Invention Grant
- Patent Title: Identification of neural-network-generated fake images
-
Application No.: US17182250Application Date: 2021-02-23
-
Publication No.: US11676408B2Publication Date: 2023-06-13
- Inventor: Matthias Nießner , Gaurav Bharaj
- Applicant: Artificial Intelligence Foundation, Inc.
- Applicant Address: US NV Las Vegas
- Assignee: Artificial Intelligence Foundation, Inc.
- Current Assignee: Artificial Intelligence Foundation, Inc.
- Current Assignee Address: US NV Las Vegas
- Agent Steven Stupp
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06V20/80 ; G06T7/00 ; G06V10/42 ; G06V10/764 ; G06V10/77 ; G06V10/82 ; G06V10/44 ; G06V10/46 ; G06V20/00

Abstract:
A computer that identifies a fake image is described. During operation, the computer receives an image. Then, the computer performs analysis on the image to determine a signature that includes multiple features. Based at least in part in the determined signature, the computer classifies the image as having a first signature associated with the fake image or as having a second signature associated with a real image, where the first signature corresponds to a finite resolution of a neural network that generated the fake image, a finite number of parameters in the neural network that generated the fake image, or both. For example, the finite resolution may correspond to floating point operations in the neural network. Moreover, in response to the classification, the computer may perform a remedial action, such as providing a warning or a recommendation, or performing filtering.
Public/Granted literature
- US20210174487A1 Identification of Neural-Network-Generated Fake Images Public/Granted day:2021-06-10
Information query