A method, device, medium and electronic device for protecting vehicle-side privacy data

Abstract

The present application discloses a method, device, medium and electronic device for protecting vehicle-side privacy data, which obtains the vehicle-side data of a target vehicle; identifies the privacy data and the corresponding privacy type in the vehicle-side data based on an aggregated data group of the vehicle-side data; wherein the aggregated data group represents a cluster containing the vehicle-side data; if the privacy type is vehicle speed or mileage, anonymizes the privacy data using a salted hash function and an XOR operation; that is, after obtaining the vehicle-side data, cluster analysis is performed on the vehicle-side data to improve the recognition accuracy of a single privacy data, and anonymizes the privacy data using a salted hash function and an XOR operation, thereby maximizing the efficiency of privacy data processing while ensuring the security of privacy protection, that is, taking into account both the processing efficiency and security performance of smart vehicle privacy data.

Description

Technical Field

[0001] The present application relates to the technical field of privacy protection of vehicle-side data, and specifically to a method, device, medium and electronic device for protecting vehicle-side privacy data. Background Art

[0002] With the continuous development of smart cars and digital technology, smart cars can collect and process a large amount of data during driving, including driving environment, vehicle performance, driver behavior, etc. The collection of this data is conducive to improving vehicle performance, driving safety and passenger comfort, but it also poses serious privacy and data protection issues.

[0003] In order to protect the privacy of vehicle-side data, there are solutions for protecting vehicle-side data in the prior art. However, most of these protection measures are simple anonymization or traditional encryption technology. Anonymization can be reverse engineered with sufficient auxiliary information, and traditional encryption technology may not be efficiently applied in real-time data processing. Therefore, there is an urgent need for a comprehensive technical solution that can balance the efficiency of intelligent vehicle data processing and privacy security. Summary of the invention

[0004] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a method, device, medium and electronic device for protecting vehicle-side privacy data.

[0005] According to one aspect of the present application, a method for protecting vehicle-side privacy data is provided, comprising: obtaining vehicle-side data of a target vehicle; identifying privacy data and corresponding privacy types in the vehicle-side data based on an aggregated data group of the vehicle-side data; wherein the aggregated data group represents a cluster containing the vehicle-side data; if the privacy type is vehicle speed or mileage, anonymizing the privacy data using a salted hash function and an XOR operation; wherein the formula for the anonymization processing is:

[0006] ;

[0007] in, is the private data, It is the data after anonymization. by is the salt value, is the salted hash function of the argument, is a key-based hash message authentication code function, According to the data item The salt value is dynamically generated based on the sensitivity level and application frequency. Is related to data item The associated key value, is generated using a keyed hash function or a pseudo-random function with the data item Related dynamic masks, Represents the exclusive-or operation.

[0008] In one embodiment, the vehicle-side privacy data protection method further includes:

[0009] If the privacy type is image data, a convolutional neural network is used to identify sensitive areas in the image data and the sensitivity of the sensitive areas;

[0010] Based on the sensitive areas and sensitivities in the image data, a Gaussian fuzzy function is used to perform fuzzy processing on the privacy data; wherein the fuzzy processing formula is:

[0011] ;

[0012] in, is the original image, is the processed image, The deep learning model is based on the sensitivity The generated sensitive area mask, is the Gaussian blur function, is the standard deviation dynamically adjusted according to the sensitive area, Represents element-wise multiplication.

[0013] In one embodiment, the calculation method of the standard deviation of the sensitive area includes:

[0014] ;

[0015] in, is the information entropy feature extraction function, and is a tuning parameter.

[0016] In one embodiment, the blurring the privacy data using a Gaussian blur function based on the sensitive area and sensitivity in the image data includes:

[0017] Based on the sensitive areas and sensitivities in the image data, an edge-preserving filter function is used to perform bilateral filtering on the image data; wherein the formula for the bilateral filtering is:

[0018] ;

[0019] in, is the original image, is the diameter of the bilateral filter, is the standard deviation of the color space, is the standard deviation of the coordinate space, is the bilateral filter function, is the image processed by the bilateral filter;

[0020] The privacy data after bilateral filtering is fuzzified using a Gaussian fuzzy function; wherein the fuzzy processing formula is:

[0021] .

