A vehicle-cloud video data desensitization method and device based on quantum information security

Abstract

The application provides a vehicle-cloud video data desensitization method and device based on quantum information security, which comprises the following steps: when a target system collects a video and performs image perception on the video, sensitive information in the video is synchronously identified, a desensitization layer is generated based on the sensitive information, the desensitization layer is bound and encrypted with the corresponding video through a preset quantum password to form an encrypted video, and the encrypted video is transmitted to a cabin control unit; the cabin control unit responds to a viewing request of a local user, performs quantum password decryption on the received encrypted video according to the quantum password, and sends the video to the cloud or the local.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a method and apparatus for desensitizing vehicle-to-cloud video data based on quantum information security. Background Technology

[0002] The principle of vehicle data anonymization is to anonymize / de-identify sensitive information outside the vehicle (faces, license plates, etc.). This is significant in protecting personal privacy, mitigating compliance risks, ensuring security, and simultaneously unlocking data value. Among these, video from inside and outside the vehicle is the core of data anonymization, including external images / videos and internal audio / video.

[0003] Currently, video desensitization is usually performed at the data sending end, such as the cockpit control unit and TBOX, that is, before the video data is uploaded to the cloud.

[0004] However, existing video anonymization methods require anonymization before video data is uploaded to the cloud, resulting in redundant anonymization work and generally low data anonymization processing efficiency. Furthermore, intelligent driving systems often require anonymization, while cockpit systems require displaying unanonymized data, necessitating the transmission of multiple videos and leading to high data resource consumption. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a vehicle cloud video data desensitization method and device based on quantum information security. By performing video data desensitization processing at the video generation end, i.e., during intelligent driving or cockpit system perception and recognition, there is no need to perform desensitization again when uploading to the cloud, which improves the desensitization efficiency. In addition, by identifying sensitive information to generate a desensitization layer, and binding the desensitization layer as a separate masking layer with the original video through quantum encryption for transmission, the data resource consumption is reduced.

[0006] In a first aspect, embodiments of this application provide a method for de-identifying vehicle-to-cloud video data based on quantum information security, the method comprising: When the target system acquires video and performs image perception on the video, it simultaneously identifies sensitive information in the video and generates a desensitized layer based on the sensitive information. The desensitized layer is bound and encrypted with the corresponding video using a preset quantum cryptography to form an encrypted video, which is then transmitted to the cockpit control unit; wherein, the target system is an intelligent driving system or a cockpit system; In response to a local user's viewing request, the cockpit control unit performs quantum cryptographic decryption of the received encrypted video according to the quantum cryptography and sends it to the cloud or local device.

[0007] In one possible implementation, the step of synchronously identifying sensitive information in the video and generating a desensitized layer based on the sensitive information includes: During the image perception process of the video, the target system analyzes the semantic features of the video in real time and performs desensitization recognition when it detects that the current video frame contains a face region or a license plate region. A pixel-level desensitized layer is generated on the face area or the license plate area.

[0008] In one possible implementation, the step of binding and encrypting the desensitized layer with the corresponding video using a preset quantum cryptography to form an encrypted video includes: Quantum cryptography is invoked to generate a binding key by using the hash value of the video and the hash value of the desensitized layer as key derivation inputs. The encryption operation is performed on the de-identified layer using the binding key, and the encrypted de-identified layer is packaged with the video in a fixed encapsulation format to form the encrypted video.

[0009] In one possible implementation, the step of performing quantum cryptographic decryption of the received encrypted video according to the quantum cryptography and sending it to the cloud or local storage includes: Determine whether the viewing request is a request to watch an anonymized video; If the viewing request is for viewing an anonymized video, then the received encrypted video is decrypted using quantum cryptography and sent to the cloud. If the viewing request is not a request to view a de-identified video, then the received encrypted video is decrypted using quantum cryptography to obtain a de-identified layer, and the de-identified layer is hidden. The video without the de-identified layer is then output to the local device for the user to view.

[0010] In one possible implementation, the step of performing quantum cryptographic decryption of the received encrypted video using the quantum cryptography and sending it to the cloud includes: The received encrypted video is decrypted using quantum cryptography to obtain the desensitized layer and the corresponding video. The desensitized layer is superimposed pixel by pixel onto the corresponding area of ​​the video to obtain the merged desensitized external video, and the desensitized external video is uploaded to the cloud address specified in the viewing request.

