Systems and methods for detecting scam emails
A scam detection system includes a user computer that runs a security application and a backend system that runs a scam detector. An email is received at the user computer. The security application extracts and forwards a content of the email, which includes a body of the email, to the backend system. The email body of the email is anonymized by removing personally identifiable information from the email body. A hash of the anonymized email body is generated and compared against hashes of a whitelist and a blacklist. The anonymized email body is classified. A segment of text of the anonymized email body is identified and provided to the user computer when the anonymized email body is classified as scam.
1 . A method of detecting scam emails, the method comprising:
at a user computer:
receiving an email; and
forwarding, by a security application running at the user computer, at least an email body of the email from the user computer to a backend system for evaluation; and
at the backend system:
removing personally identifiable information from the email body to generate an anonymized email body;
classifying the anonymized email body to determine whether or not the email is a scam email;
classifying the anonymized email body as a scam;
identifying a segment of text that is indicative of scam emails in the anonymized email body; and
providing a result to the user computer, wherein the result includes the segment of text.
2 . A system for detecting scam emails, the system comprising:
a user computer comprising at least one processor and a memory that stores instructions of a security application, the instructions of the security application when executed by the at least one processor of the user computer cause the user computer to extract a content of an email that has been received at the user computer and forward the extracted content of the email; and
a backend system comprising at least one processor and a memory that stores instructions of a scam detector, the instructions of the scam detector when executed by the at least one processor of the backend system cause the backend system to:
receive the extracted content that has been forwarded from the user computer, remove personally identifiable information from an email body that is included in the extracted content to generate an anonymized email body,
check a reputation of an object that is included in the email body,
classify the anonymized email body to determine whether or not the anonymized email body is a scam,
generate a hash of the anonymized email body,
compare the hash to a whitelist,
compare the hash to a blacklist, and
provide a result of evaluation of the extracted content to the user computer,
wherein the instructions of the scam detector when executed by the at least one processor of the backend system further cause the backend system to identify, from the anonymized email body, a segment of text that is indicative of scam and to provide the segment of text to the user computer.
3 . A method of detecting scam emails, the method comprising:
removing personally identifiable information from an email body of an email to generate an anonymized email body;
generating a hash of the anonymized email body;
classifying the anonymized email body to determine whether or not the anonymized email body is a scam; and
checking the hash against a listing of hashes,
wherein the anonymized email body is classified as a scam and the method further comprises:
identifying, in the anonymized email body, a segment of text that is indicative of scam; and
providing the segment of text to a user computer.