[0022] In one embodiment, the vehicle-side privacy data protection method further includes:

[0023] If the privacy type is location data, a differential privacy algorithm is used to desensitize the privacy data; wherein the desensitization formula is:

[0024] ;

[0025] in, is the original position data, It is the location data after desensitization. is the scale parameter Laplace distributed random noise with scale parameter Based on the sensitive areas and sensitivity settings of location data.

[0026] In one embodiment, the vehicle-side privacy data protection method further includes:

[0027] If the privacy type is location data, identifying sensitive areas in the location data;

[0028] The encryption function is used to encrypt the sensitive area in the positioning data; wherein the encryption formula is:

[0029] ;

[0030] in, It is the location data of sensitive areas. is the encrypted positioning data. is the encryption function, It is a security key.

[0031] According to another aspect of the present application, a device for protecting vehicle-side privacy data is provided, comprising: a vehicle-side data acquisition module, used to acquire vehicle-side data of a target vehicle; a privacy type identification module, used to identify privacy data and corresponding privacy types in the vehicle-side data based on an aggregated data group of the vehicle-side data; wherein the aggregated data group represents a cluster containing the vehicle-side data; and a privacy data processing module, used to anonymize the privacy data by using a salted hash function and an XOR operation if the privacy type is vehicle speed or mileage; wherein the anonymization processing formula is:

[0032] ;

[0033] in, is the private data, It is the data after anonymization. by is the salt value, is the salted hash function of the argument, is a key-based hash message authentication code function, According to the data item The salt value is dynamically generated based on the sensitivity level and application frequency. Is related to the data item The associated key value, is generated using a keyed hash function or a pseudo-random function with the data item Related dynamic masks, Represents the exclusive-or operation.

[0034] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute any of the above-mentioned vehicle-side privacy data protection methods.

[0035] According to another aspect of the present application, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor is used to execute any of the above-mentioned vehicle-side privacy data protection methods.

[0036] The present application provides a method, device, medium and electronic device for protecting vehicle-side privacy data, which obtains the vehicle-side data of the target vehicle; identifies the privacy data and the corresponding privacy type in the vehicle-side data based on the aggregated data group of the vehicle-side data; wherein the aggregated data group represents a cluster containing the vehicle-side data; if the privacy type is vehicle speed or mileage, the privacy data is anonymized by using a salted hash function and an XOR operation; that is, after obtaining the vehicle-side data, cluster analysis is performed on the vehicle-side data to improve the recognition accuracy of a single privacy data, and the privacy data is anonymized by using a salted hash function and an XOR operation on the vehicle speed and mileage data, thereby maximizing the efficiency of privacy data processing while ensuring the security of privacy protection, that is, taking into account both the processing efficiency and safety performance of smart vehicle privacy data. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0038] Figure 1 It is a flowchart of a method for protecting vehicle-side privacy data provided by an exemplary embodiment of the present application.

[0039] Figure 2 It is a structural diagram of a vehicle-side privacy data protection device provided by an exemplary embodiment of the present application.

[0040] Figure 3 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0041] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0042] Figure 1 FIG. 1 is a flow chart of a method for protecting vehicle-side privacy data provided by an exemplary embodiment of the present application. Figure 1 As shown, the method for protecting the privacy data of the vehicle side includes the following steps:

[0043] Step 110: Obtain vehicle-side data of the target vehicle.

[0044] Since the smart vehicle (target vehicle) needs to continuously collect environmental data, vehicle status information, navigation data, etc. on the driving path, the smart vehicle will be equipped with various sensors to collect the above data in real time. The sensors of the target vehicle of this application process the vehicle-side data after collecting it in real time to protect the privacy data.

[0045] Step 120: Based on the aggregated data group of the vehicle-side data, identify the privacy data and the corresponding privacy type in the vehicle-side data.

[0046] Among them, the aggregated data group represents a cluster containing vehicle-side data. After acquiring the vehicle-side data, the present application identifies the vehicle-side data to determine the privacy data in the vehicle-side data, that is, determines the data in the vehicle-side data that needs to be processed for privacy protection. Specifically, the present application clusters and divides the vehicle-side data based on the data aggregation strategy to obtain multiple vehicle-side data of the same category, thereby realizing the classification of the vehicle-side data to reduce the risk of misidentification during individual identification. Optionally, the present application can also use distributed representation coding to encode the vehicle-side data (privacy data) to further protect the privacy data.