[0011] In one possible implementation, the step of de-identifying and uploading the video to the cloud address specified in the viewing request includes: The de-identified outgoing video is sent to the smart gateway and packaged based on a preset information security policy to obtain a de-identified outgoing video security package; Upload the desensitized video security package to the cloud address specified in the viewing request.

[0012] In one possible implementation, the method further includes: After receiving the viewing request through the cockpit control unit, the video category identifier and target cloud address carried in the viewing request are parsed. When it is confirmed that the video category corresponding to the viewing request belongs to the target video category based on the video category identifier and the target cloud address, the received encrypted video is decrypted using quantum cryptography and then sent.

[0013] Secondly, embodiments of this application also provide a vehicle-to-cloud video data anonymization device based on quantum information security, the device comprising: The generation module is used to simultaneously identify sensitive information in the video when the target system acquires the video and performs image perception on the video, and generate a desensitized layer based on the sensitive information; wherein the target system is an intelligent driving system or a cockpit system; The encryption module is used to bind and encrypt the desensitized layer with the corresponding video using a preset quantum cryptography to form an encrypted video, and then transmit the encrypted video to the cockpit control unit. The sending module is used to respond to the viewing request of the local user through the cockpit control unit, perform quantum cryptographic decryption on the received encrypted video according to the quantum cryptography, and send it to the cloud or local device.

[0014] In one possible implementation, the generation module is specifically used for: During the image perception process of the video, the target system analyzes the semantic features of the video in real time and performs desensitization recognition when it detects that the current video frame contains a face region or a license plate region. A pixel-level desensitized layer is generated on the face area or the license plate area.

[0015] In one possible implementation, the encryption module is specifically used for: Quantum cryptography is invoked to generate a binding key by using the hash value of the video and the hash value of the desensitized layer as key derivation inputs. The encryption operation is performed on the de-identified layer using the binding key, and the encrypted de-identified layer is packaged with the video in a fixed encapsulation format to form the encrypted video.

[0016] In one possible implementation, the sending module is specifically used for: Determine whether the viewing request is a request to watch an anonymized video; If the viewing request is for viewing an anonymized video, then the received encrypted video is decrypted using quantum cryptography and sent to the cloud. If the viewing request is not a request to view a de-identified video, then the received encrypted video is decrypted using quantum cryptography to obtain a de-identified layer, and the de-identified layer is hidden. The video without the de-identified layer is then output to the local device for the user to view.

[0017] In one possible implementation, the sending module is specifically used for: The received encrypted video is decrypted using quantum cryptography to obtain the desensitized layer and the corresponding video. The desensitized layer is superimposed pixel by pixel onto the corresponding area of ​​the video to obtain the merged desensitized external video, and the desensitized external video is uploaded to the cloud address specified in the viewing request.

[0018] In one possible implementation, the sending module is specifically used for: The de-identified outgoing video is sent to the smart gateway and packaged based on a preset information security policy to obtain a de-identified outgoing video security package; Upload the desensitized video security package to the cloud address specified in the viewing request.

[0019] In one possible implementation, the device further includes: The parsing module is used to parse the video category identifier and target cloud address carried in the viewing request after receiving the viewing request through the cockpit control unit; The confirmation module is used to perform quantum cryptographic decryption of the received encrypted video and send it back when it is confirmed that the video category corresponding to the viewing request belongs to the target video category based on the video category identifier and the target cloud address.

[0020] Thirdly, embodiments of this application provide an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the vehicle-to-cloud video data desensitization method based on quantum information security as described in any of the first aspects.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the vehicle-to-cloud video data desensitization method based on quantum information security as described in any one of the first aspects.

[0022] This application provides a vehicle-to-cloud video data anonymization method and apparatus based on quantum information security. When a target system acquires video and performs image perception on the video, it simultaneously identifies sensitive information in the video and generates an anonymized layer based on this sensitive information. The anonymized layer is then bound and encrypted with the corresponding video using a preset quantum cryptography, forming an encrypted video. This encrypted video is transmitted to the cockpit control unit. In response to a local user's viewing request, the cockpit control unit decrypts the received encrypted video using quantum cryptography and sends it to the cloud or local machine. This application improves anonymization efficiency by performing video data anonymization at the video generation point (i.e., during intelligent driving or cockpit system perception and recognition), eliminating the need for anonymization during cloud upload. Furthermore, by generating an anonymized layer based on identified sensitive information and binding it as a separate masking layer with the original video via quantum encryption during transmission, data resource consumption is reduced.

