A payment data security assessment method and system

Abstract

The present invention discloses a payment data security assessment method and system, including the steps of data collection, risk identification, security assessment and report generation, etc., utilizing distributed collection nodes in combination with a quantum random number generator, adopting innovative modules such as deep learning models, autoencoders, knowledge graphs, adding adversarial sample detection and risk dynamic simulation, report encryption, visualization and automatic updating, as well as real-time monitoring, simulated attack and emergency response modules, to ensure the comprehensiveness, accuracy and timeliness of payment data security assessment; the present invention collaborates with multiple modules to ensure that data collection is comprehensive, real-time and secure, improves the accuracy of risk identification, makes security assessment more scientific, makes reports intuitive and timely, and also has an all-round protection system, providing strong protection for payment data security and enhancing the confidence of users and payment service providers.

Description

Technical Field

[0001] The present invention relates to the technical field of payment security systems, and in particular to a payment data security assessment method and system. Background Art

[0002] With the rapid development of the digital age, electronic payment plays an increasingly important role in people's daily lives and business activities. The security of payment data has become a crucial issue. Once payment data is leaked, tampered with, or maliciously attacked, it may cause huge economic losses to users and also have a serious impact on the reputation of payment service providers.

[0003] At present, traditional payment data security assessment methods have some limitations. On the one hand, the data collection method is often relatively simple, and it is difficult to fully cover all data in various payment scenarios, which may lead to potential risks being ignored. In addition, during the data transmission process, security measures are not perfect and are vulnerable to network attacks, which makes payment data face the risk of being stolen during the collection stage.

[0004] On the other hand, risk identification methods are relatively backward. They usually rely on simple rule engines or statistical analysis methods, which make it difficult to accurately identify complex and changing payment risks, especially for new transaction fraud methods and data leakage channels. There is a lack of effective detection capabilities. At the same time, there is a lack of in-depth mining of potential risk associations in payment data, and it is impossible to comprehensively evaluate the security status of the payment system from a global perspective.

[0005] In the security assessment phase, the existing assessment indicator system is relatively rigid and cannot adapt to the ever-changing network environment and payment business needs in a timely manner. Moreover, the method of determining the indicator weights is not scientific enough and it is difficult to accurately reflect the actual impact of various factors on payment data security. In addition, the lack of detection of new attack methods such as adversarial samples has cast doubt on the reliability of security assessment results.

[0006] In terms of report generation, assessment reports generated by traditional methods are often monotonous in form and obscure in content, making it difficult for users to understand and make decisions. In addition, there is a lack of automatic update mechanism, making it difficult to timely reflect the dynamic changes in the payment system and emerging security risks.

[0007] In summary, there is an urgent need for an innovative payment data security assessment method and system to solve the problems existing in the existing technology, improve the security of payment data, and protect the interests of users and payment service providers. Summary of the invention

[0008] The present invention proposes a payment data security assessment method and system to solve the problems mentioned in the above-mentioned prior art.

[0009] In order to achieve the above object, the present invention adopts the following technical solution: a payment data security assessment method, comprising the following steps:

[0010] S1. Data collection: Collect payment data in the payment system, including transaction information, user information, and payment channel information. In the process of payment data collection, innovative methods are used to ensure the security, comprehensiveness, and real-time nature of the data. Suppose the payment data set in the payment system is ,in Represents a collection of transaction information data. Represents a collection of user information data. Represents a collection of payment channel information data;

[0011] Distributed data collection nodes are used to ensure the comprehensiveness and real-time nature of data collection. Data is transmitted between nodes through encrypted communication to prevent data from being stolen during the collection process. The number of distributed nodes is , the formula for the amount of data collected by each node is ,in Indicates The amount of transaction information data collected by each node, Indicates The amount of user information data collected by the node, Indicates The amount of payment channel information data collected by each node, function It represents the comprehensive calculation method of the three types of information data. The total collected data volume formula is: ;

[0012] Introducing a quantum random number generator to provide a key source for encrypted communications during data collection;

[0013] S2. Risk identification: Risk identification is performed on the collected payment data. Suppose the collected payment data is a vector set ,in Representative payment data sample;