[0047] Step 130: If the privacy type is vehicle speed or mileage, the private data is anonymized using a salted hash function and an XOR operation.

[0048] The anonymization formula is:

[0049] ;

[0050] in, It is private data. It is the data after anonymization. by is the salt value, is the salted hash function of the argument, is a key-based hash message authentication code function, According to the data item The salt value is dynamically generated based on the sensitivity level and application frequency. Is related to data item The associated key value, is generated using a keyed hash function or a pseudo-random function with the data item Related dynamic masks, Represents XOR operation

[0051] This application anonymizes the vehicle speed, mileage and other data in the vehicle-side data by setting up a data desensitization module, and specifically uses enhanced hashing technology and data perturbation algorithm to anonymize the privacy data to protect the privacy data. Specifically, this application introduces a dynamic salting strategy and a mask generation algorithm, where the dynamic salting strategy refers to dynamically changing the salt value according to factors such as the type of data, sensitivity level, and application frequency, and the mask is no longer static, but is dynamically generated using a keyed hash function or a pseudo-random function (PRF) with a high correlation with the data item.

[0052] The present application provides a method for protecting vehicle-side privacy data, which obtains the vehicle-side data of a target vehicle; based on an aggregated data group of the vehicle-side data, identifies the privacy data and the corresponding privacy type in the vehicle-side data; wherein the aggregated data group represents a cluster containing the vehicle-side data; if the privacy type is vehicle speed or mileage, the privacy data is anonymized by using a salted hash function and an XOR operation; that is, after obtaining the vehicle-side data, a cluster analysis is performed on the vehicle-side data to improve the recognition accuracy of a single privacy data, and the privacy data is anonymized by using a salted hash function and an XOR operation on the vehicle speed and mileage data, thereby maximizing the efficiency of privacy data processing while ensuring the security of privacy protection, that is, taking into account both the processing efficiency and safety performance of smart vehicle privacy data.

[0053] In one embodiment, the specific implementation of step 130 may be:

[0054] If the privacy type is image data, a convolutional neural network is used to identify sensitive areas and the sensitivity of sensitive areas in the image data. Based on the sensitive areas and sensitivity in the image data, a Gaussian fuzzy function is used to fuzzify the privacy data. The fuzzification formula is:

[0055] ;

[0056] in, is the original image, is the processed image, The deep learning model is based on the sensitivity The generated sensitive area mask, is the Gaussian blur function, is the standard deviation dynamically adjusted according to the sensitive area, Represents element-wise multiplication.

[0057] When the target vehicle is driving, cameras or other devices may collect relevant image data in real time, including vehicle images of other vehicles, facial information of pedestrians, and facial information of people in the vehicle. In order to avoid the leakage of private image data, especially private areas in image data (such as license plate areas in vehicle images), this application first uses a convolutional neural network to identify sensitive areas in the image data and the sensitivity of sensitive areas; then, based on the sensitive areas and corresponding sensitivities, the privacy data (image data of sensitive areas) is blurred to obtain blurred image data of sensitive areas, thereby achieving privacy protection for sensitive images. Specifically, this application uses deep learning to identify sensitive information in images (such as faces, license plates, etc.), such as a convolutional neural network (CNN) in conjunction with an attention mechanism. The convolutional neural network outputs a mask of the sensitive area. and the corresponding sensitivity :

[0058] .

[0059] In one embodiment, the calculation method of the standard deviation of the sensitive area includes:

[0060] ;

[0061] in, is the information entropy feature extraction function, and is a tuning parameter.

[0062] For the identified sensitive areas, according to the corresponding sensitivity Dynamically adjust Gaussian blur standard deviation ,The specific calculation method can be based on the characteristics of the sensitive ,region, such as information entropy or other related feature extraction ,functions.

[0063] In one embodiment, the specific method of using the Gaussian fuzzy function to fuzzify the privacy data may be:

[0064] Based on the sensitive areas and sensitivities in the image data, the image data is subjected to bilateral filtering using an edge-preserving filtering function; the formula for bilateral filtering is:

[0065] ;

[0066] in, is the original image, is the diameter of the bilateral filter, is the standard deviation of the color space, is the standard deviation in coordinate space, is the bilateral filter function, is the image processed by the bilateral filter;

[0067] This application applies different degrees of blur to areas of different sensitivities, uses edge-preserving filtering technology for non-sensitive areas to maintain image quality, and uses bilateral filtering to process images to ensure the quality of non-sensitive areas of the image while appropriately blurring sensitive areas, thereby achieving the purpose of protecting privacy.

