CN117560456A - Large model data leakage prevention method and system - Google Patents
Large model data leakage prevention method and system Download PDFInfo
- Publication number
- CN117560456A CN117560456A CN202410041960.6A CN202410041960A CN117560456A CN 117560456 A CN117560456 A CN 117560456A CN 202410041960 A CN202410041960 A CN 202410041960A CN 117560456 A CN117560456 A CN 117560456A
- Authority
- CN
- China
- Prior art keywords
- area
- private information
- algorithm
- private
- blurring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000002265 prevention Effects 0.000 title claims abstract description 25
- 238000003672 processing method Methods 0.000 claims abstract description 43
- 238000004590 computer program Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/44—Secrecy systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0021—Image watermarking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/32—Circuits or arrangements for control or supervision between transmitter and receiver or between image input and image output device, e.g. between a still-image camera and its memory or between a still-image camera and a printer device
- H04N1/32101—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title
- H04N1/32144—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title embedded in the image data, i.e. enclosed or integrated in the image, e.g. watermark, super-imposed logo or stamp
- H04N1/32149—Methods relating to embedding, encoding, decoding, detection or retrieval operations
- H04N1/32267—Methods relating to embedding, encoding, decoding, detection or retrieval operations combined with processing of the image
- H04N1/32272—Encryption or ciphering
Abstract
The application discloses a large model data leakage prevention method and system, which relate to the technical field of data security and comprise the following steps: and carrying out blurring processing on a plurality of private information areas in the same target image by adopting different data processing methods, generating an encrypted image, and independently generating area passwords of each private information area. Therefore, the user selectively sends the area password to the target object, the viewing authority of different private information areas of different objects is granted in the mode of the area password, and only encrypted images can be transferred or downloaded under the condition that the area password is not acquired, so that the private information of the user can be well protected.
Description
Technical Field
The invention relates to the technical field of data security, in particular to a large-model data leakage prevention method and system.
Background
With the widespread use of current chat software applications in life and work, people are using these applications more and more frequently to communicate and share information. These applications provide a convenient and quick way to send text, pictures, video and other multimedia content. However, this widespread use also presents a range of potential privacy and security concerns.
During chat, users often share private pictures containing personal and sensitive information. These pictures may include, but are not limited to, family photographs, identification documents, medical records, financial documents, and the like. Although chat software generally provides a certain level of security, private information such as private pictures may still be downloaded and forwarded by others, causing unnecessary confusion and negative impact to the parties.
Disclosure of Invention
In order to solve the technical problem that privacy information such as private pictures and the like in the prior art can still be downloaded and forwarded by other people, and unnecessary trouble and negative influence are brought to a principal, the embodiment of the invention provides a large-model data leakage prevention method and a large-model data leakage prevention system. The technical scheme is as follows:
in one aspect, a method for preventing leakage of large model data is provided, the method is implemented by large model data leakage preventing equipment, and the method includes:
s1, acquiring at least two private information areas in a target image;
s2, blurring the private information area by adopting at least two data processing methods to obtain an encrypted image;
s3, generating a region password according to the position size information of the private information region and the identification code of the reverse processing method; the reverse processing method is a reverse processing method of the data processing method.
The steps S1, S2, etc. are only step identifiers, and the execution sequence of the method is not necessarily performed in the order from small to large, for example, the step S2 may be executed first and then the step S1 may be executed, which is not limited in this application.
It can be understood that the application discloses a large model data leakage prevention method, which adopts different data processing methods to carry out blurring processing on a plurality of private information areas in the same target image, generates an encrypted image and independently generates area passwords of each private information area. Therefore, the user selectively sends the area password to the target object, the viewing authority of different private information areas of different objects is granted in the mode of the area password, and only encrypted images can be transferred or downloaded under the condition that the area password is not acquired, so that the private information of the user can be well protected.