[0023] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a vehicle-to-cloud video data anonymization method based on quantum information security provided in the embodiments of this application; Figure 2 This is a schematic diagram of the overall process of the vehicle-cloud video data anonymization method; Figure 3 This is a schematic diagram of the structure of a vehicle-to-cloud video data desensitization device based on quantum information security, provided in an embodiment of this application. Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0027] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0028] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0029] The principle of data anonymization in the automotive industry is to anonymize / de-identify sensitive information outside the vehicle (faces, license plates, etc.). This is significant for protecting personal privacy, mitigating compliance risks, ensuring security, and simultaneously unlocking data value. Among these, videos inside and outside the vehicle are the core of data anonymization, including external images / videos and internal audio / video.

[0030] Currently, video desensitization is usually performed at the data sending end, such as the cockpit control unit and TBOX, that is, before the video data is uploaded to the cloud.

[0031] However, existing video anonymization methods require anonymization before video data is uploaded to the cloud, resulting in redundant anonymization work and generally low data anonymization processing efficiency. Furthermore, intelligent driving systems often require anonymization, while cockpit systems require displaying unanonymized data, necessitating the transmission of multiple videos and leading to high data resource consumption.

[0032] To address this issue, this application provides a vehicle-to-cloud video data anonymization method and apparatus based on quantum information security. By performing video data anonymization at the video generation end, i.e., during intelligent driving or cockpit system perception and recognition, the anonymization process is eliminated during cloud upload, thus improving anonymization efficiency. In addition, by identifying sensitive information to generate an anonymized layer, and binding the anonymized layer as a separate masking layer with the original video through quantum encryption for transmission, the data resource consumption is reduced.

[0033] Figure 1 This is a flowchart of a vehicle-to-cloud video data anonymization method based on quantum information security, provided in an embodiment of this application. For example... Figure 1 As shown in the embodiments of this application, the vehicle-to-cloud video data anonymization method based on quantum information security may specifically include: S101. When acquiring video through the target system and performing image perception on the video, simultaneously identify sensitive information in the video and generate a desensitization layer based on the sensitive information.

[0034] S102. The desensitized layer is bound and encrypted with the corresponding video using a preset quantum cryptography to form an encrypted video, and the encrypted video is transmitted to the cockpit control unit.

[0035] S103, responding to the local user's viewing request through the cockpit control unit, performs quantum cryptography decryption on the received encrypted video according to quantum cryptography and sends it to the cloud or local device.

[0036] In the aforementioned vehicle-to-cloud video data anonymization method based on quantum information security, video data anonymization is performed at the video generation end, i.e., during intelligent driving or cockpit system perception and recognition, eliminating the need for anonymization during cloud upload and improving anonymization efficiency. In addition, an anonymized layer is generated by identifying sensitive information, and this anonymized layer is bound to the original video as a separate masking layer and transmitted via quantum encryption, reducing data resource consumption.

[0037] The exemplary steps described above in the embodiments of this application are illustrated below with specific examples: S101, when the target system acquires video and performs image perception on the video, it simultaneously identifies sensitive information in the video and generates a desensitized layer based on the sensitive information.

[0038] It should be noted that the target system is the intelligent driving system and the cockpit system. That is, the vehicle cloud video data anonymization based on quantum information security in this application is applied to the target system and the cockpit system. This application uses the intelligent driving system as an example for description, and the same applies to the cockpit system.

[0039] In this embodiment, the sensitive information includes at least facial information and license plate information. When the target system acquires video and performs image perception on the video, it simultaneously identifies the sensitive information in the video and generates a desensitized layer based on the sensitive information for subsequent processing. For example, such as Figure 2 As shown, the intelligent driving system acquires video A and obtains sensitive information through image perception to generate layer m.

[0040] It should be noted that the desensitized layers are generated based on the sensitive information and correspond one-to-one with the spatial location of the video (layer-by-layer correspondence).

[0041] Optionally, during the image perception process of the video, the target system analyzes the semantic features of the video in real time and performs desensitization recognition when the current video frame detects that it contains a face region or license plate region; a pixel-level desensitization layer is generated over the face region or license plate region. The coordinate position, size, and transparency parameters of the desensitization layer are strictly aligned with the corresponding area in the original video.

[0042] S102 binds and encrypts the desensitized layer with the corresponding video using a preset quantum cryptography to form an encrypted video, and then transmits the encrypted video to the cockpit control unit.

[0043] In this embodiment, the desensitized layer generated in step S101 is bound and encrypted with the corresponding video (video frame) using quantum cryptography (e.g., PQC or QKD) to form an encrypted video, which is then transmitted to the cockpit control unit for subsequent processing. For example, as Figure 2 As shown, layer m and the original video are superimposed with quantum cryptography encryption to form video B, i.e., the encrypted video.

