Communication method and device

By obtaining user's secure access data and using machine learning algorithms to build a policy decision model, identifying message changes and attack trends, the network security measurement problems caused by network complexity are solved, and effective identification and defense of network attacks are achieved.

CN118944947APending Publication Date: 2024-11-12NEW H3C TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411135134.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The prior art is difficult to effectively solve the network security measurement problems caused by network complexity, and it is impossible to effectively identify and respond to potential threats from network attacks.

Method used

By obtaining user's secure access data, using machine learning algorithms to build an initial decision model, and obtaining a policy decision model through multiple iterative training, identifying the change trend of packets and attack development trends, providing a basis for formulating anti-attack security strategies.

Benefits of technology

It realizes intelligent analysis and real-time monitoring of network security, can identify and respond to network attacks, improves the level of network security protection, and solves the measurement problems caused by network complexity.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118944947A_ABST
    Figure CN118944947A_ABST
Patent Text Reader

Abstract

The invention provides a communication method and device. The method comprises the following steps: acquiring security access data of a user; according to the security access data, through a machine learning algorithm, constructing an initial decision model; performing multiple iterative training on the initial decision model to obtain a strategy decision model, the strategy decision model being used for identifying a message change trend and an attack development trend through security access data and attack data acquired in real time; and displaying the message change trend and the attack development trend.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a communication method and device. Background Art

[0002] With the widespread application of technologies such as cloud computing and big data, and the rapid development of remote office and mobile Internet services, enterprise IT facilities are becoming more and more diverse, and business system access requirements are becoming more and more complex. Internal employees, suppliers, external partners, etc. can flexibly access various business systems in a variety of ways, and the interconnection between business systems will also be accessed by more terminals, and the original network boundaries of enterprises are gradually blurred.

[0003] At the same time, network security risks and threats are becoming increasingly complex. New network attack methods such as APT attacks, ransomware, and internal unauthorized operations are emerging in an endless stream, making it difficult for many companies to defend themselves and causing significant business losses. Traditional perimeter-based network security protection methods are no longer able to cope with these potential security threats.

[0004] The main goal of network security is to protect data and information in computer systems and communication networks from unauthorized access, tampering or disclosure. Network security involves many fields, such as cryptography, operating systems, network security, database security, application security, etc. The importance of network security is self-evident, because once network security is compromised, it may lead to serious consequences. For example, the business secrets of enterprises are leaked, the privacy information of individuals is stolen, and the important data of government agencies is destroyed. Therefore, it is very important to improve the level of network security protection.

[0005] From the perspective of application methods and purposes, network security situation awareness evaluates the network's security situation by collecting, refining, and integrating various security information, providing security analysts with a basis for decision-making in risk management. However, when it comes to the implementation of security assessment, due to the complexity of networking, network security measurement is still a recognized academic problem in the academic community at home and abroad, including network security measurement models and methods, automated collection of security data, perception measurement, and quantitative evaluation, which have not yet been well resolved. Summary of the invention

[0006] In view of this, the present application provides a communication method and device to solve the problem that network security measurement cannot be achieved due to the complexity of the existing network.

[0007] In a first aspect, the present application provides a communication method, the method comprising:

[0008] Obtain user security access data;

[0009] Based on the security access data, an initial decision model is constructed through a machine learning algorithm;

[0010] Performing multiple iterations of training on the initial decision model to obtain a policy decision model, wherein the policy decision model is used to identify message change trends and attack development trends through real-time acquired security access data and attack data;

[0011] Display the message change trend and the attack development trend.

[0012] In a second aspect, the present application provides a communication device, the device comprising:

[0013] A first acquisition unit, used to acquire the user's security access data;

[0014] A construction unit, configured to construct an initial decision model according to the security access data through a machine learning algorithm;

[0015] A training unit, used for performing multiple iterations of training on the initial decision model to obtain a policy decision model, wherein the policy decision model is used to identify message change trends and attack development trends through real-time acquired security access data and attack data;

[0016] The display unit is used to display the message change trend and the attack development trend.

