US-12626345-B2 - F-stat statistical detection of digital image tampering

Abstract

Embodiments relate to a digital image file alteration detection controller which implements a processor configuration to efficiently detect an alteration to a digital image file. The digital image file alteration detection controller can include a processor, and a memory associated with the processor, the memory including instructions stored thereon that when executed by the processor will cause the processor to: extract Photo Response Non-Uniformity (PRNU) data of a digital image file received from the memory; determine a local variability representing a variability in PRNU data for a locale of a digital image file; determine a global variability representing a variability in PRNU data for an entire digital image file; compare local variability to global variability; and generate an alteration detection indicator indicative of an alteration detected when the local variability to global variability comparison is less than a threshold value.

Inventors

• Robert Shaw Sneddon

Assignees

• BOOZ ALLEN HAMILTON INC.

Dates

Publication Date

20260512

Application Date

20231005

Claims (20)

1. 1 . A digital image file alteration detection controller which implements a processor configuration to efficiently detect an alteration to a digital image file, the digital image file alteration detection controller comprising: a processor, and a memory associated with the processor, the memory including instructions stored thereon that when executed by the processor will cause the processor to: extract Photo Response Non-Uniformity (PRNU) data of a digital image file received from the memory; determine a local variability representing a variability in PRNU data for a locale of a digital image file; determine a global variability representing a variability in PRNU data for an entire digital image file; compare local variability to global variability; and generate an alteration detection indicator indicative of an alteration detected based on an evaluation of the local variability to global variability comparison.
2. 2 . The controller of claim 1 , wherein: instructions will cause the processor to determine a local variability for plural locales of a digital image file.
3. 3 . The controller of claim 2 , wherein: instructions will cause the processor to compare plural local variabilities and global variabilities.
4. 4 . The controller of claim 1 , wherein: instructions will cause the processor to determine a local variability for each locale of a digital image file.
5. 5 . The controller of claim 4 , wherein: instructions will cause the processor to compare an individual local variability to global variability for each individual locale.
6. 6 . The controller of claim 1 , wherein: a locale is a zone of a digital image file including plural pixels.
7. 7 . The controller of claim 1 , wherein: a local is a zone of a digital image file including plural pixels in which at least two pixels are adjacent each other.
8. 8 . The controller of claim 1 , wherein: local variability includes a measure of variability, a measure of change, a measure of variance, and/or an entropy type measure; global variability includes a measure of variability, a measure of change, a measure of variance, and/or an entropy type measure; compare local variability to global variability includes dividing a local variability by a global variability.
9. 9 . The controller of claim 1 , wherein: instructions will cause the processor to measure a central tendency and variance of signal strength from PRNU data; and instructions will cause the processor to set a threshold value or bounded set of values based on a central tendency and variance in signal strength from PRNU data.
10. 10 . The controller of claim 1 , wherein: instructions will cause the processor to measure a mean, a variance, and a standard deviation of signal strength from PRNU data; and instructions will cause the processor to set a threshold value or bounded set of values based on a standard deviation in signal strength from PRNU data.
11. 11 . The controller of claim 1 , wherein: instructions will cause the processor to generate a no-alteration detection indicator indicative of no alteration detected for a locale when the local variability to global variability comparison is greater than or equal to a threshold value.
12. 12 . The controller of claim 11 , wherein: instructions will cause the processor to generate a heat map including a color-coded representation based on the alteration detection indicator and the no-alteration detection indicator.
13. 13 . A method for managing a processor configuration to efficiently detect an alteration to a digital image file by: extracting Photo Response Non-Uniformity (PRNU) data of a digital image file; determining a local variability representing a variability in PRNU data for a locale of a digital image file; determining a global variability representing a variability in PRNU data for an entire digital image file; comparing a local variability to global variability; and generating an alteration detection indicator indicative of an alteration detected based on an evaluation of the local variability to global variability comparison.
14. 14 . The method of claim 13 , comprising: determining a local variability for plural locales of a digital image file.
15. 15 . The method of claim 14 , comprising: comparing plural local variabilities and global variabilities.
16. 16 . The method of claim 13 , comprising: determining a local variability for each locale of a digital image file.
17. 17 . The method of claim 16 , comprising: comparing an individual local variability to global variability for each individual locale.
18. 18 . The method of claim 13 , comprising: generating a no-alteration detection indicator indicative of no alteration detected for a locale when the local variability to global variability comparison is greater than or equal to a threshold value.
19. 19 . The method of claim 18 , comprising: generating a heat map including a color-coded representation based on the alteration detection indicator and the no-alteration detection indicator.
20. 20 . A non-transitory computer readable medium including instructions stored thereon that when executed by a processor will cause the processor to efficiently detect an alteration to a digital image file by: extracting Photo Response Non-Uniformity (PRNU) data of a digital image file; determining a local variability representing a variability in PRNU data for a locale of a digital image file; determining a global variability representing a variability in PRNU data for an entire digital image file; comparing a local variability to global variability; and generating an alteration detection indicator indicative of an alteration detected based on an evaluation of the local variability to global variability comparison.

