US 11,658,987 B2
Dynamic fraudulent user blacklist to detect fraudulent user activity with near real-time capabilities
Jeremy Edward Goodsitt, Champaign, IL (US); Austin Grant Walters, Savoy, IL (US); Reza Farivar, Champaign, IL (US); and Vincent Pham, Champaign, IL (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jan. 6, 2021, as Appl. No. 17/142,664.
Application 17/142,664 is a continuation of application No. 16/549,306, filed on Aug. 23, 2019, granted, now 10,911,469.
Prior Publication US 2021/0126930 A1, Apr. 29, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 9/40 (2022.01)
CPC H04L 63/1416 (2013.01) 17 Claims
OG exemplary drawing
 
1. An apparatus comprising:
one or more processors operable to execute stored instructions that, when executed, cause the one or more processors to:
determine a first fraudulent user pattern in response to a notification from a first user account of a first fraudulent access, the first fraudulent user pattern comprising a fraudster sequentially performing a first action and a second action via an account interface;
add the first fraudulent user pattern to a blacklist;
determine a second fraudulent user pattern indicating an abnormal user pattern likely to be fraudulent, the second fraudulent user pattern being determined without notification from any user account;
dynamically update the blacklist to add the second fraudulent user pattern and generate an updated blacklist;
perform a fraud analysis by analyzing a plurality of user accounts by comparing at least the first and second fraudulent user patterns of the blacklist to user account activities associated with the plurality of user accounts;
detect that a second fraudulent access associated with a second user account has occurred based on the performed fraud analysis; and
alert the second user account of the second fraudulent access,
wherein the determination of the second fraudulent user pattern comprises the one or more processors to:
detect that the abnormal user pattern likely to be fraudulent is similarly or identically associated with multiple user accounts;
perform a second fraud analysis by analyzing the abnormal user pattern across the multiple accounts; and
determine that there is a probability that the multiple accounts are being fraudulently accessed by a same fraudster based at least in part on the performed second fraud analysis.