View source for 18387461. Deepfake Detection System (Bank of America Corporation)

<!-- JSON-LD markup for search engines:
{"@context":"https://schema.org","@type":"TechArticle","headline":"Deepfake Detection System","name":"Deepfake Detection System","description":"Various aspects of the disclosure relate to automated monitoring of content associated with an individual for indicators that the content may be a deepfake. A deepfake analysis training device trains ...","datePublished":"2023-11-07","mainEntity":{"@type":"Patent","identifier":"18387461","name":"Deepfake Detection System","abstract":"Various aspects of the disclosure relate to automated monitoring of content associated with an individual for indicators that the content may be a deepfake. A deepfake analysis training device trains artificial intelligence-based models based on validated content associated with one or more profiles. Each profile is associated with an individual. A deepfake analysis engine may be installed on computing devices to monitor access to content (e.g., multimedia content) for deepfakes associated with the one or more profiles, as configured. The deepfake analysis engine may be stand-alone application, an application extension, or may be integrated into third-party applications via application programming interface functions. Analyzed content is assigned a likelihood score that is compared to threshold values that indicates a likelihood that the content is a deepfake. When identified, deepfake content initiates an alert generation and/or blocking of the content otherwise the content is presented to a user.","applicationNumber":"18387461","datePublished":"2023-11-07","inventor":[{"@type":"Person","name":"Dylan Bellinger"},{"@type":"Person","name":"Sanjay Lohar"},{"@type":"Person","name":"Kyle Mayers"},{"@type":"Person","name":"Amado Martinez Suarez"},{"@type":"Person","name":"Cody Searl"},{"@type":"Person","name":"Rachel Howze"}],"applicant":{"@type":"Organization","name":"Bank of America Corporation"},"additionalProperty":[{"@type":"PropertyValue","name":"IPC Classification","value":"G06V20/40"},{"@type":"PropertyValue","name":"IPC Classification","value":"G06N20/00"},{"@type":"PropertyValue","name":"IPC Classification","value":"H04N21/454"},{"@type":"PropertyValue","name":"CPC Classification","value":"G06V20/46"}]}}
-->

=Deepfake Detection System=


==Organization Name==

[[:Category:Bank of America Corporation|Bank of America Corporation]]


[[Category:Bank of America Corporation]]

==Inventor(s)==

[[:Category:Dylan Bellinger of Charlotte NC US|Dylan Bellinger of Charlotte NC US]][[Category:Dylan Bellinger of Charlotte NC US]]

[[:Category:Sanjay Lohar of Charlotte NC US|Sanjay Lohar of Charlotte NC US]][[Category:Sanjay Lohar of Charlotte NC US]]

[[:Category:Kyle Mayers of Charlotte NC US|Kyle Mayers of Charlotte NC US]][[Category:Kyle Mayers of Charlotte NC US]]

[[:Category:Amado Martinez Suarez of Charlotte NC US|Amado Martinez Suarez of Charlotte NC US]][[Category:Amado Martinez Suarez of Charlotte NC US]]

[[:Category:Cody Searl of Pineville NC US|Cody Searl of Pineville NC US]][[Category:Cody Searl of Pineville NC US]]

[[:Category:Rachel Howze of Charlotte NC US|Rachel Howze of Charlotte NC US]][[Category:Rachel Howze of Charlotte NC US]]

==Deepfake Detection System==


This abstract first appeared for US patent application 18387461 titled 'Deepfake Detection System

==Original Abstract Submitted==

Various aspects of the disclosure relate to automated monitoring of content associated with an individual for indicators that the content may be a deepfake. A deepfake analysis training device trains artificial intelligence-based models based on validated content associated with one or more profiles. Each profile is associated with an individual. A deepfake analysis engine may be installed on computing devices to monitor access to content (e.g., multimedia content) for deepfakes associated with the one or more profiles, as configured. The deepfake analysis engine may be stand-alone application, an application extension, or may be integrated into third-party applications via application programming interface functions. Analyzed content is assigned a likelihood score that is compared to threshold values that indicates a likelihood that the content is a deepfake. When identified, deepfake content initiates an alert generation and/or blocking of the content otherwise the content is presented to a user.



[[Category:G06V20/40]]
[[Category:G06N20/00]]
[[Category:H04N21/454]]
[[Category:CPC_G06V20/46]]