[0014] Introducing the neural network model in deep learning, studying historical payment data, and establishing a risk prediction model, the security risk factors of data leakage risk, transaction fraud risk, and payment channel risk are divided. Assuming that the neural network model has several hidden layers, The output of the layer is , the activation function is , the weight matrix is , the bias vector is , then for the The layers are: The final risk prediction value is the output of the neural network model, that is ,in is the total number of layers of the neural network;

[0015] Add the autoencoder module to perform unsupervised learning on the payment data, extract the key features of the data, and train the autoencoder by minimizing the reconstruction error. The reconstruction error can be expressed as the mean square error function: ,in represents the reconstruction error of the autoencoder, represents the total number of payment data samples, Indicates the sample number, represents the original payment data sample, Represents the autoencoder for The sample obtained by reconstructing the original payment data samples is Indicates The distance between the original sample and the reconstructed sample;

[0016] S3. Introduce the knowledge graph construction module, construct the entities and relationships in the payment data into a knowledge graph, and mine risk associations through graph analysis. Suppose the entity set in the payment data is , the relationship set is , the knowledge graph can be represented by a triple set To indicate that Representing Entities Through relationships With entity Associated.

[0017] By building a knowledge graph module, each entity and relationship is assigned a feature vector. The eigenvector of ,relation The eigenvector of For a triple , define a scoring function ,in Is and relationship By optimizing this scoring function, the score for true triples is as high as possible, while the score for false triples is as low as possible.

[0018] Using the constructed knowledge graph, we can perform graph analysis to mine risk associations. For example, we can calculate the risk propagation probability between different entities. To Entity Through relationships The probability of risk transmission is , this probability can be estimated by analyzing and counting the paths in the knowledge graph. In this way, potential risks in payment data can be more comprehensively identified, providing stronger support for payment data security assessment;

[0019] S4. Security assessment: Based on the risk identification results, the security of payment data is assessed. A quantitative assessment index system is used to introduce dynamic risk factors, including changes in the network environment and abnormal user behavior. Fuzzy logic algorithms are used to determine the weight of each index to comprehensively assess the security level of payment data.

[0020] S5. Introduce an adversarial sample detection module to perform adversarial sample detection on payment data to prevent malicious attackers from deceiving risk identification and security assessment models by constructing adversarial samples. Add a risk dynamic simulation module to simulate different risk scenarios to evaluate the security performance of the payment system in various situations, providing a basis for formulating response strategies.

[0021] S6. Report generation: Generate a payment data security assessment report, detailing the assessment results and existing security issues, and proposing targeted improvement suggestions. The report is stored and transmitted using encryption technology, and the assessment report is presented in the form of a chart using visualization technology. An automatic report update module is introduced to automatically update the assessment report when major changes occur in the payment system or new risks arise.

[0022] Preferably, in step S2, in addition to the deep learning neural network model, a genetic algorithm is also used to optimize the model to improve the accuracy and efficiency of risk identification.

[0023] Preferably, in step S4, blockchain technology is used to record and verify the evaluation process to ensure that the evaluation results are tamper-proof and traceable.

[0024] Preferably, the present invention further discloses a payment data security assessment system, comprising:

[0025] The data collection module is used to collect payment data in the payment system and is composed of several distributed data collection nodes, which are connected by encrypted communication links;

[0026] The risk identification module identifies risks in the collected payment data and uses a deep learning neural network model and a risk prediction model optimized by a genetic algorithm to accurately analyze potential security risks. It includes an autoencoder module and a knowledge graph construction module.

[0027] The security assessment module evaluates the security of payment data based on the risk identification results, uses a quantitative assessment index system and fuzzy logic algorithm to determine the weights, and combines blockchain technology to record and verify the assessment process. It has an adversarial sample detection module and a risk dynamic simulation module for a comprehensive assessment of security conditions;

[0028] Report generation module generates payment data security assessment reports. The reports are stored and transmitted using encryption technology, presented using visualization technology, and an automatic report update module is introduced to ensure timeliness;

[0029] Real-time monitoring module, which continuously monitors the operation status of the payment system, including network traffic, system load, and user behavior. Once an abnormal situation is found, an alarm is immediately triggered and in-depth analysis is performed;

[0030] The simulated attack module regularly simulates attacks on the payment system to detect security vulnerabilities in the system based on the simulated attack results.

[0031] Preferably, the neural network model and genetic algorithm in the risk identification module can be dynamically updated and optimized according to new payment data.

