A method for protecting and tracing the rights of three-dimensional models

Abstract

The invention provides a three-dimensional model rights protection and traceability method, which includes: collecting data information; using the sha256 hash algorithm to calculate the unique identifier of the computer that purchased the three-dimensional model rights product according to the data information; using the deep neural network invisible watermark technology to make a deep neural network model with the node unique identifier implanted, using the implanted neural network model to process the three-dimensional model rights product to obtain an encrypted file; using the sha256 hash function to calculate and process according to the encrypted file and the unique identifier; encrypting the three-dimensional model rights product again; packaging the product unique identifier and the node unique identifier of the second encrypted three-dimensional model file and submitting them to the smart contract of the alliance chain to obtain the three-dimensional model file authentication information. By exporting the stolen three-dimensional model file circulation process information, the details of the stolen three-dimensional model file can be analyzed.

Description

Technical Field

[0001] The present invention relates to the field of three-dimensional models, and in particular to a three-dimensional model rights protection and source tracing method. Background Art

[0002] At present, the schemes for tracing and protecting the rights of three-dimensional models using blockchain technology are prone to being cracked, because blockchain technology can only ensure that the information in the blockchain is credible, and cannot manage information outside the blockchain, especially the physical world. Since the model viewer in the computer must store the decrypted model information in the computer memory, the memory extraction method can be used to extract it and spread it without using the blockchain. In particular, blockchain technology is powerless to prevent piracy using the physical world method of taking screenshots or shooting the screen. Summary of the invention

[0003] In view of the above problems, the present invention is proposed to provide a three-dimensional model rights protection and source tracing method that overcomes the above problems or at least partially solves the above problems.

[0004] According to one aspect of the present invention, a method for protecting and tracing the rights of a three-dimensional model is provided, comprising:

[0005] Collecting data information, the data information including a MAC address of a computer network card of the three-dimensional model right product, and a collection of personal and / or institutional information;

[0006] Calculate the unique identifier of the computer that purchased the three-dimensional model rights product using the sha256 hash algorithm based on the data information;

[0007] The unique identifier includes a product unique identifier and a node unique identifier;

[0008] The product unique identifier is a unique identifier of the purchased three-dimensional model right;

[0009] The node unique identifier is a unique identifier of a peer node represented by a computer group of an individual and / or organization that has purchased the rights to the stereo model;

[0010] Using a deep neural network invisible watermarking technology to create a deep neural network model implanted with the unique identifier of the node, to obtain an implanted deep neural network model;

[0011] Processing the three-dimensional model rights product using the implanted neural network model to obtain an encrypted file;

[0012] The encrypted file and the unique identifier are processed by using the sha256 hash function to obtain a hash value;

[0013] encrypting the three-dimensional model right product again to obtain a secondary encrypted three-dimensional model file;

[0014] The product unique identifier and node unique identifier of the secondary encrypted 3D model file are packaged and submitted to the smart contract of the alliance chain to obtain the 3D model file authentication information.

[0015] Optionally, the traceability method further includes:

[0016] When the organization and / or individual who purchases the rights to the 3D model product shares the 3D model file with other computers, the shared party must also join the alliance chain as a peer node;

[0017] The purchaser packages the unique identifier of the 3D model file with the asymmetric encrypted public key of the computer to be shared, and signs the 3D model file with his own private key to generate a description file;

[0018] Upload the description file to the smart contract;

[0019] The smart contract will establish the circulation information and authorize the computer represented by the shared node to open the three-dimensional model file through smart contract authentication.

[0020] Optionally, the traceability method further includes:

[0021] Obtain the stolen 3D model file and decrypt the unique identifier;

[0022] The computer network card MAC address of the individual and / or organization that purchased the corresponding digital rights product and the previously written purchaser information are queried in the smart contract according to the unique identifier.

[0023] Optionally, the traceability method further includes:

[0024] Generate an information description file according to the MAC address of the computer network card of the purchaser, the purchaser information and the unique identifier of the three-dimensional model file;

[0025] Uploading the information description file to the smart contract to generate a directed acyclic graph representing the flow information of the three-dimensional model file;

[0026] According to the directed acyclic graph, a depth-first search is performed starting from the peer node represented by the computer that steals information to obtain all legal paths.

[0027] The present invention provides a method for protecting and tracing the rights of a three-dimensional model, including: collecting data information, wherein the data information includes a MAC address of a computer network card of a three-dimensional model rights product, and a collection of personal and / or institutional information; calculating a unique identifier of a computer that purchases the three-dimensional model rights product using a sha256 hash algorithm according to the data information; the unique identifier includes a product unique identifier and a node unique identifier; the product unique identifier is a unique identifier of the purchased three-dimensional model rights; the node unique identifier is a unique identifier of a peer node represented by a computer group of an individual and / or organization that has purchased the three-dimensional model rights; using a deep neural network invisible watermarking technology to create a deep neural network model implanted with the node unique identifier to obtain an implanted deep neural network model; using the implanted neural network model to process the three-dimensional model rights product to obtain an encrypted file; using a sha256 hash function to calculate and process according to the encrypted file and the unique identifier to obtain a hash value; encrypting the three-dimensional model rights product again to obtain a secondary encrypted three-dimensional model file; packaging the product unique identifier and the node unique identifier of the secondary encrypted three-dimensional model file and submitting them to a smart contract of an alliance chain to obtain three-dimensional model file authentication information. By exporting the circulation process information of the stolen 3D model files, the details of the stolen 3D model files can be analyzed, which is helpful for intellectual property protection.

