Network security access authentication method, device, electronic device and readable storage medium
By analyzing and clustering model classification of traffic data of network access devices, combined with hierarchical authentication rules, the problem of low authentication accuracy and efficiency of network access devices in the existing technology is solved, and the rapid and accurate nature of heterogeneous devices is achieved Authentication enhances network security.
Patent Information
- Application Number
- CN202110281155.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-03-16
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-03-16
AI Technical Summary
When the existing network access equipment authentication methods face massive heterogeneous devices and diversified devices, the authentication accuracy and efficiency are low, making it difficult to effectively identify and verify the security of unknown devices.
By analyzing the traffic data of network access devices, using pre-trained clustering models for classification, and combining preset hierarchical authentication rules for authentication, rapid classification and non-invasive authentication of heterogeneous devices are achieved, and human participation is reduced , improve certification accuracy and efficiency.
It realizes rapid classification and certification of massive heterogeneous network access devices, improves the accuracy and efficiency of authentication, can effectively handle the certification of unknown devices and equipment with diversified functions, reduces human participation, and enhances network security.
Smart Images

Figure CN115085960B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of network security, and in particular relates to a data-driven network security access authentication method, device, electronic device and computer-readable storage medium. Background Art
[0002] With the in-depth development of 5G networks, a large number of heterogeneous devices will be connected to the Internet of Things as real-time data sources, and the security of network devices has received widespread attention. If unauthenticated and untrusted devices are connected to the network, many security risks will be introduced, causing other devices to be attacked or data information to be leaked. Therefore, in order to ensure the safe and stable operation of the network environment, it is necessary to identify and authenticate network access devices.
[0003] The existing authentication methods for network access devices are suitable for authenticating known access devices with fixed functions or stable behavior information. With hundreds of millions of devices connected to the network, a large number of unknown devices connected to the network, and the ever-increasing functional dimensions and complex and diverse network interaction behaviors of devices, the difficulty of device authentication has increased, resulting in low authentication accuracy and efficiency. Summary of the invention
[0004] The purpose of the embodiments of the present invention is to provide a network security access authentication method, device, electronic device and computer-readable storage medium to solve the problem of low accuracy and efficiency of the existing authentication method for network access equipment.
[0005] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:
[0006] In a first aspect, an embodiment of the present invention provides a network security access authentication method, the method comprising:
[0007] Analyze the collected traffic data of network access devices to obtain target information;
[0008] Classifying the target information based on a pre-trained clustering model to obtain the type of the target information;
[0009] Based on preset hierarchical authentication rules, the network access device is authenticated according to the type of the target information.
[0010] In a second aspect, an embodiment of the present invention provides a network security access authentication device, the device comprising:
[0011] The parsing module is used to parse the collected traffic data of the network access device to obtain the target information;
[0012] A device classification module, used to classify the target information based on a pre-trained clustering model to obtain the type of the target information;
[0013] The hierarchical authentication module is used to authenticate the network access device based on preset hierarchical authentication rules and according to the type of the target information.
[0014] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.
[0015] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.
[0016] In an embodiment of the present invention, target information is obtained by parsing the collected traffic data of the network access device, the target information is classified based on a pre-trained clustering model to obtain the type of the target information, and the network access device is authenticated according to the type of the target information based on a preset hierarchical authentication rule; the network access device is evaluated for credibility based on the authentication result of the network access device and the behavioral characteristics of the network access device, thereby achieving rapid classification and non-intrusive authentication of massive heterogeneous network access devices, reducing human participation, achieving authentication of unknown devices and devices with diverse functional behaviors, and improving the accuracy and efficiency of authentication. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 is a flow chart of a network security access authentication method provided by an embodiment of the present invention;
[0018] Figure 2 is a flow chart of a hierarchical authentication method provided by an embodiment of the present invention;
[0019] Figure 3 It is a structural diagram of a network security access authentication device provided by an embodiment of the present invention;
[0020] Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0021] 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 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.
[0022] The terms "first", "second", etc. in the specification and claims of the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.
[0023] The network security access authentication method provided by the embodiment of the present invention is described in detail below through specific embodiments and application scenarios in conjunction with the accompanying drawings.
[0024] See also Figure 1 , Figure 1 is a flow chart of a network security access authentication method provided by an embodiment of the present invention, the method is applied to electronic devices such as Figure 1 As shown, the method comprises the following steps:
[0025] Step 101, parse the collected traffic data of the network access device to obtain target information.
[0026] In the embodiment of the present invention, the network access device may include a desktop computer, a smart phone, a printer, a tablet computer, a car computer, a robot, a wearable device and other IoT access devices, and the embodiment of the present invention does not limit the type of the network access device. In this embodiment, the dynamic network traffic data of the network access device can be collected, and the collected dynamic network traffic data of the network access device can be cleaned and parsed, etc. to obtain target information, and the target information reflects the function of the network access device. For example, the target information may include source IP address, destination IP address, source port, destination port, message type and other information, and the embodiment of the present invention does not limit the content of the target information.
[0027] Step 102: classify the target information based on the pre-trained clustering model to obtain the type of the target information.
[0028] In the embodiment of the present invention, the flow data of each network access device within a period of time can be collected in advance, parsed and stored to obtain a training data set, and the preset clustering model can be trained by the training data set to obtain a trained clustering model, thereby completing the offline training of the clustering model. Among them, the preset clustering model can adopt an existing clustering algorithm, such as a k-means clustering algorithm, and the embodiment of the present invention does not limit the type of clustering algorithm adopted by the clustering model.