[0032] Preferably, the blockchain technology in the security assessment module is integrated with other security systems to achieve cross-system security assessment and data sharing.

[0033] Preferably, the real-time monitoring module uses intelligent sensors and data analysis algorithms to achieve real-time monitoring of the payment system.

[0034] Preferably, the simulated attack module adopts several attack methods and strategies, including network attacks and social engineering attacks, to comprehensively detect the security of the payment system.

[0035] Preferably, an emergency response module is also included. When the system detects a serious security incident, an emergency plan is activated to take measures to limit losses and restore normal operation of the system.

[0036] Preferably, the emergency response module cooperates with other security agencies and departments to jointly respond to payment data security incidents.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] The present invention ensures the comprehensiveness and real-time nature of payment data collection by adopting distributed data collection nodes, avoids data omissions, and provides a solid foundation for accurately evaluating payment data security. At the same time, the encrypted communication between nodes combined with the quantum random number generator greatly enhances the security of data transmission and effectively prevents data from being stolen during the collection process.

[0039] The present invention greatly improves the accuracy of risk identification by introducing a deep learning neural network model and an autoencoder module. The autoencoder can extract key data features and cooperate with the neural network model to more accurately analyze potential security risk factors, such as data leakage risk, transaction fraud risk, payment channel risk, etc.

[0040] The present invention constructs a knowledge graph module to construct entities and relationships in payment data into a knowledge graph, mines potential risk associations, makes risk identification more comprehensive, and helps to discover complex risk patterns in advance.

[0041] The present invention sets up a quantitative evaluation index system, introduces dynamic risk factors, such as changes in the network environment and abnormal user behavior, and uses a fuzzy logic algorithm to determine the weight of each index, comprehensively evaluates the security level of payment data, and makes the evaluation results more scientific and reasonable, which can better meet the payment data security assessment needs in different scenarios.

[0042] The present invention effectively prevents malicious attackers from deceiving risk identification and security assessment models by constructing adversarial samples by adding an adversarial sample detection module, thereby improving the anti-attack capability and reliability of the assessment system.

[0043] The present invention provides a dynamic risk simulation module to simulate different risk scenarios and evaluate the security performance of the payment system under various circumstances, thereby providing a strong basis for formulating response strategies and enhancing the overall security of the payment system.

[0044] The present invention ensures the security of the assessment report by using encryption technology to store and transmit the assessment report. Visualization technology presents the assessment report in an intuitive chart form, which is convenient for users to understand and make decisions. The report automatic update module ensures the timeliness of the report and can promptly reflect changes in the payment system and emerging risks.

[0045] The present invention forms a comprehensive payment data security protection system by setting up a real-time monitoring module, a simulated attack module and an emergency response module. The real-time monitoring module continuously monitors the operating status of the payment system and discovers abnormalities in a timely manner; the simulated attack module detects system security loopholes and improves security protection measures; the emergency response module quickly activates the emergency plan when a serious security incident occurs, limits losses and restores the normal operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic block diagram of a payment data security assessment method proposed by the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0049] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, and it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0050] Reference Figure 1 :A payment data security assessment method comprises the following steps:

[0051] S1. Data collection: Collect payment data in the payment system, including transaction information, user information, and payment channel information. In the process of payment data collection, innovative methods are used to ensure the security, comprehensiveness, and real-time nature of the data. Suppose the payment data set in the payment system is ,in Represents a collection of transaction information data. Represents a collection of user information data. Represents a collection of payment channel information data;

[0052] Distributed data collection nodes are used to ensure the comprehensiveness and real-time nature of data collection. Data is transmitted between nodes through encrypted communication to prevent data from being stolen during the collection process. The number of distributed nodes is , the formula for the amount of data collected by each node is ,in Indicates The amount of transaction information data collected by each node, Indicates The amount of user information data collected by each node, Indicates The amount of payment channel information data collected by each node, function It represents the comprehensive calculation method of the three types of information data. The total collected data volume formula is: ;

[0053] Introducing quantum random number generators to provide a key source for encrypted communications during data collection;

[0054] S2. Risk identification: Risk identification is performed on the collected payment data. Suppose the collected payment data is a vector set ,in Representative payment data sample;