In an alternative embodiment of the present application, S1 includes at least one of:
s11: and acquiring a target image, and regarding the selected area as a private information area aiming at the selection operation of at least two areas. It can be understood that the user can select at least two regions in the target image through selection operations such as frame selection and circling according to his own judgment, and the selected region is confirmed as the private information region.
S12: at least two character areas and/or image areas in the target image are identified, and the character areas and/or the image areas are used as private information areas. It will be appreciated that each character and image in the target image may be identified by the artificial neural network model, the region where the characters are aggregated is referred to as the character region, each image is referred to as a single image region, and the private information region in the target image may comprise at least one of:
at least two character areas;
at least two image areas;
a combination of at least one character area and at least one image area.
In step S12, at least two character areas in the target image are identified, including the steps of:
s121: identifying each character in the target image and confirming the character coordinates of each character;
s122: removing known character areas in the target image to obtain an area to be processed;
s123: randomly selecting any character in the area to be processed as a central character, and classifying the central character into a newly built clustering area;
s124: grouping other characters which are at a first distance from the center character into a newly built clustering area;
s125: continuing to divide other characters with a first distance from the edge characters of the new clustering area into the new clustering area until the characters in the new clustering area are not increased;
s126: and taking the single newly built cluster area as a single character area.
In an alternative embodiment of the present application, S2 includes at least one of:
s21: and carrying out blurring processing on each private information area by adopting different data processing methods to obtain an encrypted image, namely carrying out blurring processing on each private information area by adopting only one data processing method, wherein the data processing methods adopted by each private information area are different.
S22: and carrying out blurring processing on at least one private information area at least twice by adopting different data processing methods to obtain an encrypted image, namely, the data processing methods adopted by each blurring processing are different.
Step S21 includes the steps of:
s211: superposing the private watermark on each private information area to obtain a watermark private area;
s212: and carrying out blurring processing on each watermark private area by adopting different data blurring algorithms to obtain an encrypted image.
It can be understood that, in order to avoid the decrypted image from being disseminated, a preset private watermark is first superimposed during encryption and then subjected to fuzzification encryption processing. The watermarked watermark private area is obtained after the area password is decrypted, so that each real-time communication software can conveniently forward and intercept the picture with the private watermark, and the privacy of a picture owner is better protected.
Step S22 includes the steps of:
s221: carrying out primary blurring processing on at least one private information area by adopting a primary data blurring algorithm to obtain a primary blurring area;
s222: and carrying out secondary blurring processing on the primary blurring area and other private information areas by adopting a secondary data blurring algorithm to obtain an encrypted image.
It can be understood that the densities of different private information areas in the same target image are different, and a higher density of the private information areas can be embodied in a mode of multiple blurring processing.
Wherein, step S221 includes the following steps:
s2211: superposing the private watermark on each private information area to obtain a watermark private area;
s2212: and carrying out fuzzification processing on at least one watermark private area by adopting a primary data fuzzification algorithm to obtain a primary fuzzy area.
In an alternative embodiment of the present application, the identification code of the reverse processing method includes at least one of:
the code is used for identifying a defuzzification algorithm, and the defuzzification algorithm is a reverse algorithm of the data fuzzification algorithm and is used for restoring the area after fuzzification into a private information area;
the code is used for identifying a primary defuzzification algorithm, wherein the primary defuzzification algorithm is a reverse algorithm of the primary data defuzzification algorithm and is used for restoring the primary fuzzy area into a private information area;
the code is used for identifying a secondary defuzzification algorithm, wherein the secondary defuzzification algorithm is a reverse algorithm of the secondary data defuzzification algorithm and is used for restoring the area subjected to secondary fuzzification processing into a primary fuzzy area.