[0017] In a third aspect, the present application provides a network device, including a processor and a machine-readable storage medium, the machine-readable storage medium storing machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to execute the method provided in the first aspect of the present application.

[0018] Therefore, by applying the communication method and device provided by the present application, the intelligent analysis system obtains the user's security access data; based on the security access data, the intelligent analysis system constructs an initial decision model through a machine learning algorithm; the intelligent analysis system performs multiple iterative training on the initial decision model to obtain a policy decision model, which is used to identify message change trends and attack development trends through real-time acquired security access data and attack data; the intelligent analysis system displays message change trends and attack development trends.

[0019] In this way, through machine learning algorithms, the policy decision model is continuously optimized and improved based on the user's security access data. The policy decision model is used to output the message change trend and attack development trend, providing a basis for formulating anti-attack security strategies. This solves the problem that network security cannot be measured due to the complexity of the existing network. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flow chart of a communication method provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of the structure of the intelligent analysis system provided in the embodiment of the present application;

[0022] Figure 3 A structural diagram of a communication device provided in an embodiment of the present application;

[0023] Figure 4 The network device hardware structure provided in the embodiment of the present application. DETAILED DESCRIPTION

[0024] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0025] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more corresponding listed items.

[0026] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0027] The communication method provided in the embodiment of the present application is described in detail below. Figure 1 , Figure 1 Flow chart of the communication method provided in the embodiment of the present application. The method is applied to the intelligent analysis system. The communication method provided in the embodiment of the present application may include the following steps.

[0028] Step 110: Obtain the user's security access data;

[0029] Specifically, the intelligent analysis system obtains the user's security access data and analyzes the security access data.

[0030] Optionally, in the embodiment of the present application, the process of the intelligent analysis system acquiring the user's security access data is specifically as follows:

[0031] In one implementation, the intelligent analysis system obtains user characteristics from the service message; the intelligent analysis system performs a legitimacy check on the user characteristics to obtain legal user characteristics, and the legal user characteristics include security access data.

[0032] In another implementation, a user (or administrator) inputs a configuration instruction into the intelligent analysis system, and the configuration instruction includes user characteristics; the intelligent analysis system receives the configuration instruction and obtains the user characteristics therefrom; the intelligent analysis system performs a legitimacy check on the user characteristics to obtain legal user characteristics, and the legal user characteristics include security access data.

[0033] The above-mentioned security access data includes user identity information, user authority information and user subject information. User identity information may specifically include information such as user name and password; user authority information may specifically include resources that the user is allowed to access and resources that the user is not allowed to access; user subject information may specifically include attributes of the user terminal used by the user, such as whether it is a designated user terminal, user terminal identification, etc.

[0034] In an embodiment of the present application, business messages can be input into the intelligent analysis system by a management personnel, or, during the communication process between a user terminal and a network device, or between network devices, the intelligent analysis system can capture business messages interacting between user terminals and network devices, or between network devices.

[0035] In the embodiment of the present application, the legitimacy check specifically refers to whether there is a matching record for each information included in the user feature. If there is a matching record, the user feature passes the legitimacy check; otherwise, it fails the legitimacy check.

[0036] Optionally, in an embodiment of the present application, after the intelligent analysis system obtains the security access data, it can also identify the user characteristic change trend (for example, the relationship between the accessed resources and the user characteristics, the ratio between the accessed resources and the user characteristics, etc.) based on the security access data, and display the user characteristic change trend, so that the management personnel can dynamically adjust the anti-attack security strategy for different users according to the user characteristic change trend.

[0037] The intelligent analysis system needs to continuously learn the user characteristics of various users from the security access data and continuously expand the scope of user characteristics to ensure user access.

[0038] In the embodiment of the present application, the user characteristics included in the configuration instruction may be the user characteristics of the user (or manager) after the legitimacy check. In this case, the intelligent analysis system does not need to perform a legitimacy check on the user characteristics included in the configuration series.