[0068] The Gaussian fuzzy function is used to fuzzify the privacy data after bilateral filtering. The fuzzy processing formula is:

[0069] .

[0070] The present application retains the edges of sensitive areas and non-sensitive areas after bilateral filtering of the original image, and then uses a high-speed blur function to blur the sensitive areas and non-sensitive areas respectively, so as to appropriately blur the sensitive areas while ensuring the quality of the non-sensitive areas of the image.

[0071] In one embodiment, the specific implementation of step 130 may be:

[0072] If the privacy type is location data, the differential privacy algorithm is used to desensitize the privacy data; the desensitization formula is:

[0073] ;

[0074] in, is the original position data, It is the location data after desensitization. is the scale parameter Laplace distributed random noise with scale parameter Based on the sensitive areas and sensitivity settings of location data.

[0075] Specifically, this application uses geo-fencing technology to define sensitive areas In order to simplify the model, this application sets the sensitive area as a circular or polygonal fence. For the non-sensitive area, a basic scale parameter is set ; For sensitive areas, set a higher scale parameter , to provide a higher level of privacy. For each location data point , depending on whether it is located in a sensitive area Select the corresponding :

[0076] ;

[0077] Desensitized location data :

[0078]

[0079] in, According to the selected Parameters Random noise generated from a Laplace distribution.

[0080] In one embodiment, the specific implementation of step 130 may be:

[0081] If the privacy type is location data, the sensitive area in the location data is identified; the encryption function is used to encrypt the sensitive area in the location data; wherein the encryption formula is:

[0082] ;

[0083] in, It is the location data of sensitive areas. is the encrypted positioning data. is the encryption function, It is a security key.

[0084] Specifically, this application uses specific identification and encryption technology for confidential positioning data, where the identification formula is: ;in, is the positioning data to be identified, Indicates a directory of confidential geographic locations. is the identification function. For each real confidential area Add random noise to create a blurred area , and create a fake confidential area , the fake confidential area does not contain any real sensitive information. and Included in the obfuscated confidential geographic information directory ,make sure In addition to the location information, it does not contain any other attributes. For each image or point cloud data point , extract its spatial coordinates And check if the point is in the sensitive area fence Inside:

[0085]

[0086] The positioning data collected by the vehicle is analyzed to confirm whether it contains information about confidential areas. , using a more complex spatial analysis algorithm to determine whether it is classified information:

[0087]

[0088] For data points identified as containing confidential information , apply the encryption function to these data points:

[0089] ;

[0090] in, is an encryption algorithm, such as AES, and is a predefined security key.

[0091] Encrypted data It needs to be transmitted through a secure communication protocol and kept in a secure storage environment to ensure end-to-end data security.

[0092] Optionally, the present application may also utilize the Elliptic Curve Diffie-Hellman (ECDH) algorithm for secure key exchange. The calculation formula is: ;in, is Party A's private key, is Party B’s public key, is the elliptic curve key exchange function.

[0093] Optionally, the present application may also use a permission verification algorithm and a key management protocol to authorize users to access data. Further, a multi-layer identity authentication mechanism may be used, including but not limited to passwords, biometrics, and security tokens.

[0094] Optionally, the present application may also periodically evaluate and clean up the stored data, using a deletion policy decision algorithm to determine which data needs to be cleared.

[0095] Optionally, the application can also educate users on data protection and privacy policies, including evaluation algorithms for knowledge transfer efficiency and comprehension.

[0096] Figure 2 Schematic diagram of the structure of a vehicle-side privacy data protection device provided by an exemplary embodiment of the present application. Figure 2 As shown, the vehicle-side privacy data protection device 20 includes: a vehicle-side data acquisition module 21, used to acquire the vehicle-side data of the target vehicle; a privacy type identification module 22, used to identify the privacy data and the corresponding privacy type in the vehicle-side data based on the aggregated data group of the vehicle-side data; wherein the aggregated data group represents a cluster containing the vehicle-side data; a privacy data processing module 23, used to anonymize the privacy data by using a salted hash function and an XOR operation if the privacy type is vehicle speed or mileage; wherein the anonymization processing formula is:

[0097] ;

[0098] in, It is private data. It is the data after anonymization. by is the salt value, is the salted hash function of the argument, is a key-based hash message authentication code function, According to the data item The salt value is dynamically generated based on the sensitivity level and application frequency. Is related to the data item The associated key value, is generated using a keyed hash function or a pseudo-random function with the data item Related dynamic masks, Represents the exclusive-or operation.