[0028] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0030] Figure 1 A flowchart of a three-dimensional model rights protection and source tracing method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0032] The terms "comprises" and "having" and any variations thereof in the description embodiments, claims and drawings of the present invention are intended to cover non-exclusive inclusions, for example, including a series of steps or units.

[0033] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0034] like Figure 1 As shown, a method for protecting and tracing the rights of a three-dimensional model includes:

[0035] Step 100: Collecting data information, the data information includes a MAC address of a computer network card of the three-dimensional model right product, and a collection of personal and / or institutional information;

[0036] Step 200: Calculate the unique identifier of the computer that purchased the three-dimensional model rights product using the sha256 hash algorithm based on the data information;

[0037] The unique identifier includes a product unique identifier and a node unique identifier; the product unique identifier is a unique identifier of the purchased 3D model right; the node unique identifier is a unique identifier of a peer node represented by a computer group of an individual and / or organization that purchased the 3D model right;

[0038] Step 300: using a deep neural network invisible watermarking technology to create a deep neural network model implanted with the unique identifier of the node, to obtain an implanted deep neural network model;

[0039] Step 400: Processing the three-dimensional model rights product using the implanted neural network model to obtain an encrypted file;

[0040] Step 500: Calculate and process the encrypted file and the unique identifier using the sha256 hash function to obtain a hash value;

[0041] Step 600: encrypting the 3D model rights product again to obtain a secondary encrypted 3D model file;

[0042] Step 700: The product unique identifier and node unique identifier of the secondary encrypted 3D model file are packaged and submitted to the smart contract of the alliance chain to obtain the 3D model file authentication information.

[0043] After a user or organization purchases the rights to the 3D model digital product, they add their personal computer or a group of computers of the organization to the consortium chain and define each computer as a peer node in the chain.

[0044] The traceability and immutability of blockchain are used within the blockchain to ensure that the 3D model file cannot be directly copied and used. If you want to share the file, you must write the sharing information into the blockchain. Once a node is found to have infringed intellectual property rights, the path information of the file flow to that node can be exported from the blockchain. If the 3D model file is extracted by means that the blockchain cannot supervise, you can use your own deep neural network to decrypt the watermark information to prove the copyright. You can also use the incomplete flow information on the blockchain before interacting with the physical world to help maintain copyright.

[0045] The sha256 hash algorithm is used to calculate the unique identifier of the computer that purchased the three-dimensional model rights product. The input information during the calculation is the MAC address of the computer network card and the combination of personal or institutional information. The output information is a 256-bit binary random number hash value. Since the output space is large enough, it can be considered that the output is its unique identifier.

[0046] A deep neural network invisible watermarking technology in deep learning technology is used to create a deep neural network model with a backdoor implanted, and the backdoor includes a unique identifier of the peer node represented by the computer group of the individual or organization that purchased the rights to the three-dimensional model as mentioned above.

[0047] The purchased 3D model file is processed using the deep neural network embedded with the backdoor, so that the 3D model file is embedded with the purchaser's unique identifier without the purchaser knowing or seeing it, and the identifier can be decrypted by another corresponding deep neural network to obtain the backdoor information added previously.

[0048] The purchased three-dimensional model file is encrypted by a deep neural network with a backdoor and the unique identifier of the peer node represented by the computer that purchased the file is used as the input of the sha256 hash function, and the output is a 256-bit binary hash value, which is regarded as the unique identifier of the three-dimensional model right to be purchased.

[0049] The 3D model file to be purchased is encrypted again. To decrypt the encrypted file, the identity and authorization information must be verified through a smart contract. Unauthorized identities or computers not in the alliance chain cannot open the file.

[0050] The unique identifier represented by the purchased and encrypted 3D model file and the unique identifier of the peer node represented by the individual or organization that purchased the 3D model rights are packaged and submitted to the smart contract of the alliance chain. The smart contract will match the unique identifier of the individual or organization that purchased the rights with the unique identifier of the purchased 3D model file and write them into the Merkel tree. After a period of time, when the node with the bookkeeping right mines a new block, the information will be permanently written into the historical block, becoming the 3D model file authentication information that cannot be tampered with and can be traced.