[0039] Step 120: construct an initial decision model based on the security access data through a machine learning algorithm;

[0040] Specifically, according to the description of step 110, after the intelligent analysis system obtains the security access data, it uses a machine learning algorithm (for example, any machine learning algorithm including a decision tree algorithm, a naive Bayes algorithm, a support vector machine algorithm, an artificial neural network algorithm, deep learning, etc.) to build an initial decision model (for example, a large language model LLM).

[0041] It is understandable that the construction of the initial decision model by the intelligent analysis system using machine learning algorithms can be achieved through existing construction methods, which will not be repeated here.

[0042] Step 130: Perform multiple iterations of training on the initial decision model to obtain a policy decision model, wherein the policy decision model is used to identify message change trends and attack development trends through real-time acquired security access data and attack data;

[0043] Specifically, according to the description of step 120, after the intelligent analysis system constructs the initial decision model, it can use the security access data to perform multiple iterations of training on the initial decision model to obtain a policy decision model. The policy decision model is used to identify the message change trend and attack development trend through the real-time security access data and attack data.

[0044] The machine learning algorithm can first build an initial decision model that can predict trends and make decisions based on the characteristics and rules of security access data. Then, the machine learning algorithm needs to train the model through a large amount of historical data so that the initial decision model can learn the characteristics and rules of normal business messages and abnormal attack messages, and have the ability to predict future trends (message change trends, attack development trends).

[0045] It can be understood that the historical data includes positive sample data and negative sample data, that is, normal business messages and abnormal attack messages.

[0046] After the intelligent analysis system obtains the policy decision model, it can input the real-time business data entered by subsequent users (managers) (or captured by the intelligent analysis system itself) into the policy decision model. The policy decision model identifies the security access data and attack data included in the business data, and identifies the message change trend and attack development trend.

[0047] For example, when the policy decision model identifies attack data multiple times (for example, more than 3 times) within a preset time (for example, 1 minute), the message change trend is from receiving security access data to receiving attack data; the attack development trend is from a non-attack state to a mild attack state (3 attack data identified within 1 minute).

[0048] Furthermore, the policy decision model can quantify the message change trend and attack development trend in the form of scores. For example, the score interval of the message change trend is [0,10]; the score interval of the attack development trend is [0,10]. Each score represents a different message change trend or attack development trend, and each score matches a set of time and number of times.

[0049] For example, if 0 attack data are identified within 1 minute, the score of the message change trend is 0, and the score of the attack development trend is 0; if 1 attack data is identified within 1 minute, the score of the message change trend is 1, and the score of the attack development trend is 1... and so on.

[0050] It is understandable that the time value and the number value can be set according to the actual situation of the current networking.

[0051] Step 140: Display the message change trend and the attack development situation.

[0052] Specifically, according to the description of step 130, the intelligent analysis system displays the message change trend and the attack development trend, so that users (or managers) can accurately evaluate the current network attack situation based on the message change trend and the attack development trend, and formulate reasonable anti-attack security strategies.

[0053] Optionally, as can be seen from the above, the intelligent analysis system also displays the trend of user feature changes. Users (or managers) can also accurately assess the current network attack situation based on the message change trend and attack development trend, combined with the user feature change trend, and formulate a reasonable anti-attack security strategy.

[0054] For example, according to the above examples, the message change trend is from receiving security access data to receiving attack data; the attack development trend is from non-attack state to mild attack state, and the user feature change trend is from non-designated terminals (large proportion: 85%) accessing the network to non-designated terminals with a small proportion (20%) accessing the network. Users (or managers) can formulate anti-attack security policies that match each trend or a combination of trends (for example, by setting a filter condition, that is, setting a filter condition for the source IP address) to intercept attack data.

[0055] It can be understood that if the message change trend is receiving attack data, the attack development trend is a severe attack state, and the user feature change trend is non-designated terminals (large proportion: 90%) accessing the network, that is, it will continue to be in an attacked state for a long time in the future, then the user (or manager) can formulate an anti-attack security policy that matches each trend or a combination of trends (for example, by configuring multiple filtering conditions, that is, setting filtering conditions for source IP address, destination IP address, source port, destination port, etc.) to intercept the attack data.