[0099] The present application provides a vehicle-side privacy data protection device, which acquires the vehicle-side data of the target vehicle through the vehicle-side data acquisition module 21; the privacy type identification module 22 identifies the privacy data and the corresponding privacy type in the vehicle-side data based on the aggregated data group of the vehicle-side data; wherein the aggregated data group represents the cluster containing the vehicle-side data; if the privacy type is vehicle speed or mileage, the privacy data processing module 23 uses a salted hash function and an XOR operation to anonymize the privacy data; that is, after acquiring the vehicle-side data, a cluster analysis is performed on the vehicle-side data to improve the recognition accuracy of a single privacy data, and the vehicle speed and mileage data are anonymized using a salted hash function and an XOR operation to anonymize the privacy data, thereby maximizing the efficiency of privacy data processing while ensuring the security of privacy protection, that is, taking into account both the processing efficiency and safety performance of the privacy data of smart vehicles.

[0100] In one embodiment, the privacy data processing module 23 may be further configured as follows:

[0101] If the privacy type is image data, a convolutional neural network is used to identify sensitive areas in the image data and the sensitivity of the sensitive areas;

[0102] Based on the sensitive areas and sensitivity in the image data, the Gaussian fuzzy function is used to fuzzify the privacy data; the fuzzy processing formula is:

[0103] ;

[0104] in, is the original image, is the processed image, The deep learning model is based on the sensitivity The generated sensitive area mask, is the Gaussian blur function, is the standard deviation dynamically adjusted according to the sensitive area, Represents element-wise multiplication.

[0105] In one embodiment, the calculation method of the standard deviation of the sensitive area includes:

[0106] ;

[0107] in, is the information entropy feature extraction function, and is a tuning parameter.

[0108] In one embodiment, the privacy data processing module 23 may be further configured as follows:

[0109] Based on the sensitive areas and sensitivities in the image data, the image data is subjected to bilateral filtering using an edge-preserving filtering function; the formula for bilateral filtering is:

[0110] ;

[0111] in, is the original image, is the diameter of the bilateral filter, is the standard deviation of the color space, is the standard deviation in coordinate space, is the bilateral filter function, is the image processed by the bilateral filter;

[0112] The Gaussian fuzzy function is used to fuzzify the privacy data after bilateral filtering. The fuzzy processing formula is:

[0113] .

[0114] In one embodiment, the privacy data processing module 23 may be further configured as follows:

[0115] If the privacy type is location data, the differential privacy algorithm is used to desensitize the privacy data; the desensitization formula is:

[0116] ;

[0117] in, is the original position data, It is the location data after desensitization. is the scale parameter Laplace distributed random noise with scale parameter Based on the sensitive areas and sensitivity settings of location data.

[0118] In one embodiment, the privacy data processing module 23 may be further configured as follows:

[0119] If the privacy type is location data, identify sensitive areas in the location data;

[0120] The encryption function is used to encrypt the sensitive areas in the positioning data; the encryption formula is:

[0121] ;

[0122] in, It is the location data of sensitive areas. is the encrypted positioning data. is the encryption function, It is a security key.

[0123] Below, reference Figure 3 The electronic device according to the embodiment of the present application is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signal from them.

[0124] Figure 3 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0125] like Figure 3 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0126] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0127] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the methods of the various embodiments of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0128] In one example, the electronic device 10 may further include: an input device 13 and an output device 14 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0129] When the electronic device is a stand-alone device, the input device 13 may be a communication network connector, which is used to receive the collected input signals from the first device and the second device.

[0130] In addition, the input device 13 may also include, for example, a keyboard, a mouse, and the like.