[0044] Optionally, quantum cryptography is invoked to generate a binding key by using the hash value of the video and the hash value of the desensitized layer as key derivation inputs; the binding key is used to perform encryption operations on the desensitized layer, and the encrypted desensitized layer and the video are packaged in a fixed encapsulation format to form an encrypted video.

[0045] It should be noted that after encryption, the desensitized layer can be stored and moved along with the video, for example, moved to the cockpit.

[0046] Therefore, while performing video perception (related to intelligent driving), the target system, upon determining that the video needs to be uploaded to the cloud, simultaneously perceives sensitive information (such as facial features and license plates) and applies a desensitization layer. This desensitization layer is then encrypted using quantum cryptography at the end of video generation. The use of quantum cryptography ensures that the layer is not misused and that the connection between the layer and the original video is not easily broken.

[0047] S103 responds to local users' viewing requests via the cockpit control unit by performing quantum cryptography decryption on the received encrypted video and sending it to the cloud or local device.

[0048] In this embodiment, the user generates a viewing request by watching video through a recorder, surround view, etc. The viewing request indicates a request to watch either a non-anonymized or anonymized video. When watching anonymized video, the request is sent to the cloud; when watching non-anonymized video, the request is sent locally. The cockpit control unit receives the user's viewing request locally, performs quantum cryptography decryption on the received encrypted video using quantum cryptography, and matches the viewing request to send it to the cloud or local machine. For example, ... Figure 2 As shown.

[0049] In some implementations, it is determined whether the viewing request is for viewing a de-identified video. If the viewing request is for viewing a de-identified video, the received encrypted video is decrypted using quantum cryptography and sent to the cloud. If the viewing request is not for viewing a de-identified video, the received encrypted video is decrypted using quantum cryptography to obtain a de-identified layer, and the de-identified layer is hidden. The video without the overlaid de-identified layer is then output to the local device for the user to view.

[0050] Optionally, when performing quantum cryptography decryption on the received encrypted video and sending it to the cloud, the received encrypted video is decrypted using quantum cryptography to obtain a desensitized layer and the corresponding video; the desensitized layer is then overlaid pixel-by-pixel onto the corresponding area of ​​the video to obtain the merged desensitized outgoing video, which is then uploaded to the cloud address specified in the viewing request. For example, as... Figure 2 As shown, the layers are unlocked using quantum cryptography, merged, and a desensitized video C is generated for external distribution.

[0051] Optionally, when sending the de-identified video to the cloud address specified in the viewing request, the de-identified video is sent to the smart gateway (TBOX, Telematics-BOX) and packaged according to the preset information security policy to obtain a de-identified video security package; the de-identified video security package is then uploaded to the cloud address specified in the viewing request.

[0052] It should be noted that when hiding the desensitized layer, you can make a local copy of the desensitized layer and provide prompts and permission handling.

[0053] Therefore, when it is necessary to send videos externally, the data is decrypted and the layers and videos are merged. In this way, the de-identified videos can be uploaded to the cloud along with the communication terminal without the need to run a separate de-identification program and software.

[0054] The vehicle-to-cloud video data anonymization method based on quantum information security provided in this application involves simultaneously identifying sensitive information in a video acquired by a target system and performing image perception on the video. An anonymization layer is generated based on this sensitive information, and the anonymization layer is bound and encrypted with the corresponding video using a preset quantum cryptography to form an encrypted video. This encrypted video is then transmitted to the cockpit control unit. In response to a local user's viewing request, the cockpit control unit decrypts the received encrypted video using quantum cryptography and sends it to the cloud or local storage. This quantum information security-based vehicle-to-cloud video data anonymization method performs video data anonymization at the video generation end—i.e., during intelligent driving or cockpit system perception and recognition—eliminating the need for anonymization during cloud upload, thus improving anonymization efficiency. Furthermore, by generating an anonymization layer based on identified sensitive information and binding it as a separate masking layer with the original video via quantum encryption during transmission, data resource consumption is reduced.

[0055] Furthermore, after receiving a viewing request through the cockpit control unit, the system parses the video category identifier and target cloud address carried in the viewing request; when it is confirmed that the video category corresponding to the viewing request belongs to the target video category based on the video category identifier and target cloud address, the system performs quantum cryptography decryption on the received encrypted video and sends it.

[0056] The target video categories include at least intelligent driving training sample videos and driver status monitoring videos.