[0056] Of course, the message change trend, attack development trend, and user feature change trend may also change over time. For example, the message change trend changes from receiving attack data to receiving security access data; the attack development trend changes from a severe attack state to a mild attack state; for example, the message change trend changes from receiving attack data to receiving security access data; the attack development trend changes from a mild attack state to a non-attack state; for example, the user feature changes from a non-designated terminal to a designated terminal, etc. Users (or managers) can formulate anti-attack security policies that match each trend or a combination of trends to intercept attack data.

[0057] Optionally, in the embodiment of the present application, the following process is also included:

[0058] Specifically, the user (or manager) inputs the developed multiple anti-attack security policies applicable to different types (for example, anti-attack policies applicable to protecting various types of applications, anti-attack policies applicable to protecting various types of networks, anti-attack policies applicable to protecting various types of services, and anti-attack policies applicable to protecting various types of data) into the intelligent analysis system. After receiving the multiple security policies, the intelligent analysis system stores the multiple security policies in the security library.

[0059] At the same time, the intelligent analysis system also inputs different security policies of the same type into the policy decision model to obtain the difference results of different security policies of the same type; the intelligent analysis system displays the difference results of the policies, thereby helping users (or managers) make the best choice between different security policies. Users (or managers) notify the intelligent analysis system of the best selected different types of anti-attack security policies, and the intelligent analysis system saves all decision-making behaviors input by users (or managers) in the security library.

[0060] The policy difference result specifically refers to the difference between multiple different security policies of the same type, which can be reflected in the difference in matching items (source IP address, destination IP address, source port, destination port, etc.) and action items (pass, discard, block sending and receiving, redirect, etc.). The intelligent analysis system can list and display the differences between multiple different security policies.

[0061] It is understandable that the user (or manager) will also input the anti-attack security policies that are suitable for different users into the intelligent analysis system. The intelligent analysis system can also perform difference analysis on different security policies of the same user and display the results of the policy differences, thereby helping the user (or manager) to make the best choice between different security policies.

[0062] Optionally, in the embodiment of the present application, the following process is also included:

[0063] Specifically, the user (or manager) inputs the user access demand into the intelligent analysis system. After receiving the user access demand, the intelligent analysis system updates the security policy in the security library according to the message change trend, attack development trend, user feature change trend and user access demand; the intelligent analysis system stores the updated security policy in the security library and sends the updated security policy to the policy execution point.

[0064] It should be noted that users (or managers) will input access requirements for different types of resources. For example, user access requirements for various types of networks are required bandwidth, transmission rate, etc. for different networks; user access requirements for various types of services are service requirements, service quality, etc. for different services.

[0065] In the embodiment of the present application, the policy execution point is used to execute the security policy. Each user terminal that wants to access the intranet must first be identified by the policy execution point. Legal and secure user terminals can access and control the services of the intranet, greatly improving the security of network access.

[0066] Therefore, by applying the communication method provided by the present application, the intelligent analysis system obtains the user's security access data; based on the security access data, the intelligent analysis system constructs an initial decision model through a machine learning algorithm; the intelligent analysis system performs multiple iterative training on the initial decision model to obtain a policy decision model, which is used to identify message change trends and attack development trends through real-time acquired security access data and attack data; the intelligent analysis system displays message change trends and attack development trends.

[0067] In this way, through machine learning algorithms, the policy decision model is continuously optimized and improved based on the user's security access data. The policy decision model is used to output the message change trend and attack development trend, providing a basis for formulating anti-attack security strategies. This solves the problem that network security cannot be measured due to the complexity of the existing network.

[0068] The communication method provided in the embodiment of the present application is described in detail below. Figure 2 , Figure 2 A schematic diagram of the structure of the intelligent analysis system provided in the embodiment of the present application. Figure 2 In the intelligent analysis system, the security data collection and analysis module, the situation assessment engine, the policy decision center and the security library are included. The policy decision center and the security library can also be referred to as the security protection decision system. The security protection decision system also establishes communication connections with the policy execution points and provides anti-attack security policies for resource types (including but not limited to the following types: applications, networks, services, and data).