[0051] When an organization or individual who purchases the rights to a 3D model product needs to share the file with other computers, the shared party must also join the alliance chain as a peer node. The purchaser needs to package the unique identifier of the file with the asymmetric encrypted public key of the computer to be shared, and sign it with his own private key to generate a description file. After that, the description file is uploaded to the smart contract, which will establish the flow information and authorize the computer represented by the shared node to open the file through smart contract authentication.

[0052] After discovering a stolen 3D model file, the unique identifier of the file can be decrypted. Through the unique identifier, the MAC address of the computer network card of the individual or organization that purchased the digital rights product and the previously written purchaser information can be queried in the smart contract.

[0053] An information description file is generated based on the MAC address of the purchaser's network card, the purchaser information and the unique identifier of the three-dimensional model file. Uploading the description file to the smart contract can generate a directed acyclic graph representing all the flow information of the file. Each node of the directed acyclic graph represents a peer node that has the right to open the file, and each directed path represents the information of the sharer and the sharee of the file.

[0054] According to the derived directed acyclic graph, a depth-first search DFS is performed starting from the peer node represented by the computer that steals the information, and all legal paths are output. Each legal path searched represents the complete flow path information of the stolen three-dimensional model file.

[0055] If it is found that the stolen file is stored in other formats or ways, it means that the file may have been leaked by screenshots or memory extraction methods, which may be an infringement. The decryption deep neural network corresponding to the encryption deep neural network with a backdoor is used to decrypt the stereoscopic model file, and the previously embedded unique identifier of the purchaser can be decrypted. The unique identifier of the purchaser and the unique identifier of the file are used to generate an information description file and upload it to the smart contract. The smart contract will export a directed acyclic graph representing the flow information of the stereoscopic model file. By parsing the directed acyclic graph, incomplete flow information before the stereoscopic model was stolen by screenshots or other methods can also be obtained.

[0056] By exporting the stolen 3D model file circulation process information, the details of the stolen 3D model file can be analyzed, which is helpful for intellectual property protection.

[0057] Beneficial effects: Blockchain technology cannot guarantee the credibility of information outside the chain. The present invention combines deep learning invisible watermark technology with blockchain technology. The three-dimensional model is embedded with an invisible watermark, and there are also tools outside the blockchain that can protect copyright, achieving double insurance. Once piracy is discovered, the copyright can be proved by decrypting the deep neural network, and an incomplete file flow roadmap can be exported in the blockchain to help copyright owners protect their rights.

[0058] The above specific implementation methods further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific implementation methods of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for protecting and tracing the rights of a three-dimensional model, characterized in that: The traceability method includes: Collecting data information, the data information including a MAC address of a computer network card of the three-dimensional model right product, and a collection of personal and / or institutional information; Calculate the unique identifier of the computer that purchased the three-dimensional model rights product using the sha256 hash algorithm based on the data information; The unique identifier includes a product unique identifier and a node unique identifier; The product unique identifier is a unique identifier of the purchased three-dimensional model right; The node unique identifier is a unique identifier of a peer node represented by a computer group of an individual and / or organization that has purchased the rights to the stereo model; Using a deep neural network invisible watermarking technology to create a deep neural network model implanted with the unique identifier of the node, to obtain an implanted deep neural network model; Processing the three-dimensional model rights product using the implanted neural network model to obtain an encrypted file; The encrypted file and the unique identifier are processed by using the sha256 hash function to obtain a hash value; encrypting the three-dimensional model right product again to obtain a secondary encrypted three-dimensional model file; The product unique identifier and node unique identifier of the secondary encrypted 3D model file are packaged and submitted to the smart contract of the alliance chain to obtain the 3D model file authentication information.

2. A three-dimensional model rights protection and source tracing method according to claim 1, characterized in that: The traceability method further comprises: When the organization and / or individual who purchases the rights to the 3D model product shares the 3D model file with other computers, the shared party must also join the alliance chain as a peer node; The purchaser packages the unique identifier of the 3D model file with the asymmetric encrypted public key of the computer to be shared, and signs the 3D model file with his own private key to generate a description file; Upload the description file to the smart contract; The smart contract will establish the circulation information and authorize the computer represented by the shared node to open the three-dimensional model file through smart contract authentication.

3. A method for protecting and tracing the rights of a three-dimensional model according to claim 1, characterized in that: The traceability method further comprises: Obtain the stolen 3D model file and decrypt the unique identifier; The computer network card MAC address of the individual and / or organization that purchased the corresponding digital rights product and the previously written purchaser information are queried in the smart contract according to the unique identifier.

4. A three-dimensional model rights protection and source tracing method according to claim 3, characterized in that: The traceability method further comprises: Generate an information description file according to the MAC address of the computer network card of the purchaser, the purchaser information and the unique identifier of the three-dimensional model file; Uploading the information description file to the smart contract to generate a directed acyclic graph representing the flow information of the three-dimensional model file; According to the directed acyclic graph, a depth-first search is performed starting from the peer node represented by the computer that steals information to obtain all legal paths.

Images