It can be understood that the data obfuscation algorithm, the defuzzation algorithm and the corresponding identification codes can be stored in a query table, and when the obfuscation processing is performed, a certain data obfuscation algorithm can be randomly selected from the query table to perform the obfuscation processing, and meanwhile, the identification code corresponding to the data obfuscation algorithm is used as a part of elements for generating the region password. In addition, the primary data fuzzification algorithm, the primary defuzzification algorithm, the secondary data fuzzification algorithm, the secondary defuzzification algorithm and the corresponding identification codes can also be stored in the query table for carrying out multiple fuzzification processing.
In an alternative embodiment of the present application, the location size information includes a first coordinate of the private information area and a length and a width of the private information area; the first coordinates are coordinates of the first pixel in the first row and first column in the private information area.
In another aspect, the present application provides a large model data leakage prevention system comprising a processor, an input device, an output device, and a memory, the processor, the input device, the output device, and the memory being interconnected, wherein the memory is for storing a computer program, the computer program comprising program instructions, the processor being configured to invoke the program instructions to perform a method as in any of the first aspects.
In another aspect, there is provided a large-model data leakage preventing apparatus including: a processor; a memory having stored thereon computer readable instructions which, when executed by the processor, implement any of the large model data leakage prevention methods described above.
In another aspect, a computer readable storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement any of the above large model data leakage prevention methods is provided.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
the application discloses a large model data leakage prevention method, which adopts different data processing methods to carry out blurring processing on a plurality of private information areas in the same target image, generates an encrypted image and independently generates area passwords of all the private information areas. Therefore, the user selectively sends the area password to the target object, the viewing authority of different private information areas of different objects is granted in the mode of the area password, and only encrypted images can be transferred or downloaded under the condition that the area password is not acquired, so that the private information of the user can be well protected.
In order to avoid the decrypted image from being spread in a flooding way, a preset private watermark is firstly overlapped during encryption, and then fuzzy encryption processing is carried out. The watermarked watermark private area is obtained after the area password is decrypted, so that each real-time communication software can conveniently forward and intercept the picture with the private watermark, and the privacy of a picture owner is better protected. In addition, the densities of different private information areas in the same target image are different, and the higher density of the private information areas can be embodied in a mode of multiple blurring processing.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a process for blurring a private information area provided herein;
FIG. 2 is a schematic diagram of another blurring process for a private information area provided herein;
FIG. 3 is a schematic diagram of the image result obtained by reversing the encrypted image shown in FIG. 2;
FIG. 4 is a schematic diagram of a blurring process for a private information area provided herein;
FIG. 5 is a schematic diagram of an image result obtained by performing a reverse process of the secondary blurring process on the encrypted image shown in FIG. 2;
fig. 6 is a schematic structural diagram of a large-model data leakage prevention system provided in the present application.
Detailed Description
The technical scheme of the invention is described below with reference to the accompanying drawings.
In embodiments of the invention, words such as "exemplary," "such as" and the like are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the term use of an example is intended to present concepts in a concrete fashion. Furthermore, in embodiments of the present invention, the meaning of "and/or" may be that of both, or may be that of either, optionally one of both.
In the embodiments of the present invention, "image" and "picture" may be sometimes used in combination, and it should be noted that the meaning of the expression is consistent when the distinction is not emphasized. "of", "corresponding" and "corresponding" are sometimes used in combination, and it should be noted that the meaning of the expression is consistent when the distinction is not emphasized.
In the embodiment of the present invention, sometimes a subscript such as W1 may be wrongly expressed in a non-subscript form such as W1, and the meaning of the subscript is consistent when the distinction is not emphasized.
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.
The embodiment of the invention provides a large model data leakage prevention method which can be realized by large model data leakage prevention equipment, wherein the large model data leakage prevention equipment can be a terminal or a server. The flow chart of the large model data leakage prevention method shown in fig. 1, the processing flow of the method can comprise the following steps:
s1, acquiring at least two private information areas in a target image.
The target image is the private picture containing the personal information and the sensitive information, such as a family photo, an identification document, a medical record, a financial document and the like.