[0057] Furthermore, after the encrypted video is generated, it is written to the isolated storage area within the Trusted Execution Environment (TEE) and its data source is marked as the target system. A data ready notification with a digital signature is sent to the cockpit control unit via the vehicle bus. After the cockpit control unit verifies the signature, the encrypted video is read from the isolated storage area using DMA.

[0058] Figure 3 This is a schematic diagram of the structure of a vehicle-to-cloud video data anonymization device based on quantum information security, according to an embodiment of this application; as shown below. Figure 3 As shown in the figure, the vehicle-to-cloud video data anonymization device 300 based on quantum information security in this application embodiment may specifically include: The generation module 301 is used to simultaneously identify sensitive information in the video when the target system acquires video and performs image perception on the video, and generate a desensitized layer based on the sensitive information; wherein the target system is an intelligent driving system or a cockpit system.

[0059] The encryption module 302 is used to bind and encrypt the desensitized layer with the corresponding video using a preset quantum cryptography to form an encrypted video, and then transmit the encrypted video to the cockpit control unit.

[0060] The sending module 303 is used to respond to the viewing request of the local user through the cockpit control unit, perform quantum cryptography decryption on the received encrypted video according to quantum cryptography, and send it to the cloud or local device.

[0061] In one possible implementation, the generation module is specifically used for: During the image perception process of the video, the target system analyzes the semantic features of the video in real time and performs desensitization recognition when it detects that the current video frame contains a face region or a license plate region. Generate pixel-level desensitized layers over the face or license plate area.

[0062] In one possible implementation, the encryption module is specifically used for: Quantum cryptography uses the hash value of the video and the hash value of the desensitized layer as key derivation inputs to generate a binding key; The desensitized layer is encrypted using a binding key, and the encrypted desensitized layer and the video are packaged together in a fixed encapsulation format to form an encrypted video.

[0063] In one possible implementation, the sending module is specifically used for: Determine whether the viewing request is for viewing an anonymized video; If the viewing request is for viewing an anonymized video, then the received encrypted video will be decrypted using quantum cryptography and sent to the cloud. If the viewing request is not for viewing the de-identified video, then the received encrypted video is decrypted using quantum cryptography to obtain the de-identified layer, which is then hidden. The video without the de-identified layer is then output to the local device for the user to view.

[0064] In one possible implementation, the sending module is specifically used for: The received encrypted video is decrypted using quantum cryptography to obtain the desensitized layer and the corresponding video. The desensitized layer is superimposed pixel by pixel onto the corresponding area of ​​the video to obtain the merged desensitized video for external distribution. The desensitized video for external distribution is then uploaded to the cloud address specified by the viewing request.

[0065] In one possible implementation, the sending module is specifically used for: The anonymized video is sent to the smart gateway and packaged according to the preset information security policy to obtain the anonymized video security package. Upload the desensitized video security package to the cloud address specified by the viewing request.

[0066] In one possible implementation, the apparatus further includes: The parsing module is used to parse the video category identifier and target cloud address carried in the viewing request after receiving the viewing request through the cockpit control unit. The confirmation module is used to confirm that the video category corresponding to the viewing request belongs to the target video category based on the video category identifier and the target cloud address. Then, it performs quantum cryptography decryption on the received encrypted video and sends it back.

[0067] The vehicle-to-cloud video data desensitization device based on quantum information security provided in this application identifies sensitive information in the video simultaneously when the target system acquires video and performs image perception. A desensitization layer is generated based on this sensitive information, and the desensitization layer is bound and encrypted with the corresponding video using a preset quantum cryptography to form an encrypted video. This encrypted video is then transmitted to the cockpit control unit. In response to a local user's viewing request, the cockpit control unit decrypts the received encrypted video using quantum cryptography and sends it to the cloud or local machine. This vehicle-to-cloud video data desensitization device performs video data desensitization at the video generation point—i.e., during intelligent driving or cockpit system perception and recognition—eliminating the need for desensitization during cloud upload, thus improving desensitization efficiency. Furthermore, by generating a desensitization layer by identifying sensitive information and binding it as a separate masking layer with the original video via quantum encryption during transmission, data resource consumption is reduced.

[0068] like Figure 4 As shown in the embodiment of this application, an electronic device 400 includes a processor 401, a memory 402, and a bus. The memory 402 stores machine-readable instructions executable by the processor 401. When the electronic device is running, the processor 401 communicates with the memory 402 via the bus. The processor 401 executes the machine-readable instructions to perform the steps of the above-described vehicle-to-cloud video data desensitization method based on quantum information security.