Description

STATEMENT CONCERNING FEDERALLY SPONSORED RESEARCH This invention was made with government support under Contract No. GS00Q14OADU406 (Task Order No. HM047618F0198). The Government has certain rights in the invention. FIELD Embodiments relate to methods and systems to detect digital image forgeries or tampering of a digital image. BACKGROUND INFORMATION Known system and methods are deficient in that they lack a robust technique for detecting alterations of the PRNU of a digital image. Known systems and methods can be appreciated from CN 112330632 to Quan et al., CN 114066965 to Tan et al., CN 114612411 to Han et al., CN 115223217 to Liu et al., U.S. Pat. No. 7,643,699 to Lim et al., U.S. Pat. No. 9,760,973 to Bayram et al., U.S. Pat. No. 11,288,537 to McCloskey et al., US 2022/0084223 by Norris et al., Debiasi, L., Rathgeb, C., Scherhag, U., Uhl, A., & Busch, C. (2018 October). “PRNU Variance Analysis for Morphed Face Image Detection”, and Tan, Q., Qi, S., Zhang, Y., & Xue, M. (2022 September). “PRNU-based Image Forgery Localization With Convolutional Neural Network” SUMMARY Embodiments can relate to a digital image file alteration detection controller which implements a processor configuration to efficiently detect an alteration to a digital image file. The digital image file alteration detection controller can include a processor, and a memory associated with the processor. The memory can include instructions stored thereon that when executed by the processor will cause the processor to extract Photo Response Non-Uniformity (PRNU) data of a digital image file received from the memory. The instructions will cause the processor to determine a local variability representing a variability in PRNU data for a locale of a digital image file. The instructions will cause the processor to determine a global variability representing a variability in PRNU data for an entire digital image file. The instructions will cause the processor to compare local variability to global variability. The instructions will cause the processor to generate an alteration detection indicator indicative of an alteration detected when the local variability to global variability comparison is less than a threshold value. Embodiments can relate to a method for managing a processor configuration to efficiently detect an alteration to a digital image file. The method can involve extracting Photo Response Non-Uniformity (PRNU) data of a digital image file. The method can involve determining a local variability representing a variability in PRNU data for a locale of a digital image file. The method can involve determining a global variability representing a variability in PRNU data for an entire digital image file. The method can involve comparing a local variability to global variability. The method can involve generating an alteration detection indicator indicative of an alteration detected when the local variability to global variability comparison is less than a threshold value. Embodiments can relate to a computer readable medium including instructions stored thereon that when executed by a processor will cause the processor to efficiently detect an alteration to a digital image file. The instructions will cause the processor to extract Photo Response Non-Uniformity (PRNU) data of a digital image file or a similar type of noise which is dependent on the response properties a spectroscopic type of sensor. The instructions will cause the processor to determine a local variability representing a variability in PRNU data for a locale of a digital image file. The instructions will cause the processor to determine a global variability representing a variability in PRNU data for an entire digital image file. The instructions will cause the processor to compare a local variability to global variability. The instructions will cause the processor to generate an alteration detection indicator indicative of an alteration detected when the local variability to global variability comparison is less than a threshold value. BRIEF DESCRIPTION OF THE DRAWINGS Other features and advantages of the present disclosure will become more apparent upon reading the following detailed description in conjunction with the accompanying drawings, wherein like elements are designated by like numerals, and wherein: FIG. 1 shows an exemplary digital image file alteration detection controller; FIG. 2 shows an exemplary F-STAT technique that can be used to detect an alteration to a digital image file; FIG. 3 shows an exemplary process for generating a heat map for a digital image file; and FIG. 4 shows an exemplary heat map for a digital image file. DETAILED DESCRIPTION Embodiments can relate to a controller, a system, and/or a method for detecting alteration of a file. The file can include spectroscopic dependent fixed pattern noise (e.g., the production of Photo Response Non-Uniformity (PRNU)). A digital image can be an example of such file. As a non-limiting example, the fil