[0055] Introducing the neural network model in deep learning, studying historical payment data, and establishing a risk prediction model, the security risk factors of data leakage risk, transaction fraud risk, and payment channel risk are divided. Assuming that the neural network model has several hidden layers, The output of the layer is , the activation function is , the weight matrix is , the bias vector is , then for the The layers are: The final risk prediction value is the output of the neural network model, that is ,in is the total number of layers of the neural network;

[0056] Add the autoencoder module to perform unsupervised learning on the payment data, extract the key features of the data, and train the autoencoder by minimizing the reconstruction error. The reconstruction error can be expressed as the mean square error function: ,in represents the reconstruction error of the autoencoder, represents the total number of payment data samples, Indicates the sample number, represents the original payment data sample, Represents the autoencoder for The sample obtained by reconstructing the original payment data samples is Indicates The distance between the original sample and the reconstructed sample;

[0057] S3. Introduce the knowledge graph construction module, construct the entities and relationships in the payment data into a knowledge graph, and mine risk associations through graph analysis. Suppose the entity set in the payment data is , the relationship set is , the knowledge graph can be represented by a triple set To indicate that Representing Entities Through relationships With entity Associated.

[0058] By building a knowledge graph module, each entity and relationship is assigned a feature vector. The eigenvector of ,relation The eigenvector of For a triple , define a scoring function ,in Is and relationship By optimizing this scoring function, the score for true triples is as high as possible, while the score for false triples is as low as possible.

[0059] Using the constructed knowledge graph, we can perform graph analysis to mine risk associations. For example, we can calculate the risk propagation probability between different entities. To Entity Through relationships The probability of risk transmission is , this probability can be estimated by analyzing and counting the paths in the knowledge graph. In this way, potential risks in payment data can be more comprehensively identified, providing stronger support for payment data security assessment;

[0060] S4. Security assessment: Based on the risk identification results, the security of payment data is assessed. A quantitative assessment index system is used to introduce dynamic risk factors, including changes in the network environment and abnormal user behavior. Fuzzy logic algorithms are used to determine the weight of each index to comprehensively assess the security level of payment data.

[0061] S5. Introduce an adversarial sample detection module to perform adversarial sample detection on payment data to prevent malicious attackers from deceiving risk identification and security assessment models by constructing adversarial samples. Add a risk dynamic simulation module to simulate different risk scenarios to evaluate the security performance of the payment system in various situations, providing a basis for formulating response strategies.

[0062] S6. Report generation: Generate a payment data security assessment report, detailing the assessment results and existing security issues, and proposing targeted improvement suggestions. The report is stored and transmitted using encryption technology, and the assessment report is presented in the form of a chart using visualization technology. An automatic report update module is introduced to automatically update the assessment report when major changes occur in the payment system or new risks arise.

[0063] In the present invention, in step S2, in addition to the deep learning neural network model, the model is also optimized in combination with a genetic algorithm to improve the accuracy and efficiency of risk identification.

[0064] In the present invention, in step S4, blockchain technology is used to record and verify the evaluation process to ensure the non-tamperability and traceability of the evaluation results.

[0065] The present invention also discloses a payment data security evaluation system, comprising:

[0066] The data collection module is used to collect payment data in the payment system and is composed of several distributed data collection nodes, which are connected by encrypted communication links;

[0067] The risk identification module identifies risks in the collected payment data and uses a deep learning neural network model and a risk prediction model optimized by a genetic algorithm to accurately analyze potential security risks. It includes an autoencoder module and a knowledge graph construction module.

[0068] The security assessment module evaluates the security of payment data based on the risk identification results, uses a quantitative assessment index system and fuzzy logic algorithm to determine the weights, and combines blockchain technology to record and verify the assessment process. It has an adversarial sample detection module and a risk dynamic simulation module for a comprehensive assessment of security conditions;

[0069] Report generation module generates payment data security assessment reports. The reports are stored and transmitted using encryption technology, presented using visualization technology, and an automatic report update module is introduced to ensure timeliness;

[0070] Real-time monitoring module, which continuously monitors the operation status of the payment system, including network traffic, system load, and user behavior. Once an abnormal situation is found, an alarm is immediately triggered and in-depth analysis is performed;

[0071] The simulated attack module regularly simulates attacks on the payment system to detect security vulnerabilities in the system based on the simulated attack results.

[0072] In the present invention, the risk identification module exhibits a high degree of intelligence and adaptability, wherein the combination of the neural network model and the genetic algorithm provides a powerful impetus for accurately identifying risks in payment data.

