	US 11,997,138 B1
	Detecting and analyzing phishing attacks through artificial intelligence
Ahmed Alyahya, Al Hasa (SA); and Mohammed Alzahrani, Al Hasa (SA)
Assigned to KING FAISAL UNIVERSITY, Al Hasa (SA)
Filed by KING FAISAL UNIVERSITY, Al Hasa (SA)
Filed on Feb. 5, 2024, as Appl. No. 18/432,907.
Int. Cl. H04L 9/40 (2022.01)

CPC H04L 63/1483 (2013.01)

12 Claims

1. A method for detecting phishing messages in network communications, the method comprising:

receiving a transmitted message and detecting characteristics of the message;

determining if the message matches a pattern of a phishing message in a database;

in the case of the message matching a known phishing message, classifying the message as spam or a phishing message and moved to a phishing or spam folder;

in the case of the message not matching a known phishing message pattern, checking the message for common signs of phishing or spam by determining the severity of a threat embodied by the message, and categorizing the message as having phishing characteristics;

in the case of a determination of a low probability of phishing characteristics, not further process the message for phishing;

in the case of a determination of a high or moderate probability of phishing characteristics, classifying the message as presenting signs of a phishing attempt;

in the case of a determination indicating phishing with a high accuracy, classifying the message as presenting signs of a phishing attempt with a high accuracy, and sending a warning message of a high probability of phishing to the recipient; and

in the case of a determination indicating phishing with a moderate or medium accuracy, classifying the message as presenting signs of a phishing attempt with a moderate or medium accuracy, and sending a warning message of a moderate probability of phishing.