[0069] The security data collection and analysis module obtains the user's security access data and analyzes the security access data.

[0070] In one implementation, the security data collection and analysis module obtains user characteristics from the business message; the security data collection and analysis module performs a legitimacy check on the user characteristics to obtain legal user characteristics, and the legal user characteristics include security access data.

[0071] In another implementation, a user (or administrator) inputs configuration instructions into the intelligent analysis system, and the configuration instructions include user characteristics; the security data collection and analysis module receives the configuration instructions and obtains user characteristics therefrom; the security data collection and analysis module performs a legitimacy check on the user characteristics to obtain legal user characteristics, and the legal user characteristics include security access data.

[0072] In the embodiment of the present application, the legitimacy check specifically refers to whether there is a matching record for each data included in the user feature. If there is a matching record, the user feature passes the legitimacy check; otherwise, it fails the legitimacy check.

[0073] After the security data collection and analysis module obtains the security access data, it can also identify the changing trends of user characteristics based on the security access data (for example, the relationship between the accessed resources and user characteristics, the ratio between the accessed resources and user characteristics, etc.), and display the changing trends of user characteristics, so that managers can dynamically adjust the anti-attack security policies for different users based on the changing trends of user characteristics.

[0074] In the embodiment of the present application, the user characteristics included in the configuration instruction may be the user characteristics of the user (or manager) after the legitimacy check. In this case, the security data collection and analysis module does not need to perform a legitimacy check on the user characteristics included in the configuration series.

[0075] After the security data collection and analysis module obtains the security access data, it transmits the security access data to the situation assessment engine.

[0076] Using a machine learning algorithm (e.g., any machine learning algorithm including a decision tree algorithm, a naive Bayes algorithm, a support vector machine algorithm, an artificial neural network algorithm, deep learning, etc.), the situation assessment engine constructs an initial decision model (e.g., a large language model LLM).

[0077] It is understandable that the construction of the initial decision model by the situation assessment engine using machine learning algorithms can be achieved through existing construction methods, which will not be repeated here.

[0078] After the situation assessment engine builds the initial decision model, it can use the security access data to perform multiple iterations of training on the initial decision model to obtain a policy decision model. The policy decision model is used to identify the message change trend and attack development trend through the real-time security access data and attack data.

[0079] The machine learning algorithm can first build an initial decision model that can predict trends and make decisions based on the characteristics and rules of security access data. Then, the machine learning algorithm needs to train the model through a large amount of historical data so that the initial decision model can learn the characteristics and rules of normal business messages and abnormal attack messages, and have the ability to predict future trends (message change trends, attack development trends).

[0080] After the situation assessment engine has trained the policy decision model, the real-time business data transmitted by the subsequent security data collection and analysis module can be input into the policy decision model. The policy decision model identifies the security access data and attack data included in the business data, and identifies the message change trend and attack development trend.

[0081] For example, when the policy decision model identifies attack data multiple times (for example, more than 3 times) within a preset time (for example, 1 minute), the message change trend is from receiving security access data to receiving attack data; the attack development trend is from a non-attack state to a mild attack state (3 attack data identified within 1 minute).

[0082] Furthermore, the policy decision model can quantify the message change trend and attack development trend in the form of scores. For example, the score interval of the message change trend is [0,10]; the score interval of the attack development trend is [0,10]. Each score represents a different message change trend or attack development trend, and each score matches a set of time and number of times.

[0083] For example, if 0 attack data are identified within 1 minute, the score of the message change trend is 0, and the score of the attack development trend is 0; if 1 attack data is identified within 1 minute, the score of the message change trend is 1, and the score of the attack development trend is 1... and so on.

[0084] It is understandable that the time value and the number value can be set according to the actual situation of the current networking.

[0085] The situation assessment engine displays the message change trends and attack development trends, so that users (or managers) can accurately assess the current network attack situation based on the message change trends and attack development trends, and formulate reasonable anti-attack security strategies.

