US 12,137,115 B2
System and methods for mitigating fraud in real time using feedback
Luke Anthony James Taylor, Cloverdale (AU); Raigon Jolly, Thornlie (AU); André Bonkowski, Lynwood (AU); and Andrey Kostenko, East Perth (AU)
Appl. No. 17/048,359
Filed by TrafficGuard Pty Ltd, Bentley (AU)
PCT Filed Apr. 17, 2019, PCT No. PCT/AU2019/050343
§ 371(c)(1), (2) Date Oct. 16, 2020,
PCT Pub. No. WO2019/200432, PCT Pub. Date Oct. 24, 2019.
Claims priority of application No. 2018901298 (AU), filed on Apr. 18, 2018.
Prior Publication US 2021/0067544 A1, Mar. 4, 2021
Int. Cl. H04L 29/06 (2006.01); G06F 11/30 (2006.01); G06F 17/18 (2006.01); G06N 20/00 (2019.01); H04L 9/40 (2022.01)
CPC H04L 63/1441 (2013.01) [G06F 11/3065 (2013.01); G06F 17/18 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method for mitigating fraud, the method comprising:
storing on a database, electronic program instructions for controlling an advertiser server with a processor and controlling the processor via the electronic program instructions;
receiving input data from a local device in response to a selectable advertisement transmitted from the advertiser server to the local device, wherein the input data comprises a selection of the selectable advertisement;
comparing current attributes of a source of the input data with known attributes of known sources to determine if certain behavioral anomalies of the source of the input data exists;
wherein the known attributes comprise identifying data of the known sources including demographic origins and activities of the known sources based on registered profile information, wherein the registered profile information includes duplicate profile detection, unusual profile changes, and login pattern anomalies;
detecting if the source of the input data is a malicious source or legitimate source based on an analysis of an existence of the determined certain behavioral anomalies and the comparison of the current attributes and the known attributes;
storing in an advertiser database the comparison of the current attributes of the source of the input data and the known sources and the determination if certain behavioral anomalies of the source of the input data exists;
performing a prevention process if it is determined that the source of the input data is the malicious source, wherein the prevention process comprises blocking the selection of the selectable advertisement to be transmitted to the advertiser server to prevent displaying the selectable advertisement on the local device;
generating a fraud mitigated output if it is determined that the source of the input data is the legitimate source, wherein the prevention process comprises allowing the selection of the selectable advertisement to be transmitted to the advertiser server to allow displaying the selectable advertisement on the local device; and
using the comparison of the current attributes of the source of the input data and the known sources and the determination if certain behavioral anomalies of the source of the input data exists stored in the database to enhance the prevention process when detecting the malicious source.