| CPC H04L 63/1483 (2013.01) [H04L 63/1433 (2013.01)] | 20 Claims |
|
1. A computer-implemented method for identifying brands utilized in website phishing campaigns, at least a portion of the method being performed by one or more computing devices comprising at least one processor, the method comprising:
capturing, by the one or more computing devices, a website screenshot comprising one or more visual elements representing a potential phishing vulnerability;
transforming, by the one or more computing devices and utilizing a deep learning model, the website screenshot into an image representation comprising a plurality of embeddings;
determining, by the one or more computing devices, whether the transformed website screenshot matches a dataset comprising a plurality of reference transformed website screenshots representing one or more previously identified brands utilized in phishing campaigns;
clustering, by the one or more computing devices and upon determining a mismatch between the transformed website screenshot and the dataset, the transformed website screenshot with other transformed website screenshots sharing the visual elements representing the potential phishing vulnerability and one or more visual similarities;
extracting, by the one or more computing devices, brand information based on the clustering;
adding, by the one or more computing devices, the extracted brand information to the dataset; and
performing, by the one more computing devices and based on the dataset, a security action that protects against potential phishing attacks.
|