# US 12,764,334 B2 · Securely encoding authenticity tokens into artificial intelligence (AI) generated content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,764,334 B2 - Document ID: US12764334B2 - Status: Granted - Kind: B2 - Application number: 18/734,940 - Filed: 2024-06-05 - Published: 2025-12-11 - Granted: 2026-10-13 - Earliest claimed: 2024-06-05 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Meenaz Aliraza Merchant; Bichong Li; Yue Yu - Web page: https://patentgrep.com/patent/US12764334B2 ## CPC - H04N 19/625: using discrete cosine transform [DCT] - H04N 19/184: the unit being bits, e.g. of the compressed video stream - H04N 19/63: using sub-band based transform, e.g. wavelets - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract This disclosure describes utilizing an image encoding system that provides a comprehensive and robust defense strategy for artificial intelligence (AI) generated content (AIGC). Specifically, the image encoding system provides a framework that combines multiple security measures with various transform domain methods in order to encode an image with multiple instances of an encoded image identifier. The image encoding system achieves a balance between maintaining the high quality of generative images and ensuring the traceability of the images. By doing so, the image encoding system addresses numerous technical challenges presented by AI-generated media, thereby ensuring that generative images are protected against unauthorized usage. ## Claims ### Claim 1 A computer-implemented method for encoding authenticity tokens into artificial intelligence (AI) generated content, comprising: generating discrete cosine transform (DCT) blocks for a generative image based on using discrete wavelet transform (DWT) and DCT; generating a set of singular values for a first DCT block using singular value decomposition (SVD); encoding a bit of an image identifier for the generative image into a first singular value of the set of singular values, wherein the image identifier indicates origin information about the generative image; and generating an encoded generative image based on applying an inverse SVD, an inverse DCT, and an inverse DWT to the set of singular values having an encoded singular value. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein generating the DCT blocks includes: generating wavelet coefficients for the generative image by applying the DWT to the generative image; and generating the DCT blocks by partitioning the wavelet coefficients using the DCT. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein generating the set of singular values for the first DCT block includes: identifying a shuffle pattern for the first DCT block; shuffling pixels within the first DCT block into a new configuration based on the shuffle pattern, and using the new configuration of pixels with the SVD. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein the shuffle pattern: removes a pixel from the first DCT block; applies the shuffle pattern to remaining pixels of the first DCT block; and generates the new configuration of pixels by converting remaining pixels of the first DCT block into an additional matrix for performing the SVD. ### Claim 5 (depends on 4) The computer-implemented method of claim 4, wherein: the first DCT block is four elements by four elements; and the additional matrix includes fifteen remaining elements of the first DCT block arranged into a three by five matrix. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein encoding the bit of the image identifier into the first singular value includes: identifying a first numeric value for the first singular value; modifying the first numeric value for the first singular value to a second numeric value based on the bit having a value of one; and modifying the first numeric value for the first singular value to a third numeric value based on the bit having a value of zero, wherein the first numeric value, the second numeric value, and the third numeric value differ. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, further comprising: generating the image identifier in connection with generating the generative image; and encoding the image identifier into a bit sequence, wherein the bit is part of the bit sequence. ### Claim 8 (depends on 7) The computer-implemented method of claim 7, wherein encoding the image identifier into the bit sequence includes encoding the image identifier with a private security key to generate the bit sequence. ### Claim 9 (depends on 8) The computer-implemented method of claim 8, further comprising: encoding single bits of the bit sequence into different first singular values corresponding to different DCT blocks, wherein the bit sequence is included in the generative image up to 136 times when the generative image has an original pixel size of 1024 pixels by 1024 pixels. ### Claim 10 (depends on 9) The computer-implemented method of claim 9, wherein: using the SVD generates the first DCT block into SVD matrices with a diagonal matrix that includes the set of singular values; and encoding the bit into the first singular value includes modifying the first singular value within the diagonal matrix without modifying other singular values of the set of singular values within the diagonal matrix. ### Claim 11 (depends on 1) The computer-implemented method of claim 1, further comprising utilizing an image quality model to determine that encoding the bit into the first singular value of the set of singular values will result in a visible image alteration. ### Claim 12 (depends on 11) The computer-implemented method of claim 11, wherein: the image quality model is trained to determine when encoding the bit into a singular value instance of a diagonal matrix associated with SVD matrices for a DCT block will result in a visible image alteration; and skipping encoding the bit into the singular value instance if the encoding results in a visible image alteration. ### Claim 13 (depends on 12) The computer-implemented method of claim 12, wherein the image quality model is a decision tree-based machine learning model trained based on DCT blocks generated from an inverted SVD process. ### Claim 14 A computer-implemented method for encoding authenticity tokens into artificial intelligence (AI) generated content, comprising: generating discrete cosine transform (DCT) blocks for a generative image based on using discrete wavelet transform (DWT) and DCT; generating a set of singular values for each of the DCT blocks using singular value decomposition (SVD); encoding single bits of an encrypted image identifier for the generative image into each first singular value of each set of singular values associated with each of the DCT blocks, wherein an image identifier of the encrypted image identifier indicates origin information about the generative image; and generating an encoded generative image based on applying an inverse SVD, an inverse DCT, and an inverse DWT to each first set of singular values with an encoded first singular value. ### Claim 15 (depends on 14) The computer-implemented method of claim 14, further comprising decoding a version of the encoded generative image based on: extracting multiple instances of a bit sequence from the encoded generative image; generating a combined bit sequence from the multiple instances of the bit sequence; and decrypting the combined bit sequence to identify the image identifier. ### Claim 16 (depends on 15) The computer-implemented method of claim 15, further comprising: refining the combined bit sequence using k-means clustering to determine a dynamic threshold; and applying the dynamic threshold to floating-point values within each bit in the combined bit sequence to generate a binary bit sequence. ### Claim 17 (depends on 15) The computer-implemented method of claim 15, wherein: decoding the version of the encoded generative image includes applying a shuffle pattern between the DCT blocks and the SVD; and the shuffle pattern was used to encode the generative image. ### Claim 18 (depends on 14) The computer-implemented method of claim 14, further comprising: identifying a digital image with unknown origins; decoding the digital image to identify the image identifier within the digital image; and determining the origin information of the digital image based on identifying the image identifier hidden within the digital image. ### Claim 19 (depends on 18) The computer-implemented method of claim 18, further comprising identifying a user identifier requesting the generative image be generated based on the image identifier. ### Claim 20 A system, comprising: a processing system; and a computer memory comprising instructions that, when executed by the processing system, cause the system to perform operations of: generating discrete cosine transform (DCT) blocks for a generative image based on using discrete wavelet transform (DWT) and DCT; generating a set of singular values for a first DCT block using singular value decomposition (SVD); encoding a bit of an image identifier for the generative image into a first singular value of the set of singular values, wherein the image identifier indicates origin information about the generative image; and generating an encoded generative image based on applying an inverse SVD, an inverse DCT, and an inverse DWT to the set of singular values having an encoded singular value.