[0073] The neural network model in the risk identification module has strong learning and pattern recognition capabilities. It can analyze a large amount of payment data and extract potential risk characteristics. However, as time goes by and new payment data is continuously generated, the risk pattern may also change. In order to ensure the accuracy and timeliness of risk identification, the neural network model can be dynamically updated according to the new payment data. Whenever new payment data enters the system, the neural network model will automatically learn from this data and adjust its own weights and parameters to better adapt to the new risk pattern.

[0074] At the same time, genetic algorithms play a key role in optimizing neural network models. Genetic algorithms optimize the structure and parameters of neural network models by simulating the process of biological evolution. It can search for the best solution among many possible solutions and improve the performance of neural network models. When new payment data appears, the genetic algorithm will restart the optimization process and adjust the structure and parameters of the neural network model according to the new data to make it more adaptable to the new risk environment.

[0075] This dynamic update and optimization mechanism enables the risk identification module to always maintain a keen insight into payment data risks. Whether it is new fraud methods, data leakage channels, or changes in user behavior, the risk identification module can make timely adjustments and accurately identify potential risks, providing a reliable basis for payment data security assessment.

[0076] In the present invention, the blockchain technology in the security assessment module shows strong advantages and innovative potential. Blockchain technology, with its decentralized, tamper-proof, and traceable characteristics, brings a new solution to payment data security assessment.

[0077] This module deeply integrates blockchain technology with other security systems. Through carefully designed interfaces and protocols, it achieves seamless connection with different types of security systems. This integration not only broadens the scope of security assessment, but also improves the accuracy and comprehensiveness of the assessment.

[0078] By utilizing the decentralized nature of blockchain, different security systems can interact and collaborate without relying on a single central node. Each system can upload its own security assessment data to the blockchain network to achieve cross-system security assessment. For example, the security assessment data of the payment system can be integrated with the bank's risk control system and the assessment results of a third-party security certification agency to jointly build a more comprehensive and objective security assessment system.

[0079] The tamper-proof nature of blockchain ensures the authenticity and reliability of data. Once the security assessment data is recorded on the blockchain, it cannot be easily tampered with or deleted. This provides a solid trust foundation for cross-system data sharing and avoids the risk of data being maliciously tampered with or forged.

[0080] At the same time, the traceability of blockchain makes it easier to investigate and trace security incidents. When a security issue occurs, the transaction records on the blockchain can be used to quickly trace the source of the problem, identify the responsible party, and take appropriate measures to deal with it.

[0081] In addition, blockchain technology can also make the security assessment process transparent. All participants can view the security assessment data and transaction records on the blockchain to ensure that the assessment process is fair, just and open. This helps to enhance the trust of all parties in the security assessment results and promote cross-system cooperation and collaboration.

[0082] In the present invention, the real-time monitoring module is a key component to ensure the safe and stable operation of the payment system. The module innovatively uses intelligent sensors and advanced data analysis algorithms to achieve all-round and high-precision real-time monitoring of the payment system.

[0083] As front-end devices for data collection, smart sensors are highly sensitive and accurate. They are deployed at key nodes in the payment system and can sense the system's operating status parameters in real time, such as network traffic, server load, data transmission rate, etc. These sensors can quickly capture any subtle changes and transmit the collected data to the data analysis module in real time at a high frequency.

[0084] The data analysis algorithm is the core brain of the real-time monitoring module. It uses advanced machine learning and data mining technology to quickly analyze and process the massive data from smart sensors. By establishing a dynamic monitoring model, the algorithm can accurately identify normal system operation modes and abnormal situations. For example, using the time series analysis algorithm, the changing trend of network traffic can be predicted in real time, and an alarm will be issued immediately once an abnormal increase or decrease in traffic is found. At the same time, through cluster analysis and anomaly detection algorithms, abnormal behaviors in the system can be quickly identified, such as abnormal user behavior, abnormal transaction patterns, etc.

[0085] The real-time monitoring module can not only detect security loopholes and potential risks in the payment system in a timely manner, but also optimize system performance in real time. For example, when the server load is detected to be too high, the resource allocation strategy can be automatically adjusted to ensure the stable operation of the system. In addition, this module can also be linked with other security modules. For example, when a security incident is discovered, the emergency response module is immediately activated and corresponding measures are taken to deal with it.