[0086] As mentioned above, the security data collection and analysis module also displays the trend of user feature changes. Users (or managers) can also accurately assess the current network attack situation based on the message change trend and attack development trend, combined with the user feature change trend, and formulate a reasonable anti-attack security strategy.

[0087] For example, according to the above examples, the message change trend is from receiving security access data to receiving attack data; the attack development trend is from non-attack state to mild attack state, and the user feature change trend is from non-designated terminals (large proportion: 85%) accessing the network to non-designated terminals with a small proportion (20%) accessing the network. Users (or managers) can formulate anti-attack security policies that match each trend or a combination of trends (for example, by setting a filter condition, that is, setting a filter condition for the source IP address) to intercept attack data.

[0088] It can be understood that if the message change trend is receiving attack data, the attack development trend is a severe attack state, and the user feature change trend is non-designated terminals (large proportion: 90%) accessing the network, that is, it will continue to be in an attacked state for a long time in the future, then the user (or manager) can formulate an anti-attack security policy that matches each trend or a combination of trends (for example, by configuring multiple filtering conditions, that is, setting filtering conditions for source IP address, destination IP address, source port, destination port, etc.) to intercept the attack data.

[0089] Of course, the message change trend, attack development trend, and user feature change can also change over time. For example, the message change trend changes from receiving attack data to receiving security access data; the attack development trend changes from a severe attack state to a mild attack state; for example, the message change trend changes from receiving attack data to receiving security access data; the attack development trend changes from a mild attack state to a non-attack state; for example, the user feature change changes from a non-designated terminal to a designated terminal, etc. Users (or managers) can formulate anti-attack security policies that match each trend or a combination of trends to intercept attack data.

[0090] The user (or manager) inputs the developed multiple anti-attack security policies applicable to different types (for example, anti-attack policies applicable to protecting various applications, anti-attack policies applicable to protecting various networks, anti-attack policies applicable to protecting various services, and anti-attack policies applicable to protecting various data) into the policy decision center. After receiving the multiple security policies, the policy decision center stores the multiple security policies in the security library.

[0091] The situation assessment engine may also input the scores of each trend into the policy decision center, so that the policy decision center stores the anti-attack security policy and the corresponding trend score.

[0092] At the same time, the policy decision center also inputs different security policies of the same type into the policy decision model to obtain the difference results of different security policies of the same type; the policy decision center displays the difference results of the policies, thereby helping users (or managers) make the best choice between different security policies. Users (or managers) notify the policy decision center of the best selected different types of anti-attack security policies, and the policy decision center saves all decision behaviors input by users (or managers) in the security library.

[0093] The policy decision center stores different types of anti-attack security policies and corresponding resource types according to the optimal anti-attack security policies selected by the user (or manager). At the same time, the policy decision center also stores non-optimally selected anti-attack security policies and corresponding resource types. It is understandable that the non-optimally selected anti-attack security policies can be used as backup anti-attack security policies.

[0094] It is understandable that the user (or manager) also inputs the anti-attack security policies that are suitable for different users into the policy decision center. The policy decision center inputs the security policies of different users into the policy decision model to obtain the difference results of different security policies for the same user. The policy decision center displays the policy difference results, thereby helping users (or managers) make the best choice between different security policies.

[0095] The user (or manager) also inputs the user access requirements into the policy decision center. After receiving the user access requirements, the policy decision center updates the security policy in the security library according to the message change trend, attack development trend, user feature change trend and user access requirements. The policy decision center stores the updated security policy in the security library, and also stores the updated different types of anti-attack security policies and corresponding resource types.

[0096] Anti-attack security policies are also deployed in the security protection decision-making system to provide security protection support for network security. The policy decision center sends updated security policies to the policy execution point. The policy execution point is used to execute security policies. Each user terminal that wants to access the intranet must first be identified by the policy execution point. Legal and secure user terminals can access and control the services of the intranet, greatly improving the security of network access.