There may be multiple private information areas in the same target image, and the target image 100 shown in fig. 1 is an identity card picture, and includes a basic information area 101, an ID number area 102 and a head portrait area 103, where the basic information area 101, the ID number area 102 belong to a character area, and the head portrait area 103 belongs to an image area.
S2, blurring processing is carried out on at least two private information areas by adopting at least two data processing methods, and an encrypted image is obtained.
The data processing method comprises a data blurring algorithm, wherein the data blurring algorithm is used for recalculating and updating the color values of all pixels in the private information area through a formula combination, and the whole private information area is blurred due to updating of the color values of the pixels, so that a final encrypted image is obtained.
One of the data obfuscation algorithms may include, for example:
；
；
；
wherein,a red color value representing an i-th pixel of the private information area after blurring, and +.>A green color value representing an i-th pixel of the private information area after blurring processing,/and a method for producing the same>Blue color value of i-th pixel after blurring process representing private information area,/and>red color value representing the i-th pixel in the private information area, < >>A green color value representing the i-th pixel in the private information area,/or->Representing the blue color value of the ith pixel in the private information area.
S3, generating a region password according to the position size information of the private information region and the identification code of the reverse processing method of the data processing method.
In an alternative embodiment of the present application, the location size information includes a first coordinate of the private information area and a length and a width of the private information area; the first coordinates are coordinates of the first pixel in the first row and first column in the private information area.
The reverse processing method comprises a reverse processing method of a data blurring algorithm, and is used for carrying out reduction processing on each pixel and reducing the blurred area into a private information area. The data obfuscation algorithm, the defuzzification algorithm, and the corresponding identification codes may be stored in a lookup table, and when the private information area is restored, the corresponding defuzzification algorithm may be queried from the lookup table according to the identification codes to restore the private information area.
The steps S1, S2, etc. are only step identifiers, and the execution sequence of the method is not necessarily performed in the order from small to large, for example, the step S2 may be executed first and then the step S1 may be executed, which is not limited in this application.
It can be understood that the application discloses a large model data leakage prevention method, which adopts different data processing methods to carry out blurring processing on a plurality of private information areas in the same target image, generates an encrypted image and independently generates area passwords of each private information area. Therefore, the user selectively sends the area password to the target object, the viewing authority of different private information areas of different objects is granted in the mode of the area password, and only encrypted images can be transferred or downloaded under the condition that the area password is not acquired, so that the private information of the user can be well protected.
In an alternative embodiment of the present application, S1 includes at least one of:
s11: and responding to the selection operation of at least two areas, and taking the selected area as a private information area. It can be understood that the user can select at least two regions in the target image through selection operations such as frame selection and circling according to his own judgment, and the selected region is confirmed as the private information region.
S12: at least two character areas and/or image areas in the target image are identified, and the character areas and/or the image areas are used as private information areas. It will be appreciated that each character and image in the target image may be identified by the artificial neural network model, the region where the characters are aggregated is referred to as the character region, each image is referred to as a single image region, and the private information region in the target image may comprise at least one of:
at least two character areas;
at least two image areas;
a combination of at least one character area and at least one image area.
In step S12, at least two character areas in the target image are identified, including the steps of:
s121: each character in the target image is identified, and the character coordinates of each character are confirmed.
S122: and removing the known character area in the target image to obtain the area to be processed.
Steps S122 to S126 are a circulation process, and a new cluster area can be obtained in each circulation, and the main purpose of step S122 is to remove the newly-established cluster area determined last time, and obtain the area to be processed in the present circulation.
S123: randomly selecting any character in the area to be processed as a central character, and classifying the central character into a newly built cluster area.
S124: other characters that are a first distance from the center character are also classified into the newly created cluster region.
S125: and continuing to divide other characters which are separated from the edge characters of the new clustering area by a first distance into the new clustering area until the characters in the new clustering area are not increased.
S126: and taking the single newly built cluster area as a single character area.