[0131] The output device 14 can output various information to the outside, including the determined distance information, direction information, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0132] Of course, to simplify, Figure 3 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0133] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0134] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0135] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0136] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0137] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0138] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0139] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0140] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0141] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for protecting vehicle-side privacy data, characterized in that: include: Obtain vehicle-side data of the target vehicle; Based on the aggregated data group of the vehicle-side data, identifying the privacy data and the corresponding privacy type in the vehicle-side data; wherein the aggregated data group represents a cluster containing the vehicle-side data; If the privacy type is vehicle speed or mileage, the private data is anonymized using a salted hash function and an XOR operation; wherein the anonymization formula is: ； in, is the private data, It is the data after anonymization. So is the salt value, is the salted hash function of the argument, is a key-based hash message authentication code function, According to the data item The salt value is dynamically generated based on the sensitivity level and application frequency. Is related to data item The associated key value, is generated using a keyed hash function or a pseudo-random function with the data item Related dynamic masks, Represents XOR operation; If the privacy type is image data, a convolutional neural network is used to identify sensitive areas in the image data and the sensitivity of the sensitive areas; Based on the sensitive areas and sensitivities in the image data, a Gaussian fuzzy function is used to perform fuzzy processing on the privacy data; wherein the fuzzy processing formula is: ； in, is the original image, is the processed image, The deep learning model is based on the sensitivity The generated sensitive area mask, is the Gaussian blur function, is the standard deviation dynamically adjusted according to the sensitive area, Represents element-wise multiplication.

2. The method for protecting vehicle-side privacy data according to claim 1, characterized in that: The calculation method of the standard deviation of the sensitive area includes: ； in, is the information entropy feature extraction function, and is a tuning parameter.

3. The method for protecting vehicle-side privacy data according to claim 1, characterized in that: The using a Gaussian fuzzy function to perform fuzzy processing on the privacy data based on the sensitive area and sensitivity in the image data includes: Based on the sensitive areas and sensitivities in the image data, an edge-preserving filter function is used to perform bilateral filtering on the image data; wherein the formula for the bilateral filtering is: ； in, is the original image, is the diameter of the bilateral filter, is the standard deviation of the color space, is the standard deviation in coordinate space, is the bilateral filter function, is the image processed by the bilateral filter; The privacy data after bilateral filtering is fuzzified using a Gaussian fuzzy function; wherein the fuzzy processing formula is: 。 4. The method for protecting vehicle-side privacy data according to claim 1, characterized in that: The vehicle-side privacy data protection method further includes: If the privacy type is location data, a differential privacy algorithm is used to desensitize the privacy data; wherein the desensitization formula is: ； in, is the original position data, It is the location data after desensitization. is the scale parameter Laplace distributed random noise with scale parameter Based on the sensitive areas and sensitivity settings of location data.

5. The method for protecting vehicle-side privacy data according to claim 1, characterized in that: The vehicle-side privacy data protection method further includes: If the privacy type is location data, identifying sensitive areas in the location data; The encryption function is used to encrypt the sensitive area in the positioning data; wherein the encryption formula is: ； in, It is the location data of sensitive areas. is the encrypted positioning data. is the encryption function, It is a security key.

6. A device for protecting private data on a vehicle, characterized in that: include: A vehicle-side data acquisition module is used to acquire vehicle-side data of a target vehicle; A privacy type identification module, configured to identify the privacy data and the corresponding privacy type in the vehicle-side data based on the aggregated data group of the vehicle-side data; wherein the aggregated data group represents a cluster containing the vehicle-side data; The privacy data processing module is used to anonymize the privacy data by using a salted hash function and an XOR operation if the privacy type is vehicle speed or mileage; wherein the anonymization formula is: ； in, is the private data, It is the data after anonymization. by is the salt value, is the salted hash function of the argument, is a key-based hash message authentication code function, According to the data item The salt value is dynamically generated based on the sensitivity level and application frequency. Is related to the data item The associated key value, is generated using a keyed hash function or a pseudo-random function with the data item Related dynamic masks, Represents XOR operation; The privacy data processing module is further configured as follows: If the privacy type is image data, a convolutional neural network is used to identify sensitive areas in the image data and the sensitivity of the sensitive areas; Based on the sensitive areas and sensitivities in the image data, a Gaussian fuzzy function is used to perform fuzzy processing on the privacy data; wherein the fuzzy processing formula is: ； in, is the original image, is the processed image, The deep learning model is based on the sensitivity The generated sensitive area mask, is the Gaussian blur function, is the standard deviation dynamically adjusted according to the sensitive area, Represents element-wise multiplication.

7. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the vehicle-side privacy data protection method described in any one of claims 1-5 above.

8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the vehicle-side privacy data protection method described in any one of claims 1-5 above.

Images