[0097] Based on the same inventive concept, the present application embodiment also provides a communication device corresponding to the communication method. Figure 3 , Figure 3 A communication device provided in an embodiment of the present application includes:

[0098] A first acquisition unit 310 is used to acquire the user's security access data;

[0099] A construction unit 320, configured to construct an initial decision model according to the security access data through a machine learning algorithm;

[0100] A training unit 330 is used to perform multiple iterations of training on the initial decision model to obtain a policy decision model, wherein the policy decision model is used to identify message change trends and attack development trends through real-time acquired security access data and attack data;

[0101] The display unit 340 is used to display the message change trend and the attack development trend.

[0102] Optionally, the first acquisition unit 310 is specifically configured to acquire user characteristics from a service message;

[0103] Performing a legality check on the user characteristics to obtain legal user characteristics, wherein the legal user characteristics include the security access data; or;

[0104] receiving a configuration instruction input by a user, wherein the configuration instruction includes the user characteristics;

[0105] Performing a legality check on the user characteristics to obtain legal user characteristics, wherein the legal user characteristics include the security access data;

[0106] The security access data includes user identity information, user authority information and user subject information.

[0107] Optionally, the device further comprises:

[0108] An identification unit (not shown in the figure), used to identify the user feature change trend based on the security access data;

[0109] The display unit 340 is further configured to display the user characteristic change trend.

[0110] Optionally, the device further comprises:

[0111] A receiving unit (not shown in the figure), used to receive a plurality of security policies applicable to different categories input by a user;

[0112] A storage unit (not shown in the figure), used to store the multiple security policies in a security library;

[0113] A difference unit (not shown in the figure), used to input different security policies of the same type into the policy decision model to obtain difference results of different security policies of the same type;

[0114] The display unit 340 is further configured to display the difference result.

[0115] Optionally, the device further comprises:

[0116] A second acquisition unit (not shown in the figure), used to acquire user access requirements;

[0117] An updating unit (not shown in the figure), used to update the security policy in the security library according to the message change trend, the attack development situation, the user feature change trend and the user access demand;

[0118] The storage unit (not shown in the figure) is also used to store the updated security policy in the security library;

[0119] The sending unit (not shown in the figure) is used to send the updated security policy to the policy execution point.

[0120] Therefore, by applying the communication device provided by the present application, the intelligent analysis system obtains the user's security access data; based on the security access data, the intelligent analysis system constructs an initial decision model through a machine learning algorithm; the intelligent analysis system performs multiple iterative training on the initial decision model to obtain a policy decision model, which is used to identify message change trends and attack development trends through real-time acquired security access data and attack data; the intelligent analysis system displays message change trends and attack development trends.

[0121] In this way, through machine learning algorithms, the policy decision model is continuously optimized and improved based on the user's security access data. The policy decision model is used to output the message change trend and attack development trend, providing a basis for formulating anti-attack security strategies. This solves the problem that network security cannot be measured due to the complexity of the existing network.

[0122] Based on the same inventive concept, the embodiment of the present application also provides a network device, such as Figure 4 As shown, it includes a processor 410, a transceiver 420 and a machine-readable storage medium 430, the machine-readable storage medium 430 stores machine-executable instructions that can be executed by the processor 410, and the processor 410 is prompted by the machine-executable instructions to execute the communication method provided in the embodiment of the present application. Figure 3 The communication device shown can be used as Figure 4 The network device hardware structure shown is implemented.

[0123] The computer-readable storage medium 430 may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk storage. Optionally, the computer-readable storage medium 430 may also be at least one storage device located away from the processor 410.

[0124] The processor 410 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may 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, or discrete hardware components.

[0125] In the embodiment of the present application, the processor 410 reads the machine executable instructions stored in the machine readable storage medium 430, and the machine executable instructions enable the processor 410 itself and the transceiver 420 to execute the communication method described in the aforementioned embodiment of the present application.

[0126] In addition, an embodiment of the present application provides a machine-readable storage medium 430, which stores machine-executable instructions. When called and executed by the processor 410, the machine-executable instructions prompt the processor 410 itself and the calling transceiver 420 to execute the communication method described in the aforementioned embodiment of the present application.