After steps S123 to S125 are performed on the area to be processed, the entire new cluster area is obtained, and the new cluster area is used as a single character area. The target image 100 shown in fig. 1 is an identification card picture, and includes two character areas, namely a basic information area 101 and an ID number area 102.
In an alternative embodiment of the present application, S2 includes at least one of the following steps S21 and S22.
S21: and carrying out blurring processing on each private information area by adopting different data processing methods to obtain an encrypted image, namely carrying out blurring processing on each private information area by adopting only one data processing method, wherein the data processing methods adopted by each private information area are different. The target image shown in fig. 1 includes 3 private information areas, which are respectively subjected to blurring processing by three different data processing methods, the basic information area 101 is subjected to blurring processing by a first processing method to obtain a first blurring area 201, the id number area 102 is subjected to blurring processing by a second processing method to obtain a second blurring area 202, and the head portrait area 103 is subjected to blurring processing by a third processing method to obtain a third blurring area 203, so as to finally obtain the encrypted image 200.
Alternatively, step S21 may include the steps of:
s211: and superposing the private watermark on each private information area to obtain a watermark private area.
The target image 110 as shown in fig. 2 includes 3 private information areas: before the basic information area 111, the ID number area 112 and the header area 113 blur the respective private information areas, it is necessary to superimpose a private watermark on each private information area to obtain a first watermark private area 211, a second watermark private area 212 and a third watermark private area 213.
S212: and carrying out blurring processing on each watermark private area by adopting different data blurring algorithms to obtain an encrypted image.
With continued reference to fig. 2, after the watermarks are superimposed, the three watermark privacy regions are respectively subjected to blurring processing, the first watermark privacy region 211 is subjected to blurring processing by a first processing method to obtain a first blurred region 301, the second watermark privacy region 212 is subjected to blurring processing by a second processing method to obtain a second blurred region 302, the third watermark privacy region 213 is subjected to blurring processing by a third processing method to obtain a third blurred region 303, and finally the encrypted image 300 is obtained.
It can be understood that, in order to avoid the decrypted image from being disseminated, a preset private watermark is first superimposed during encryption and then subjected to fuzzification encryption processing. The watermarked watermark private area is obtained after the decryption of the area password, as shown in fig. 3, so that each real-time communication software can conveniently forward and intercept the picture with the private watermark, and the privacy of the picture owner is better protected.
S22: and carrying out blurring processing on at least one private information area at least twice by adopting different data processing methods to obtain an encrypted image, namely, the data processing methods adopted by each blurring processing are different. Step S22 specifically includes at least one of step S221 and step S222.
S221: and carrying out primary blurring processing on at least one private information area by adopting a primary data blurring algorithm to obtain a primary blurring area.
The target image 130 as shown in fig. 4 includes 3 private information areas: the basic information area 131, the ID number area 132, and the header area 133 are higher in the density of the ID number area 132, and thus the primary blurring area 400 is obtained by selecting the ID number area 132 and performing primary blurring processing.
S222: and carrying out secondary blurring processing on the primary blurring area and other private information areas by adopting a secondary data blurring algorithm to obtain an encrypted image.
With continued reference to fig. 4, the primary blurring area 400 and the other two private areas 131 and 133 are subjected to secondary blurring processing by adopting the same secondary data blurring algorithm, so as to obtain a secondary blurring area 502, a basic information blurring area 501 and a head portrait blurring area 503, respectively, and finally obtain an encrypted image 500.
It can be understood that the densities of different private information areas in the same target image are different, and a higher density of the private information areas can be embodied in a mode of multiple blurring processing. When the encrypted image 500 is processed by the reverse algorithm of the two-stage data blurring algorithm, only the picture shown in fig. 5 can be obtained, wherein the ID number area is still in a blurred state, and the encrypted image can be clearly obtained by the reverse algorithm of the one-stage data blurring algorithm.
