includes determining whether a formatting characteristic has changed.
12. A method, comprising:
obtaining an email that is addressed to a first email account associated with a first enterprise;
establishing, at least in part by examining content of the email, that the email was sent by a second email account associated with a vendor;
accessing a database to identify a digital profile associated with the vendor, wherein the digital profile includes a record of a set of past emails sent by the second email account, wherein the digital profile is a first digital profile included in a set of digital profiles collectively associated with a plurality of vendors, and wherein at least one email included in the set of past emails is addressed to an email account associated with a second enterprise that is different from the first enterprise; and
determining, based on the digital profile, whether the email differs from the set of past emails in terms of context and/or content to such a degree that compromise of the second email account is likely, wherein the determining includes examining whether the first email account was a recipient of any of the set of past emails.
13. The method of claim 12 , wherein said determining comprises examining whether the first email account was the recipient of any of the set of past emails, and examining whether a topic of the email was discussed in any of the set of past emails.
14. The method of claim 12 , wherein the email is representative of a request for payment of an invoice by the first enterprise.
15. The method of claim 12 , wherein the email is representative of a request to alter payment information used to process payments to the vendor.
16. The method of claim 12 , wherein said establishing comprises applying a model to the email that examines (i) a subject, (ii) a body, and (iii) any attachments to a source of the email.
17. The method of claim 12 , wherein the digital profile further includes a classification indicative of risk in communicating with the vendor.
18. The method of claim 12 , wherein determining whether the email differs to the degree includes determining whether a sender domain has changed.
19. The method of claim 12 , wherein determining whether the email differs to the degree includes determining whether a sender address has changed.
20. The method of claim 14 , wherein determining whether the email differs to the degree includes determining whether a mechanism for referencing the invoice has changed.
21. The method of claim 12 , wherein determining whether the email differs to the degree includes determining whether a geographical location of a sender has changed.
22. The method of claim 12 , wherein determining whether the email differs to the degree includes determining whether a formatting characteristic has changed.