[0069] Specifically, the memory 402 and processor 401 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 401 runs the computer program stored in the memory 402, it can execute the above-mentioned vehicle-to-cloud video data desensitization method based on quantum information security.

[0070] Corresponding to the above-mentioned vehicle-to-cloud video data anonymization method based on quantum information security, this application embodiment also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the above-mentioned vehicle-to-cloud video data anonymization method based on quantum information security.

[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0072] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0073] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0074] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the deployment methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0075] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for de-identifying vehicle-to-cloud video data based on quantum information security, characterized in that, The method includes: When acquiring video through the target system and performing image perception on the video, sensitive information in the video is identified simultaneously, and a desensitization layer is generated based on the sensitive information; wherein, the target system is an intelligent driving system or a cockpit system; The desensitized layer is bound and encrypted with the corresponding video using a preset quantum cryptography to form an encrypted video, which is then transmitted to the cockpit control unit. In response to a local user's viewing request, the cockpit control unit performs quantum cryptographic decryption of the received encrypted video according to the quantum cryptography and sends it to the cloud or local device.

2. The method according to claim 1, characterized in that, The step of synchronously identifying sensitive information in the video and generating a desensitized layer based on the sensitive information includes: During the image perception process of the video, the target system analyzes the semantic features of the video in real time and performs desensitization recognition when it detects that the current video frame contains a face region or a license plate region. A pixel-level desensitized layer is generated on the face area or the license plate area.

3. The method according to claim 1, characterized in that, The step of binding and encrypting the desensitized layer with the corresponding video using a preset quantum cryptography to form an encrypted video includes: Quantum cryptography is invoked to generate a binding key by using the hash value of the video and the hash value of the desensitized layer as key derivation inputs. The encryption operation is performed on the de-identified layer using the binding key, and the encrypted de-identified layer is packaged with the video in a fixed encapsulation format to form the encrypted video.

4. The method according to claim 1, characterized in that, The step of performing quantum cryptographic decryption of the received encrypted video according to the quantum cryptography and sending it to the cloud or local machine includes: Determine whether the viewing request is a request to watch an anonymized video; If the viewing request is for viewing an anonymized video, then the received encrypted video is decrypted using quantum cryptography and sent to the cloud. If the viewing request is not a request to view a de-identified video, then the received encrypted video is decrypted using quantum cryptography to obtain a de-identified layer, and the de-identified layer is hidden. The video without the de-identified layer is then output to the local device for the user to view.

5. The method according to claim 4, characterized in that, The process of performing quantum cryptographic decryption on the received encrypted video and sending it to the cloud using the quantum cryptography includes: The received encrypted video is decrypted using quantum cryptography to obtain the desensitized layer and the corresponding video. The desensitized layer is superimposed pixel by pixel onto the corresponding area of ​​the video to obtain the merged desensitized external video, and the desensitized external video is uploaded to the cloud address specified in the viewing request.

6. The method according to claim 5, characterized in that, The step of de-identifying and sending the video externally and uploading it to the cloud address specified in the viewing request includes: The de-identified outgoing video is sent to the smart gateway and packaged based on a preset information security policy to obtain a de-identified outgoing video security package; Upload the desensitized video security package to the cloud address specified in the viewing request.

7. The method according to claim 1, characterized in that, The method further includes: After receiving the viewing request through the cockpit control unit, the video category identifier and target cloud address carried in the viewing request are parsed. When it is confirmed that the video category corresponding to the viewing request belongs to the target video category based on the video category identifier and the target cloud address, the received encrypted video is decrypted using quantum cryptography and then sent.

8. A vehicle-to-cloud video data anonymization device based on quantum information security, characterized in that, The device includes: The generation module is used to simultaneously identify sensitive information in the video when the target system acquires the video and performs image perception on the video, and generate a desensitized layer based on the sensitive information; wherein the target system is an intelligent driving system or a cockpit system; The encryption module is used to bind and encrypt the desensitized layer with the corresponding video using a preset quantum cryptography to form an encrypted video, and then transmit the encrypted video to the cockpit control unit. The sending module is used to respond to the viewing request of the local user through the cockpit control unit, perform quantum cryptographic decryption on the received encrypted video according to the quantum cryptography, and send it to the cloud or local device.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the vehicle-to-cloud video data desensitization method based on quantum information security as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the vehicle-to-cloud video data desensitization method based on quantum information security as described in any one of claims 1 to 7.

Images