Wherein, step S221 includes the following steps:
s2211: superposing the private watermark on each private information area to obtain a watermark private area;
s2212: and carrying out fuzzification processing on at least one watermark private area by adopting a primary data fuzzification algorithm to obtain a primary fuzzy area.
In an alternative embodiment of the present application, the identification code of the reverse processing method includes at least one of:
the code is used for identifying a defuzzification algorithm, and the defuzzification algorithm is a reverse algorithm of the data fuzzification algorithm and is used for restoring the area after fuzzification into a private information area;
the code is used for identifying a primary defuzzification algorithm, wherein the primary defuzzification algorithm is a reverse algorithm of the primary data defuzzification algorithm and is used for restoring the primary fuzzy area into a private information area;
the code is used for identifying a secondary defuzzification algorithm, wherein the secondary defuzzification algorithm is a reverse algorithm of the secondary data defuzzification algorithm and is used for restoring the area subjected to secondary fuzzification processing into a primary fuzzy area.
It can be understood that the data obfuscation algorithm, the defuzzation algorithm and the corresponding identification codes can be stored in a query table, and when the obfuscation processing is performed, a certain data obfuscation algorithm can be randomly selected from the query table to perform the obfuscation processing, and meanwhile, the identification code corresponding to the data obfuscation algorithm is used as a part of elements for generating the region password. In addition, the primary data fuzzification algorithm, the primary defuzzification algorithm, the secondary data fuzzification algorithm, the secondary defuzzification algorithm and the corresponding identification codes can also be stored in the query table for carrying out multiple fuzzification processing.
In the embodiment of the invention, different data processing methods are adopted to carry out blurring processing on a plurality of private information areas in the same target image, an encrypted image is generated, and the area passwords of the private information areas are independently generated. Therefore, the user selectively sends the area password to the target object, the viewing authority of different private information areas of different objects is granted in the mode of the area password, and only encrypted images can be transferred or downloaded under the condition that the area password is not acquired, so that the private information of the user can be well protected.
FIG. 6 is a block diagram of a large model data leakage prevention system for a large model data leakage prevention method, according to an example embodiment. As shown in fig. 6, the large model data leakage prevention system includes one or more processors 601; one or more input devices 602, one or more output devices 603, and a memory 604. The processor 601, input device 602, output device 603, and memory 604 are connected by a bus 605. The memory 604 is used for storing a computer program comprising program instructions, and the processor 601 is used for executing the program instructions stored in the memory 604. Wherein the processor 601 is configured to invoke the program instructions to perform the operations of any of the methods of the first aspect.
It should be appreciated that in embodiments of the present invention, the processor 601 may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 602 may include a touch display, a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of a fingerprint), a microphone, etc., and the output device 603 may include a display (LCD, etc.), a speaker, etc.
The memory 604 may include read only memory and random access memory and provides instructions and data to the processor 601. A portion of memory 604 may also include non-volatile random access memory. For example, the memory 604 may also store information of device type.
In a specific implementation, the processor 601, the input device 602, and the output device 603 described in the embodiments of the present invention may perform an implementation described by any of the methods of the first aspect, or may perform an implementation of the terminal device described in the embodiments of the present invention, which is not described herein again.
It is to be appreciated that the processor 601 in embodiments of the present invention may be a central processing unit (central processing unit, CPU) that may also be other general purpose processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits (application specific integrated circuit, ASIC), off-the-shelf programmable gate arrays (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It should also be appreciated that the memory in embodiments of the present invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example but not limitation, many forms of random access memory (random access memory, RAM) are available, such as Static RAM (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced Synchronous Dynamic Random Access Memory (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM).
The above embodiments may be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable system. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. In addition, the character "/" herein generally indicates that the associated object is an "or" relationship, but may also indicate an "and/or" relationship, and may be understood by referring to the context.
