Detection and prevention of external fraud
Introduced here are computer programs and computer-implemented techniques for detecting instances of external fraud by monitoring digital activities that are performed with accounts associated with an enterprise. A threat detection platform may determine the likelihood that an incoming email is indicative of external fraud based on the context and content of the incoming email. For example, 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 method comprising:
obtaining an email that is addressed to a first email account associated with a first enterprise;
establishing that the email represents an instance of outreach by a second email account associated with a vendor for payment of an invoice by the first enterprise;
obtaining a metric that is indicative of a risk in communicating with the second email account based at least in part on a comparison of the email to a set of emails that are representative of past instances of outreach by the second email account, at least in part by accessing a digital profile associated with the vendor, wherein the digital profile is a first digital profile included in a set of digital profiles collectively associated with a plurality of vendors, wherein the first digital profile includes a classification indicative of correspondence risk and information regarding how the classification was determined, wherein at least one email included in the set of emails is an outreach by the second email account to an email account associated with a second enterprise that is different from the first enterprise; and
determining, based on the metric, how to handle the obtained email.
2. The method of claim 1 , wherein said establishing comprises:
determining that the email is sent from an email address with a domain that is associated with the vendor; and
determining that the email contains the invoice based on an analysis of content of the email.
3. The method of claim 1 , wherein when the metric indicates that the risk in communicating with the second email account is high, said determining comprises:
implementing a filter so as to at least temporarily prohibit incoming emails from the second email account from being received by employees of the first enterprise.
4. The method of claim 1 , wherein when the metric indicates that the risk in communicating with the second email account is high, said determining comprises:
causing display of a notification by a computer program that includes information regarding the instance of outreach by the second email account.
5. The method of claim 4 , wherein the information includes a first email address of the first email account, a second email address of the second email account, a time at which the email was transmitted, a geographical location from which the email was transmitted, an Internet Protocol (IP) address from which the email was transmitted, or any combination thereof.
6. The method of claim 1 , wherein when the metric indicates that the risk in communicating with the second email account is low, said determining comprises:
allowing the email to reach an inbox of the first email account.
7. The method of claim 1 , further comprising:
applying a first maliciousness model to the email to produce a first output indicative of whether the email is representative of a non-malicious email;
establishing, based on the first output, that the email is representative of a malicious email; and
applying a second maliciousness model to the email to produce a second output indicative of whether the email is representative of a given type of malicious email;
wherein said determining is further based on the first output and/or the second output.
8. A non-transitory medium with instructions stored thereon that, when executed by a processor of a computing device, cause the computing device to perform operations comprising:
obtaining an email that is addressed to a first email account associated with a first enterprise;
establishing that the email represents an instance of outreach by a second email account associated with a vendor for payment of an invoice by the first enterprise;
obtaining a metric that is indicative of a risk in communicating with the second email account based at least in part on a comparison of the email to a set of emails that are representative of past instances of outreach by the second email account, at least in part by accessing a digital profile associated with the vendor, wherein the digital profile is a first digital profile included in a set of digital profiles collectively associated with a plurality of vendors, wherein the first digital profile includes a classification indicative of correspondence risk and information regarding how the classification was determined, wherein at least one email included in the set of emails is an outreach by the second email account to an email account associated with a second enterprise that is different from the first enterprise; and
determining, based on the metric, how to handle the obtained email.
9. The non-transitory medium of claim 8 , wherein said establishing comprises:
determining that the email is sent from an email address with a domain that is associated with the vendor; and
determining that the email contains the invoice based on an analysis of the content of the email.
10. The non-transitory medium of claim 8 , wherein when the metric indicates that the risk in communicating with the second email account is high, said determining comprises: implementing a filter so as to at least temporarily prohibit incoming emails from the second email account from being received by employees of the first enterprise.
11. The non-transitory medium of claim 8 , wherein when the metric indicates that the risk in communicating with the second email account is high, said determining comprises: causing display of a notification by a computer program that includes information regarding the instance of outreach by the second email account.
12. The non-transitory medium of claim 11 , wherein the information includes a first email address of the first email account, a second email address of the second email account, a time at which the email was transmitted, a geographical location from which the email was transmitted, an Internet Protocol (IP) address from which the email was transmitted, or any combination thereof.
13. The non-transitory medium of claim 8 , wherein when the metric indicates that the risk in communicating with the second email account is low, said determining comprises: allowing the email to reach an inbox of the first email account.
14. The non-transitory medium of claim 8 , wherein the instructions further cause the computing device to perform operations comprising:
applying a first maliciousness model to the email to produce a first output indicative of whether the email is representative of a non-malicious email;
establishing, based on the first output, that the email is representative of a malicious email; and
applying a second maliciousness model to the email to produce a second output indicative of whether the email is representative of a given type of malicious email;
wherein said determining is further based on the first output and/or the second output.
15. A system comprising:
a processor configured to:
obtain an email that is addressed to a first email account associated with a first enterprise;
establish that the email represents an instance of outreach by a second email account associated with a vendor for payment of an invoice by the first enterprise;
obtain a metric that is indicative of a risk in communicating with the second email account based at least in part on a comparison of the obtained email to a set of emails that are representative of past instances of outreach by the second email account, at least in part by accessing a digital profile associated with the vendor, wherein the digital profile is a first digital profile included in a set of digital profiles collectively associated with a plurality of vendors, wherein the first digital profile includes a classification indicative of correspondence risk and information regarding how the classification was determined, wherein at least one email included in the set of emails used in the comparison is an outreach by the second email account to an email account associated with a second enterprise that is different from the first enterprise; and
determine, based on the metric, how to handle the obtained email; and
a memory coupled to the processor and configured to provide the processor with instructions.
16. The system of claim 15 , wherein said establishing comprises:
determining that the email is sent from an email address with a domain that is associated with the vendor; and
determining that the email contains the invoice based on an analysis of content of the email.
17. The system of claim 15 , wherein when the metric indicates that the risk in communicating with the second email account is high, said determining comprises:
implementing a filter so as to at least temporarily prohibit incoming emails from the second email account from being received by employees of the first enterprise.
18. The system of claim 15 , wherein when the metric indicates that the risk in communicating with the second email account is high, said determining comprises:
causing display of a notification by a computer program that includes information regarding the instance of outreach by the second email account.
19. The system of claim 18 , wherein the information includes a first email address of the first email account, a second email address of the second email account, a time at which the email was transmitted, a geographical location from which the email was transmitted, an Internet Protocol (IP) address from which the email was transmitted, or any combination thereof.
20. The system of claim 15 , wherein when the metric indicates that the risk in communicating with the second email account is low, said determining comprises:
allowing the email to reach an inbox of the first email account.
21. The system of claim 15 , wherein the processor is further configured to:
apply a first maliciousness model to the email to produce a first output indicative of whether the email is representative of a non-malicious email;
establish, based on the first output, that the email is representative of a malicious email; and
apply a second maliciousness model to the email to produce a second output indicative of whether the email is representative of a given type of malicious email;
wherein said determining is further based on the first output and/or the second output.