[0086] In the present invention, the simulated attack module plays a vital role, providing a comprehensive and in-depth test for the security of the payment system. The module carefully adopts several highly targeted attack methods and strategies to ensure the most stringent security test of the payment system.

[0087] Among them, cyber attacks are an important method. Cyber ​​attacks cover many forms, such as distributed denial of service attacks (DDoS), which send a large number of false requests to the target payment system in an attempt to exhaust system resources and make it unable to provide services to users normally. There are also malware injection attacks, which implant carefully designed malware into the payment system, which may steal user data, tamper with transaction information, or disrupt the normal operation of the system. In addition, cyber attacks may also include man-in-the-middle attacks, which intercept communication data between users and payment systems, obtain sensitive information and tamper with it.

[0088] At the same time, the simulated attack module also uses social engineering attack strategies. This is a means of attacking by taking advantage of human weaknesses, such as phishing attacks, which send fake emails or messages that appear to be from legitimate organizations to induce users to reveal their payment account numbers, passwords and other sensitive information. There are also disguised attacks, where attackers disguise themselves as legitimate system administrators or customer service personnel to deceive users' trust and gain access to payment systems.

[0089] By adopting these diverse attack methods and strategies, the simulated attack module can comprehensively detect the security of the payment system from different angles and levels. It can help discover potential security loopholes and weak links in the system, provide a strong basis and direction for further strengthening the security protection of the payment system, and ensure that the payment system can maintain a high degree of security and stability when facing various actual attack threats.

[0090] In the present invention, the emergency response module is a key component to ensure the security of payment data. When the system detects a serious security incident, the module can quickly activate the emergency plan and demonstrate efficient response capabilities.

[0091] Once the system detects an event that may pose a major threat to payment data security, such as a large-scale data leak or a malicious attack that causes system paralysis, the emergency response module will immediately trigger an alarm. It will first quickly assess the security incident and analyze the severity, scope of impact, and possible development trends of the incident.

[0092] Next, the emergency response module will take a series of decisive measures to limit the losses according to the pre-established emergency plan. This may include immediately cutting off the affected payment channels to prevent more data from being stolen or tampered with; launching the data backup and recovery system to ensure the security and recoverability of key payment data; at the same time, isolating the attacked system to prevent the security incident from spreading further.

[0093] While limiting losses, the emergency response module will also take proactive actions to restore the normal operation of the system. It will mobilize the technical team to conduct in-depth analysis of the security incident, find the root cause of the problem and develop a solution. It may carry out emergency repairs on the system, update security protection measures, strengthen access control, etc. At the same time, it will communicate and coordinate with relevant security agencies and partners to obtain technical support and resources to speed up the recovery process.

[0094] The emergency response module will also continuously monitor the system's recovery to ensure the effectiveness of various measures. Once new problems or risks are discovered, the strategy will be adjusted in a timely manner to ensure that the system can be restored to normal operation stably and safely, providing a solid guarantee for the security of payment data.

[0095] In the present invention, the emergency response module plays a vital role. The module has a strong linkage capability and can work closely with other security agencies and departments to jointly deal with payment data security incidents.

[0096] When the payment data security system detects a serious security incident, the emergency response module will be activated quickly. It will send alarm information to relevant security agencies and departments in a timely manner through pre-established communication channels and protocols. These security agencies may include financial regulatory departments, cybersecurity emergency response centers, and cybersecurity departments of public security departments. At the same time, it will also work with the internal security team of the payment service provider and the cooperating technical service provider.

[0097] The emergency response module will provide detailed security incident information to the coordinated institutions and departments, including the type of incident, the scope of payment data involved, the possible impact, etc. By sharing information, all parties can quickly understand the full picture of the incident and provide a basis for formulating a coordinated response strategy.

[0098] During the linkage process, the emergency response module will actively participate in coordinating the actions of all parties. For example, it will cooperate with financial regulatory authorities to ensure compliance with relevant regulations and report the progress of incident handling in a timely manner; jointly analyze the source and means of attacks with the Cybersecurity Emergency Response Center and formulate targeted defense measures; and cooperate with the public security department to investigate and track possible criminal acts.

[0099] In addition, the emergency response module will continue to follow up on the incident handling process and continuously exchange information and feedback with the linked institutions and departments to ensure that the actions of all parties are coordinated and consistent, to minimize the losses caused by the security incident, and to restore the normal operation of the payment system as soon as possible to protect the security of payment data and the rights and interests of users.