[0127] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0128] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0129] As for the communication device and machine-readable storage medium embodiments, since the method contents involved are basically similar to the aforementioned method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0130] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A communication method, characterized in that: The method comprises: Obtain user security access data; Based on the security access data, an initial decision model is constructed through a machine learning algorithm; Performing multiple iterations of training on the initial decision model to obtain a policy decision model, wherein the policy decision model is used to identify message change trends and attack development trends through real-time acquired security access data and attack data; Display the message change trend and the attack development trend.

2. The method according to claim 1, characterized in that The obtaining of the user's security access data specifically includes: Obtain user characteristics from business messages; Performing a legality check on the user characteristics to obtain legal user characteristics, wherein the legal user characteristics include the security access data; or; receiving a configuration instruction input by a user, wherein the configuration instruction includes the user characteristics; Performing a legality check on the user characteristics to obtain legal user characteristics, wherein the legal user characteristics include the security access data; The security access data includes user identity information, user authority information and user subject information.

3. The method according to claim 2, characterized in that After obtaining the user's security access data, the method further includes: Identifying a user feature change trend based on the security access data; Display the user feature change trend.

4. The method according to claim 1, characterized in that: The method further comprises: receiving a plurality of security policies applicable to different categories input by a user; Storing the plurality of security policies in a security repository; Inputting different security policies of the same type into the policy decision model to obtain different results of the different security policies of the same type; The difference results are displayed.

5. The method according to claim 3, characterized in that: The method further comprises: Obtain user access requirements; Update the security policy in the security library according to the message change trend, the attack development trend, the user feature change trend and the user access demand; The updated security policy is stored in the security repository, and the updated security policy is sent to the policy enforcement point.

6. A communication device, characterized in that: The device comprises: A first acquisition unit, used to acquire the user's security access data; A construction unit, configured to construct an initial decision model according to the security access data through a machine learning algorithm; A training unit, used for performing multiple iterations of training on the initial decision model to obtain a policy decision model, wherein the policy decision model is used to identify message change trends and attack development trends through real-time acquired security access data and attack data; The display unit is used to display the message change trend and the attack development trend.

7. The device according to claim 6, characterized in that The first acquisition unit is specifically used to acquire user characteristics from the service message; Performing a legality check on the user characteristics to obtain legal user characteristics, wherein the legal user characteristics include the security access data; or; receiving a configuration instruction input by a user, wherein the configuration instruction includes the user characteristics; Performing a legality check on the user characteristics to obtain legal user characteristics, wherein the legal user characteristics include the security access data; The security access data includes user identity information, user authority information and user subject information.

8. The device according to claim 7, characterized in that The device also includes: an identification unit, used to identify a user feature change trend based on the security access data; The display unit is further used to display the changing trend of the user characteristics.

9. The device according to claim 6, characterized in that The device also includes: A receiving unit, used for receiving a plurality of security policies applicable to different categories input by a user; A storage unit, used for storing the plurality of security policies in a security library; A difference unit, used for inputting different security policies of the same type into the policy decision model to obtain difference results of the different security policies of the same type; The display unit is further configured to display the difference result.

10. The device according to claim 9, characterized in that The device also includes: A second acquisition unit, used to acquire user access requirements; An updating unit, configured to update the security policy in the security library according to the message change trend, the attack development situation, the user feature change trend and the user access demand; The storage unit is also used to store the updated security policy in the security library; The sending unit is used to send the updated security policy to the policy execution point.

Citation Information

Patent Citations

  • Big data security analysis platform system based on network security

    CN108833397A

  • A security event automatic processing method based on a heterogeneous model strategy library

    CN109743300A

  • Cloud host security situation awareness system and method, equipment and storage medium

    CN112073389A

  • Cross-regional group company network security management method and system

    CN118214605A

  • Contextual zero trust network access (ZTNA) based on dynamic security posture insights

    US20220210173A1