| CPC G06Q 30/018 (2013.01) [G06N 3/08 (2013.01)] | 20 Claims |
|
1. A method, comprising:
training, by a computer system included as part of a web-based service, a contrastive loss function to compare a submitted image to a plurality of images stored in a database, the contrastive loss function to be used to identify fraudulent images associated with a particular entity;
receiving, by the computer system via a network connection, a request to create a new account profile, the request including new profile information that includes a new profile image and a new profile identifier;
comparing, by the computer system, the new profile identifier to one or more existing profile identifiers stored by the computer system;
in response to determining that at least one existing profile identifier satisfies a threshold identifier metric relative to the new profile identifier, generating a vector representation of the new profile image, wherein generating the vector representation of the new profile image includes using the contrastive loss function for:
extracting a plurality of characteristics from ones of a plurality of pixel data of the new profile image;
generating corresponding outputs representative of the plurality of characteristics; and
reducing a number of the outputs by combining the outputs into one or more vectors indicative of the plurality of characteristics;
comparing, by the computer system, the new profile image to one or more existing profile images corresponding to the at least one existing profile identifier, wherein the comparing includes generating a fake metric value that is indicative of a degree of similarity of the vector representation of the new profile image to vector representations of at least one of the one or more existing profile images associated with a legitimate profile; and
determining, by the computer system, whether to reject the request to create the new account profile based on the fake metric value.
|