[0100] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and inventive concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A payment data security assessment system, characterized in that: The system is used to implement the following method: S1. Data collection: Collect payment data in the payment system, including transaction information, user information, and payment channel information. Use distributed data collection nodes to ensure the comprehensiveness and real-time nature of data collection. Encrypted communication is used between nodes to transmit data to prevent data from being stolen during the collection process. A quantum random number generator is introduced to provide a key source for encrypted communication during the data collection process. S2. Risk identification: Risk identification of collected payment data, introduction of deep learning neural network model, learning of historical payment data, establishment of risk prediction model, analysis of security risk factors of data leakage risk, transaction fraud risk and payment channel risk, addition of autoencoder module, unsupervised learning of payment data, extraction of key features of data, S3. Introduce the knowledge graph construction module to construct the entities and relationships in the payment data into a knowledge graph, and mine risk associations through graph analysis; S4. Security assessment: Based on the risk identification results, the security of payment data is assessed. A quantitative assessment index system is used to introduce dynamic risk factors, including changes in the network environment and abnormal user behavior. Fuzzy logic algorithms are used to determine the weight of each index to comprehensively assess the security level of payment data. S5. Introduce an adversarial sample detection module to perform adversarial sample detection on payment data to prevent malicious attackers from deceiving risk identification and security assessment models by constructing adversarial samples. Add a risk dynamic simulation module to simulate different risk scenarios to evaluate the security performance of the payment system in various situations, providing a basis for formulating response strategies. S6. Report generation: Generate a payment data security assessment report that details the assessment results and existing security issues, and puts forward targeted improvement suggestions. The report is stored and transmitted using encryption technology, and the assessment report is presented in the form of a chart using visualization technology. An automatic report update module is introduced to automatically update the assessment report when the payment system changes or new risks arise; In step S2, in addition to the deep learning neural network model, the genetic algorithm is also used to optimize the model to improve the accuracy and efficiency of risk identification; In step S4, blockchain technology is used to record and verify the assessment process to ensure that the assessment results cannot be tampered with and are traceable; The system comprises: The data collection module is used to collect payment data in the payment system and is composed of several distributed data collection nodes, which are connected by encrypted communication links; The risk identification module identifies risks in the collected payment data and uses a deep learning neural network model and a risk prediction model optimized by a genetic algorithm to accurately analyze potential security risks. It includes an autoencoder module and a knowledge graph construction module. The security assessment module evaluates the security of payment data based on the risk identification results, adopts a quantitative assessment indicator system, uses fuzzy logic algorithm to determine the weight, and combines blockchain technology to record and verify the assessment process. It has an adversarial sample detection module and a risk dynamic simulation module to comprehensively evaluate the security status; Report generation module generates payment data security assessment reports. The reports are stored and transmitted using encryption technology, presented using visualization technology, and an automatic report update module is introduced to ensure timeliness; Real-time monitoring module, which continuously monitors the operation status of the payment system, including network traffic, system load, and user behavior. Once an abnormal situation is found, an alarm is immediately triggered and in-depth analysis is performed; The simulated attack module regularly simulates attacks on the payment system to detect security vulnerabilities in the system.

2. The payment data security assessment system according to claim 1, characterized in that: The neural network model and genetic algorithm in the risk identification module can be dynamically updated and optimized according to new payment data.

3. The payment data security assessment system according to claim 1, characterized in that: The blockchain technology in the security assessment module is integrated with other security systems to achieve cross-system security assessment and data sharing.

4. The payment data security assessment system according to claim 1, characterized in that: The real-time monitoring module uses intelligent sensors and data analysis algorithms to achieve real-time monitoring of the payment system.

5. The payment data security assessment system according to claim 1, characterized in that: The simulated attack module adopts several attack methods and strategies, including network attacks and social engineering attacks, to comprehensively detect the security of the payment system.

6. The payment data security assessment system according to claim 1, characterized in that: It also includes an emergency response module. When the system detects a serious security incident, it activates the emergency plan and takes measures to limit the losses and restore the normal operation of the system.

7. The payment data security assessment system according to claim 6, characterized in that: The emergency response module works in conjunction with other security agencies and departments to jointly respond to payment data security incidents.

Images