In the present invention, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus, system and unit described above may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, system, and method may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple elements or components may be combined or integrated into another device, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, system or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The large model data leakage prevention method is characterized by comprising the following steps of:
s1, acquiring at least two private information areas in a target image;
s2, blurring processing is carried out on the private information area by adopting at least two data processing methods, and an encrypted image is obtained;
s3, generating a region password according to the position size information of the private information region and the identification code of the reverse processing method; the reverse processing method is a reverse processing method of the data processing method.
2. The method for preventing leakage of large model data according to claim 1, wherein,
the S1 comprises at least one of the following:
s11: acquiring a target image, and aiming at the selection operation of at least two areas, taking the selected areas as private information areas;
s12: and identifying at least two character areas and/or image areas in the target image, and taking the character areas and/or the image areas as private information areas.
3. The large model data leakage prevention method according to claim 2, wherein,
the identifying at least two character areas in the target image comprises the following steps:
s121: identifying each character in the target image and confirming the character coordinates of each character;
s122: removing known character areas in the target image to obtain an area to be processed;
s123: randomly selecting any character in the area to be processed as a central character, and classifying the central character into a newly built clustering area;
s124: other characters which are separated from the center character by a first distance are also classified into the newly-built clustering area;
s125: continuing to classify other characters which are separated from the edge characters of the new clustering area by the first distance into the new clustering area until the characters in the new clustering area are not increased;
s126: and taking the single newly built cluster area as a single character area.
4. The method for preventing leakage of large model data according to claim 1, wherein,
the S2 comprises at least one of the following:
s21: carrying out blurring processing on each private information area by adopting different data processing methods to obtain an encrypted image;
s22: and carrying out blurring processing at least twice on at least one private information area by adopting different data processing methods to obtain an encrypted image.
5. The method for preventing leakage of large model data according to claim 4, wherein,
the step S21 comprises the following steps:
s211: superposing a private watermark on each private information area to obtain a watermark private area;
s212: and carrying out blurring processing on each watermark private area by adopting different data blurring algorithms to obtain an encrypted image.
6. The method for preventing leakage of large model data according to claim 5, wherein,
the step S22 includes the steps of:
s221: carrying out primary blurring processing on at least one private information area by adopting a primary data blurring algorithm to obtain a primary blurring area;
s222: and carrying out secondary blurring processing on the primary blurring area and the other private information areas by adopting a secondary data blurring algorithm to obtain an encrypted image.
7. The method for preventing leakage of large model data according to claim 6, wherein,
the step S221 includes the steps of:
s2211: superposing a private watermark on each private information area to obtain a watermark private area;
s2212: and carrying out fuzzification processing on at least one watermark private area by adopting a primary data fuzzification algorithm to obtain a primary fuzzy area.
8. The method for large model data leakage prevention according to any one of claims 6 to 7, wherein,
the identification code of the reverse processing method comprises at least one of the following:
code for identifying a defuzzification algorithm, the defuzzification algorithm being a reverse algorithm of the data obfuscation algorithm for restoring the obfuscated region to the private information region;
the code is used for identifying a primary defuzzification algorithm, wherein the primary defuzzification algorithm is a reverse algorithm of the primary data defuzzification algorithm and is used for restoring a primary fuzzy area into the private information area;
the code is used for identifying a secondary defuzzification algorithm, wherein the secondary defuzzification algorithm is a reverse algorithm of the secondary data defuzzification algorithm and is used for restoring the area subjected to secondary fuzzification processing into the primary fuzzy area.
9. The large model data leakage prevention method according to any one of claims 1 to 7, wherein,
the position size information comprises the initial coordinates of the private information area, and the length and the width of the private information area;
the first coordinates are coordinates of first pixels located in the first row and the first column in the private information area.
