# US 12,020,506 B2 · Methods and apparatus to detect deepfake content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,020,506 B2 - Document ID: US12020506B2 - Status: Granted - Kind: B2 - Application number: 18/340,013 - Filed: 2023-06-22 - Published: 2023-10-19 - Granted: 2024-06-25 - Earliest claimed: 2019-09-30 - Assignees: Mcaffe, LLC - Applicants: McAfee, LLC - Inventors: Utkarsh Verma; Sherin M Mathews; Amanda House; Carl Woodward; Celeste Fralick; Jonathan King - Web page: https://patentgrep.com/patent/US12020506B2 ## CPC - G06V 40/172: {Classification, e.g. identification} - G06V 10/449: {Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters} - G06V 10/54: relating to texture - G06V 20/49: {Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes} - G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships} - G06V 40/40: Spoof detection, e.g. liveness detection - G06V 40/45: {Detection of the body part being alive} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Methods, apparatus, systems and articles of manufacture are disclosed to detect deepfake content. An example apparatus to determine whether input media is authentic includes a classifier to generate a first probability based on a first output of a local binary model manager, a second probability based on a second output of a filter model manager, and a third probability based on a third output of an image quality assessor, a score analyzer to obtain the first, second, and third probabilities from the classifier, and in response to obtaining a first result and a second result, generate a score indicative of whether the input media is authentic based on the first result, the second result, the first probability, the second probability, and the third probability. ## Claims ### Claim 1 An apparatus comprising: network interface circuitry; instructions; processing circuitry to at least one of execute the instructions stored in the apparatus or instantiate the instructions to: generate a first probability based on a first output of a local binary model; generate a second probability based on a second output of a filter model; generate a third probability based on a third output of an image quality assessment; generate a first result indicative of whether a blink occurred in a human face in an input media; generate a second result representative of a degree of blur in frames of the input media; and generate a score indicative of whether the input media is authentic based on at least one of the first result and the second result, the first probability, the second probability, and the third probability. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein the input media is authentic when the score is less than a score threshold. ### Claim 3 (depends on 1) The apparatus of claim 1, wherein the processing circuitry is to generate the second output by: applying a Gabor filter to a frame of the input media; and extracting signals from the frame of the input media responsive to the Gabor filter being applied, the signals corresponding to changes in texture in the input media. ### Claim 4 (depends on 1) The apparatus of claim 1, wherein the processing circuitry is to determine that the blink occurred when a ratio of points in an eye satisfies a threshold for four frames of the input media. ### Claim 5 (depends on 1) The apparatus of claim 1, wherein the first, second, and third probabilities correspond to a likelihood that the input media is a deepfake. ### Claim 6 (depends on 1) The apparatus of claim 1, wherein the input media is a video. ### Claim 7 (depends on 1) The apparatus of claim 1, wherein the first probability is based on applying the local binary model to the input media. ### Claim 8 A non-transitory computer readable medium comprising instructions which, when executed, cause at least one processor to at least: generate a first probability based on a first output of a local binary model; generate a second probability based on a second output of a filter model; generate a third probability based on a third output of an image quality assessment; generate a first result indicative of whether a blink occurred in a human face in an input media; generate a second result representative of a degree of blur in frames of the input media; and generate a score indicative of whether the input media is authentic based on at least one of the first result and the second result, the first probability, the second probability, and the third probability. ### Claim 9 (depends on 8) The non-transitory computer readable medium of claim 8, wherein the input media is authentic when the score is less than a score threshold. ### Claim 10 (depends on 8) The non-transitory computer readable medium of claim 8, wherein the instructions, when executed, cause the at least one processor to generate the second output by: applying a Gabor filter to a frame of the input media; and extracting signals from the frame of the input media responsive to the Gabor filter being applied, the signals corresponding to changes in texture in the input media. ### Claim 11 (depends on 8) The non-transitory computer readable medium of claim 8, wherein the instructions, when executed, cause the at least one processor to determine that the blink occurred when a ratio of points in an eye satisfies a threshold for four frames of the input media. ### Claim 12 (depends on 8) The non-transitory computer readable medium of claim 8, wherein the first, second, and third probabilities correspond to a likelihood that the input media is a deepfake. ### Claim 13 (depends on 8) The non-transitory computer readable medium of claim 8, wherein the input media is a video. ### Claim 14 (depends on 8) The non-transitory computer readable medium of claim 8, wherein the first probability is based on applying the local binary model to the input media. ### Claim 15 A method comprising: generating a first probability based on a first output of a local binary model; generating a second probability based on a second output of a filter model; generating a third probability based on a third output of an image quality assessment; generating a first result indicative of whether a blink occurred in a human face in an input media; generating a second result representative of a degree of blur in frames of the input media; and generating a score indicative of whether the input media is authentic based on at least one of the first result and the second result, the first probability, the second probability, and the third probability. ### Claim 16 (depends on 15) The method of claim 15, wherein the input media is authentic when the score is less than a score threshold. ### Claim 17 (depends on 15) The method of claim 15, further including generating the second output by: applying a Gabor filter to a frame of the input media; and extracting signals from the frame of the input media responsive to the Gabor filter being applied, the signals corresponding to changes in texture in the input media. ### Claim 18 (depends on 15) The method of claim 15, further including determining that the blink occurred when a ratio of points in an eye satisfies a threshold for four frames of the input media. ### Claim 19 (depends on 15) The method of claim 15, wherein the first, second, and third probabilities correspond to a likelihood that the input media is a deepfake. ### Claim 20 (depends on 15) The method of claim 15, wherein the first probability is based on applying the local binary model to the input media.