US 11,710,195 B2
Detection and prevention of fraudulent activity on social media accounts
Sharon Hüffner, Berlin (DE); Harold Nguyen, Burlingame, CA (US); Richard Banks Sutton, San Mateo, CA (US); and Daniel Oshiro Nadir, Carlsbad, CA (US)
Assigned to PROOFPOINT, INC., Sunnyvale, CA (US)
Filed by Proofpoint, Inc., Sunnyvale, CA (US)
Filed on Jan. 11, 2021, as Appl. No. 17/146,450.
Application 17/146,450 is a continuation of application No. 15/395,385, filed on Dec. 30, 2016, granted, now 10,896,473.
Claims priority of provisional application 62/347,089, filed on Jun. 8, 2016.
Prior Publication US 2021/0209701 A1, Jul. 8, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/02 (2023.01); G06Q 10/06 (2023.01); G06Q 10/10 (2023.01); G06Q 40/02 (2023.01); G06Q 99/00 (2006.01); G06Q 50/00 (2012.01); G06Q 30/018 (2023.01); H04L 9/40 (2022.01)
CPC G06Q 50/01 (2013.01) [G06Q 30/0185 (2013.01); H04L 63/1425 (2013.01); H04L 63/1441 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A fraud detection system, comprising:
a processor;
a non-transitory computer-readable medium; and
stored instructions translatable by the processor for:
determining a brand account for which a brand owner of the brand account has subscribed for brand protection by the fraud detection system, the brand account being an account on a social network platform, the fraud detection system operating in a computing environment outside the social network platform;
determining, using a link to the brand account on the social network platform, metadata of legitimate content used on the social network platform by the brand owner by retrieving the metadata from the social network platform via an application programming interface (API) of the social network platform;
deriving a brand profile based at least on the metadata of legitimate content used on the social network platform by the brand owner, the brand profile applicable across multiple brand accounts on the social network platform that are owned by the brand owner;
detecting, via at least one application programming interface, a public message to the brand account on the social network platform and public replies to the public message by non-brand accounts on the social network platform, the public message originating from a social media account on the social network platform;
responsive to the detecting, monitoring public messages sent to the social media account on the social network platform over a predetermined time period, the monitoring comprising:
analyzing metadata of a non-brand account that is in communication with the social media account that originated the public message; and
determining whether a statistically significant match exists between the metadata of the non-brand account and the brand profile; and
responsive to a determination by the fraud detection system that the statistically significant match exists between the metadata of the non-brand account and the brand profile, identifying, by the fraud detection system, the non-brand account as an imposter account or a potential imposter account.