10. A large model data leakage prevention system is characterized in that,
comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is adapted to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method according to any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410041960.6A CN117560456A (en) | 2024-01-11 | 2024-01-11 | Large model data leakage prevention method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410041960.6A CN117560456A (en) | 2024-01-11 | 2024-01-11 | Large model data leakage prevention method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117560456A true CN117560456A (en) | 2024-02-13 |
Family
ID=89823613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410041960.6A Pending CN117560456A (en) | 2024-01-11 | 2024-01-11 | Large model data leakage prevention method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117560456A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019192397A1 (en) * | 2018-04-04 | 2019-10-10 | 华中科技大学 | End-to-end recognition method for scene text in any shape |
| CN112653713A (en) * | 2021-01-22 | 2021-04-13 | 深圳市房多多网络科技有限公司 | Image downloading protection method and device and computing equipment |
| CN114390316A (en) * | 2021-12-27 | 2022-04-22 | 深圳瑞德博智信息技术有限公司 | Processing method and device for image acquisition synchronous encryption privacy protection |
| CN115665341A (en) * | 2022-11-14 | 2023-01-31 | 北京佳芯信息科技有限公司 | Encryption method and encryption system for image data |
-
2024
- 2024-01-11 CN CN202410041960.6A patent/CN117560456A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019192397A1 (en) * | 2018-04-04 | 2019-10-10 | 华中科技大学 | End-to-end recognition method for scene text in any shape |
| CN112653713A (en) * | 2021-01-22 | 2021-04-13 | 深圳市房多多网络科技有限公司 | Image downloading protection method and device and computing equipment |
| CN114390316A (en) * | 2021-12-27 | 2022-04-22 | 深圳瑞德博智信息技术有限公司 | Processing method and device for image acquisition synchronous encryption privacy protection |
| CN115665341A (en) * | 2022-11-14 | 2023-01-31 | 北京佳芯信息科技有限公司 | Encryption method and encryption system for image data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11157646B2 (en) | Systems and methods for processing and handling privacy-sensitive image data | |
| Agrawal et al. | Person de-identification in videos | |
| Azeez et al. | Design a system for an approved video copyright over cloud based on biometric iris and random walk generator using watermark technique | |
| US20210211291A1 (en) | Registration and verification of biometric modalities using encryption techniques in a deep neural network | |
| WO2016188154A1 (en) | Method and device for image processing | |
| CN111814194B (en) | Image processing method and device based on privacy protection and electronic equipment | |
| Taspinar et al. | PRNU-based camera attribution from multiple seam-carved images | |
| Singh et al. | Watmif: Multimodal medical image fusion-based watermarking for telehealth applications | |
| Pal et al. | Weighted matrix based reversible watermarking scheme using color image | |
| CN112214773A (en) | Image processing method and device based on privacy protection and electronic equipment | |
| CN115841413A (en) | Image processing method and device | |
| JP5248934B2 (en) | Method and apparatus for exercising video processing rights | |
| AlEisa | Data confidentiality in healthcare monitoring systems based on image steganography to improve the exchange of patient information using the internet of things | |
| Kukreja et al. | Copyright protection scheme for color images using extended visual cryptography | |
| CN117560456A (en) | Large model data leakage prevention method and system | |
| CN109672804B (en) | Image encryption and decryption method and system | |
| CN115952529A (en) | User data processing method, computing device and storage medium | |
| KR102551230B1 (en) | Masking processing system and method for automatically masking and unmasking surveillance camera images in real time using deep learning object information | |
| CN109800590A (en) | A kind of rectangular digital image three dimensional symmetry encryption method | |
| TWI740145B (en) | Method, electrical device, and computer program product for hiding information and protecting privacy of video | |
| CN114422651B (en) | Image information hiding method, tracing method, hiding device and tracing device | |
| Abbas et al. | Sanitization of Visual Multimedia Content: A Survey of Techniques, Attacks, and Future Directions | |
| CN111968023B (en) | Dual-image reversible data hiding method based on EMD matrix | |
| CN116453173B (en) | Picture processing method based on picture region segmentation technology | |
| Muttaqi et al. | A new data hiding method for protecting bigger secret data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |