Civil aviation passenger sensitive personal information leakage verification method, system, device and medium
By introducing AI-based sensitive information recognition technology into the data desensitization system, using deep learning algorithms and recurrent neural network models to identify and evaluate the leakage risks of sensitive personal information of civil aviation passengers, the shortcomings of traditional methods in identifying and processing non-formatted data are solved, and more efficient and accurate data leakage verification is achieved.
Patent Information
- Application Number
- CN202411908239.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-23
- Publication Date
- 2025-04-18
AI Technical Summary
Traditional data desensitization protection measures based on regular expressions cannot effectively identify and process sensitive information in non-formatted data, especially in symmetric encryption and encoded data, making it difficult to ensure that the leakage of sensitive personal information of civil aviation passengers is identified and dealt with.
Using a sensitive information recognition system based on artificial intelligence, through machine learning and deep learning algorithms, sensitive information leakage risk assessment reports are identified and generated, combined with AI sensitive identification model, and sequence labeling is used by Bi-LSTM improved recurrent neural network model and CRF to ensure the accuracy and rationality of the recognition results.
It realizes accurate identification of sensitive information in massive text data and effective assessment of the risk of leakage, reduces the situation of misjudgment and misjudgment, improves the accuracy and adaptability of data leakage verification, and ensures data security and privacy protection.
Smart Images
Figure CN119848866A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure belongs to the field of data security technology, and in particular relates to a method, system, device and medium for verifying the leakage of sensitive personal information of civil aviation passengers. Background Art
[0002] In today's context of rapid development of informatization, passenger sensitive data leakage incidents occur frequently, posing a serious threat to the privacy and security of enterprises and individuals. Although traditional data desensitization protection measures based on regular expressions have played a protective role to a certain extent, they cannot guarantee the identification and handling of passenger information leakage issues in scenarios such as identification of sensitive information in unformatted data, mismatch of rules after desensitized data format changes, and sensitive personal information of civil aviation passengers included in symmetric encryption and encoded data. With the rapid development of artificial intelligence technology, its powerful capabilities in data processing and pattern recognition have provided new solutions for passenger data sharing and protection of sensitive personal information of civil aviation passengers.
[0003] Artificial intelligence technology, especially machine learning and deep learning algorithms, can effectively identify and classify sensitive data, such as personal ID cards, mobile phone numbers, passports, etc. Such systems are trained to understand and predict the patterns and structures of data, thereby accurately identifying potentially sensitive information.
[0004] 1. Global data protection regulations: With the implementation of data protection regulations such as GDPR, companies must take more stringent data protection and privacy measures. AI-based data leakage verification devices can help companies comply with these legal requirements and avoid high fines and legal liabilities.
[0005] 2. Automatic compliance detection: The AI system can automatically detect whether data processing activities comply with relevant laws and regulations, and adjust processing strategies in a timely manner to ensure that the company's data processing activities are always carried out within the scope permitted by law.
[0006] 3. Continuous learning and optimization: The core of AI technology lies in its ability to continuously learn and self-optimize. This means that the data leakage verification device is not only effective at the initial deployment, but also becomes smarter and more efficient over time.
[0007] In summary, developing data leakage verification systems, systems, equipment, and media based on artificial intelligence sensitive information identification is a necessary measure to respond to current data security challenges. Summary of the invention
[0008] The purpose of the present disclosure is to provide a method, system, device and medium for verifying the leakage of sensitive personal information of civil aviation passengers in order to solve the above-mentioned problems.
[0009] The present invention achieves the above-mentioned purpose through the following technical solutions:
[0010] A method for verifying leakage of sensitive personal information of civil aviation passengers, comprising the following steps:
[0011] Accurately sample the data according to the preset sampling rules to obtain the sampling data;
[0012] identifying the sampled data and generating an identification report;
[0013] Generate a civil aviation passenger sensitive personal information leakage risk assessment report based on the identification report;
[0014] According to the civil aviation passenger sensitive personal information leakage risk assessment report and the configured security policy, the desensitization task is notified to the relevant business applicants and platform maintenance personnel by email and the data push task is suspended.
[0015] As a further optimization scheme of the present disclosure, before accurately sampling the data according to the preset sampling rules, a preliminary screening is required according to the sampling strategy.
[0016] As a further optimization solution of the present disclosure, the sampling strategy includes random sampling or stratified sampling; the sampling rules include setting a specific passenger group or a specific data time period.
[0017] As a further optimization solution of the present disclosure, the identification report includes sensitive label information, sensitive data type and quantity information.
[0018] As a further optimization solution of the present disclosure, generating a civil aviation passenger sensitive personal information leakage risk assessment report based on the identification report includes:
[0019] The normal anesthetized report is compared with the identification report, and a civil aviation passenger sensitive personal information leakage risk assessment report is generated by applying sensitive data leakage verification rules.
[0020] As a further optimization scheme of the present disclosure, the sampled data is identified and a recognition report is generated by an AI sensitive recognition model; the AI sensitive recognition model adopts a recurrent neural network model based on the improved Bi-LSTM, which is an improvement based on the RNN model. It can capture the information of dependencies and context sequences and overcome the gradient vanishing or gradient diffusion problems of traditional RNNs caused by excessively long text sequences by introducing gating mechanisms and storage units.
[0021] As a further optimization scheme of the present disclosure, CRF is used to perform sequence labeling on the AI sensitive recognition model. By considering the relationship between adjacent labels, a joint probability analysis is performed on the label sequence to provide a globally optimal label sequence, thereby ensuring the rationality of the final prediction result.
[0022] A civil aviation passenger sensitive personal information leakage verification system, comprising:
[0023] A data sampling module is used to accurately sample data according to preset sampling rules to obtain sampled data;
[0024] AI civil aviation passenger sensitive personal information identification module, used to identify the sampled data and generate an identification report;
[0025] A sensitive data leakage verification module, used to generate a civil aviation passenger sensitive personal information leakage risk assessment report based on the identification report;
[0026] The sensitive data leakage processing module is used to send email notifications to relevant business applicants and platform maintenance personnel about the desensitization task and suspend the data push task based on the civil aviation passenger sensitive personal information leakage risk assessment report and the configured security policy.
[0027] An electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;
[0028] Memory, for storing computer programs;
[0029] The processor is used to execute the program stored in the memory to implement the leakage verification method of sensitive personal information of civil aviation passengers.
[0030] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for verifying the leakage of sensitive personal information of civil aviation passengers.
[0031] The beneficial effects of the present disclosure are:
[0032] Accuracy: Through natural language processing (NLP) and machine learning algorithms, AI can automatically learn and identify sensitive information from massive amounts of text, including synonyms, homophones, and other variants. This approach not only improves recognition accuracy, but also reduces misjudgments and missed judgments.
[0033] Adaptability: It has strong adaptability and can process various types of data, such as text, images, and audio. The AI model can adapt to new network environments and language changes through continuous learning, thereby maintaining efficient recognition capabilities.
[0034] Scalability: Different algorithms and models can be combined, such as convolutional neural networks (CNN) and recurrent neural networks (RNN) in deep learning, to continuously improve its scope of application and recognition capabilities. This scalability enables AI to cope with more complex data processing tasks.
[0035] False positives and false negatives: By analyzing large amounts of data, AI can reduce false positives and false negatives and improve overall detection performance. AI can also make accurate judgments based on context and semantics, further reducing the rate of false positives.
[0036] The complete calling interface supports task configuration, management, data query, etc., and can quickly interface with data desensitization systems, data management systems and other data sharing systems. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 is a method flow chart in an embodiment of the present disclosure;
[0038] Figure 2 is a system structure block diagram in an embodiment of the present disclosure;
[0039] Figure 3 is a diagram of the system working principle in an embodiment of the present disclosure;
[0040] Figure 4 is a flowchart of AI sensitive recognition model training in an embodiment of the present disclosure;
[0041] Figure 5 is a structural diagram of an AI sensitive recognition model in an embodiment of the present disclosure;
[0042] Figure 6 It is a block diagram of the device structure in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0043] The present application is further described in detail below in conjunction with the accompanying drawings. It is necessary to point out here that the following specific implementation methods are only used to further illustrate the present application and cannot be understood as limiting the scope of protection of the present application. Technical personnel in this field can make some non-essential improvements and adjustments to the present application based on the above application content.
[0044] like Figure 1 As shown, a method for verifying leakage of sensitive personal information of civil aviation passengers includes the following steps:
[0045] Accurately sample the data according to the preset sampling rules to obtain the sampling data;
[0046] identifying the sampled data and generating an identification report;
[0047] Generate a civil aviation passenger sensitive personal information leakage risk assessment report based on the identification report;
[0048] According to the civil aviation passenger sensitive personal information leakage risk assessment report and the configured security policy, the desensitization task is notified to the relevant business applicants and platform maintenance personnel by email and the data push task is suspended.
[0049] Before accurately sampling data according to the preset sampling rules, preliminary screening is required based on the sampling strategy.
[0050] The sampling strategy includes random sampling or stratified sampling; the sampling rules include setting a specific passenger group or a specific data time period.
[0051] The identification report includes sensitive label information, sensitive data type and quantity information.
[0052] Generating a civil aviation passenger sensitive personal information leakage risk assessment report based on the identification report includes:
[0053] The normal anesthetized report is compared with the identification report, and a civil aviation passenger sensitive personal information leakage risk assessment report is generated by applying sensitive data leakage verification rules.
[0054] The sampled data is identified and a recognition report is generated by an AI sensitive recognition model; the AI sensitive recognition model adopts a recurrent neural network model based on the improved Bi-LSTM, which is an improvement based on the RNN model. It can capture the information of dependencies and context sequences, and overcome the gradient vanishing or gradient diffusion problems of traditional RNN due to the long text sequence by introducing gating mechanisms and storage units. The AI sensitive recognition model is sequence labeled using CRF, and the label sequence is jointly analyzed by considering the relationship between adjacent labels to give the global optimal label sequence, ensuring the rationality of the final prediction result.
[0055] like Figure 2 As shown, a civil aviation passenger sensitive personal information leakage verification system includes a data sampling module, an AI civil aviation passenger sensitive personal information identification module, a sensitive data leakage verification module and a sensitive data leakage processing module; the workflow of the civil aviation passenger sensitive personal information leakage verification system is as follows Figure 3 In this embodiment, the civil aviation passenger sensitive personal information leakage verification system specifically includes:
[0056] 1. Data Sampling Module
[0057] This module is responsible for organizing model training data and receiving shared data to be tested, and performing preliminary organization based on the sampling strategy.
[0058] The data is accurately sampled according to the sampling rules to provide high-quality input data for the artificial intelligence civil aviation passenger sensitive personal information identification module.
[0059] 2. AI Civil Aviation Passenger Sensitive Personal Information Identification Module
[0060] After the data is processed by the sampling module, it is input into this module.
[0061] Based on the input data, artificial intelligence technology model training and artificial intelligence technology civil aviation passengers’ sensitive personal information identification operations can be performed.
[0062] The module can identify and output sensitive label information, sensitive data type and quantity in passenger data.
[0063] Sensitive personal information of civil aviation passengers: name, ID number, phone number, passport, frequent flyer card, email address, contact address, payment card number
[0064] 3. Sensitive Data Leakage Verification Module
[0065] The function of this module is to compare the report generated after normal desensitization with the report generated by the artificial intelligence recognition module.
[0066] By applying sensitive data leakage verification rules, this module can generate a risk assessment report on the leakage of sensitive personal information of civil aviation passengers.
[0067] 4. Sensitive Data Leakage Processing Module
[0068] When the assessment report confirms the risk of sensitive information leakage based on the preset threshold, this module will send an email notification to the relevant business applicants and platform maintenance personnel about the desensitization task according to the configured security policy.
[0069] Based on the risk assessment, the module will call the interface provided by the data desensitization task to suspend the data push task to prevent potential data leakage.
[0070] Through the coordinated work of these four modules, the device of the present invention not only improves the ability to identify sensitive information, but also enhances the response speed and processing efficiency to data leakage risks, providing a strong guarantee for data security in the production environment.
[0071] like Figure 4 As shown, in this embodiment, AI sensitive recognition model training includes:
[0072] 1.1 Data Sampling
[0073] Preliminary filtering: Preliminary screening of data based on preset sampling strategies (random sampling, stratified sampling, etc.)
[0074] Filter out data records that do not meet the sampling conditions.
[0075] Precise sampling: Apply specific sampling rules, such as setting specific traveler groups or data time periods.
[0076] Use algorithms to ensure the representativeness of samples and prepare high-quality input data for use by AI modules.
[0077] 1.2 Generate training set
[0078] Take production sampling data as input data.
[0079] Implement data cleaning and formatting to meet the requirements of AI model training.
[0080] 1.3 Update training set
[0081] Regularly sample training sets generated using new data to retrain AI models to adapt to new data patterns and information types.
[0082] Update the model to improve recognition accuracy and efficiency.
[0083] In this embodiment, the AI civil aviation passenger sensitive personal information identification and leakage prevention workflow is as follows:
[0084] 2.1 Data input:
[0085] Receive produced or anonymized data;
[0086] Configure the data interface to receive various types of anonymized production environment data.
[0087] Ensure that the received data complies with predefined format and quality standards.
[0088] 2.2 AI Identification of Sensitive Personal Information of Civil Aviation Passengers:
[0089] like Figure 5 As shown, the AI sensitive identification model interface is called to identify sensitive information. The improved recurrent neural network model based on Bi-LSTM is adopted. The model is an improvement based on the RNN model. It can capture the information of dependency and context sequence, and overcome the gradient vanishing or gradient diffusion problem caused by the long text sequence of traditional RNN by introducing gating mechanism and storage unit. Bi-LSTM is a bidirectional attention mechanism based on LSTM.
[0090] Use CRF (Conditional Random Field, a discriminant probability model) for sequence labeling model, consider the relationship between adjacent labels, conduct joint probability analysis on label sequences, give the global optimal label sequence, and ensure the rationality of the final prediction result. Label and define sensitive data in passenger information, and output sensitive label information, sensitive data type and quantity, etc.
[0091] 2.3 Sensitive data leakage verification:
[0092] Report comparison: Compare the normal desensitized report with the report generated by the AI recognition module to detect the differences between the two and identify potential sensitive information leaks.
[0093] Risk assessment report: Based on the comparison results, apply the sensitive data leakage verification rules to generate a risk assessment report. The report should list in detail the specific location and possible impact of the leakage risk.
[0094] 2.4 Disposal of sensitive data leakage:
[0095] Risk notification: When there is a risk of sensitive information leakage, an email will be automatically sent to notify relevant business personnel and tool operation and maintenance personnel immediately. Sufficient information is provided to quickly locate and respond to the problem.
[0096] Preventive measures: Perform corresponding security operations based on the tool interface that responds to the risk assessment, such as suspending data push, adjusting system permissions, etc. Record all operations to facilitate post-audit and responsibility tracing.
[0097] Through this series of specific implementation steps, the present invention will effectively reduce the risk of leakage of sensitive passenger data in the production environment, improve identification and processing efficiency, and ensure data security and protection of passenger privacy.
[0098] The implementation process of the functions and effects of each module in the above system is specifically described in the implementation process of the corresponding steps in the above method, which will not be repeated here.
[0099] For the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without paying any creative work.
[0100] In the above-mentioned embodiment, any multiple of all modules can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least some functions of one or more of these modules can be combined with at least some functions of other modules and implemented in one module. At least one of all modules can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation modes of software, hardware and firmware or in a suitable combination of any of them. Alternatively, at least one of all modules can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.
[0101] See also Figure 6 , an electronic device provided by an embodiment of the present disclosure includes a processor 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120, and the memory 1130 communicate with each other through the communication bus 1140;
[0102] Memory 1130, for storing computer programs;
[0103] The processor 1110 is used to implement the following civil aviation passenger sensitive personal information leakage verification method when executing the program stored in the memory 1130.
[0104] The communication bus 1140 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 1140 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
[0105] The communication interface 1120 is used for communication between the above electronic device and other devices.
[0106] The memory 1130 may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory 1130 may also be at least one storage device located away from the processor 1110.
[0107] The above-mentioned processor 1110 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
[0108] The embodiment of the present disclosure further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for verifying the leakage of sensitive personal information of civil aviation passengers as described above is implemented.
[0109] The computer-readable storage medium may be included in the device / apparatus described in the above embodiment; or it may exist independently without being assembled into the device / apparatus. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the civil aviation passenger sensitive personal information leakage verification method according to the embodiment of the present disclosure is implemented.
[0110] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
[0111] The above-mentioned embodiments only express several implementation methods of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present disclosure. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present disclosure, and these all belong to the protection scope of the present disclosure.
Claims
1. A method for verifying leakage of sensitive personal information of civil aviation passengers, characterized in that: The following steps are involved: Accurately sample the data according to the preset sampling rules to obtain the sampling data; identifying the sampled data and generating an identification report; Generate a civil aviation passenger sensitive personal information leakage risk assessment report based on the identification report; According to the civil aviation passenger sensitive personal information leakage risk assessment report and the configured security policy, the desensitization task is notified to the relevant business applicants and platform maintenance personnel by email and the data push task is suspended.
2. A civil aviation passenger sensitive personal information leakage verification method according to claim 1, characterized in that: Before accurately sampling data according to the preset sampling rules, preliminary screening is required based on the sampling strategy.
3. A civil aviation passenger sensitive personal information leakage verification method according to claim 2, characterized in that: The sampling strategy includes random sampling or stratified sampling; the sampling rules include setting a specific passenger group or a specific data time period.
4. A civil aviation passenger sensitive personal information leakage verification method according to claim 1, characterized in that: The identification report includes sensitive label information, sensitive data type and quantity information.
5. A civil aviation passenger sensitive personal information leakage verification method according to claim 1, characterized in that: Generating a civil aviation passenger sensitive personal information leakage risk assessment report based on the identification report includes: The normal anesthetized report is compared with the identification report, and a civil aviation passenger sensitive personal information leakage risk assessment report is generated by applying sensitive data leakage verification rules.
6. A civil aviation passenger sensitive personal information leakage verification method according to claim 1, characterized in that: The sampled data is identified and an identification report is generated through an AI sensitive recognition model; the AI sensitive recognition model adopts a recurrent neural network model based on the improved Bi-LSTM, which is an improvement based on the RNN model. It can capture the information of dependencies and context sequences and overcome the gradient vanishing or gradient diffusion problems of traditional RNN caused by excessively long text sequences by introducing gating mechanisms and storage units.
7. A civil aviation passenger sensitive personal information leakage verification method according to claim 6, characterized in that: CRF is used to perform sequence labeling on the AI sensitive recognition model. By considering the relationship between adjacent labels, a joint probability analysis is performed on the label sequence to give a globally optimal label sequence to ensure the rationality of the final prediction result.
8. A civil aviation passenger sensitive personal information leakage verification system, characterized in that: include: A data sampling module is used to accurately sample data according to preset sampling rules to obtain sampled data; AI civil aviation passenger sensitive personal information identification module, used to identify the sampled data and generate an identification report; A sensitive data leakage verification module, used to generate a civil aviation passenger sensitive personal information leakage risk assessment report based on the identification report; The sensitive data leakage processing module is used to send email notifications to relevant business applicants and platform maintenance personnel about the desensitization task and suspend the data push task based on the civil aviation passenger sensitive personal information leakage risk assessment report and the configured security policy.
9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, for storing computer programs; A processor is used to execute the program stored in the memory to implement the civil aviation passenger sensitive personal information leakage verification method described in any one of claims 1-7.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for verifying the leakage of sensitive personal information of civil aviation passengers described in any one of claims 1-7 is implemented.