[0029] In an embodiment of the present invention, after obtaining a trained clustering model, the target information currently obtained by collecting traffic data of the network access device can be input into the pre-trained clustering model, and the similarity between the current target information and the centroid information of each cluster in the clustering model is calculated, wherein the greater the similarity, the higher the match between the dynamic behavior of the device corresponding to the cluster and the current target information, and the current target information belongs to the device, so the type corresponding to the cluster with the greatest similarity can be used as the type of the current target information.
[0030] Optionally, the method for calculating the similarity may be Euclidean distance, cosine similarity, mutual information, etc. The embodiment of the present invention does not limit the similarity calculation method used when classifying the clustering model. The embodiment of the present invention can classify the target information of the network access device by adopting an unsupervised learning method, overcome the disadvantage that the supervised learning method cannot be well applied to unlabeled data, can quickly and accurately classify the functions of all network access devices, improve the applicability of the clustering model, and can meet the requirements of lack of labels for data of a large number of devices in actual engineering and the requirements for simplicity and efficiency of the algorithm, providing a basis for better authentication of network access devices.
[0031] Step 103: Authenticate the network access device based on the preset hierarchical authentication rules and according to the type of target information.
[0032] In an embodiment of the present invention, by collecting traffic data of the network access device at different times, and according to the type of target information obtained from the traffic data at different times, it can be determined whether the type of target information sent by the network access device at different times has changed. For example, the different times may be the morning and evening of a day, and the embodiment of the present invention does not limit the method of selecting different times. If the type of target information sent by the network access device at different times has changed, the network access device is authenticated according to the identity information of the network access device; and if the type of target information sent by the network access device at different times has not changed, the network access device is authenticated according to the centroid information of the type to which the target information belongs and predetermined benchmark information. Among them, the predetermined benchmark information is the target information corresponding to the successfully authenticated network access device when the network access device is authenticated through the identity information.
[0033] In an embodiment of the present invention, target information is obtained by parsing the collected traffic data of the network access device; the target information is classified based on a pre-trained clustering model to obtain the type of the target information; based on preset hierarchical authentication rules, the network access device is authenticated according to the type of the target information, thereby realizing rapid classification and non-intrusive authentication of massive heterogeneous network access devices, reducing human participation, and improving the accuracy and efficiency of authentication.
[0034] Optionally, the authenticating the network access device according to the centroid information of the type to which the target information belongs and the predetermined reference information may include:
[0035] Determine a first similarity between the target information and the centroid information, and determine whether the first similarity is less than a first preset threshold. If the first similarity is less than the first preset threshold, determine that the authentication of the network access device is successful; if the first similarity is greater than or equal to the first preset threshold, determine a second similarity between the target information and all predetermined reference information, and determine whether there is a second similarity less than the second preset threshold;
[0036] If there is a second similarity less than the second preset threshold, it is determined that the authentication of the network access device is successful; and if all the determined second similarities are greater than or equal to the second preset threshold, the network access device is authenticated according to the identity information of the network access device.
[0037] In the embodiment of the present invention, the network access device has identifiable identification information, such as Media Access Control Address (MAC address), International Mobile Equipment Identity (IMEI), shared secret or certificate, etc., which can be used for identity authentication to establish an initial trust relationship. The reference information refers to the target information corresponding to the network access device that is successfully authenticated by the identity information. That is to say, by using the target information of the trusted device after the identity information is authenticated as the reference point, the shortcomings of the existing authentication method that cannot handle the authentication of unknown devices that access the network for the first time and the shortcomings of the existing authentication method that cannot handle the authentication of devices with diverse functional behaviors when the behavior of the device accessing the network changes normally can be solved, thereby improving the accuracy and efficiency of authentication. Optionally, the method for calculating the similarity can adopt Euclidean distance, cosine similarity, mutual information, etc. The embodiment of the present invention does not limit the similarity calculation method used in hierarchical authentication.
[0038] like Figure 2As shown, it is a flowchart of a hierarchical authentication method provided by an embodiment of the present invention, and the method includes the following steps: according to the classified target information, determine whether the type of the current target information of the device has changed. If it has changed, perform identity authentication. If it has not changed, determine whether the Euclidean distance d between the current target information and the centroid information of the type to which it belongs is less than a preset threshold D1. If d is less than D1, it means that the degree of conformity to the type to which it belongs is high, and the device authentication is successful. If d is greater than or equal to D1, respectively calculate the Euclidean distance d between the current target information and all the reference information (d=(d1, d2,…, d n ), determine whether all elements in d are greater than or equal to a preset threshold D2.
[0039] If any element in d is less than the preset threshold D2, the device authentication is successful. If all elements in d are greater than or equal to the preset threshold D2, it means that the device behavior reliability is weak and the device needs to be authenticated.
[0040] By authenticating the device. If the device authentication succeeds, the current target information is used as the reference information. Otherwise, the device authentication fails.
[0041] Optionally, after authenticating the network access device according to the type of target information based on preset hierarchical authentication rules, the credibility of the network access device may also be evaluated based on the authentication result of the network access device and the behavioral characteristics of the network access device.
[0042] Furthermore, when conducting a credibility assessment on a network access device, the membership of each evaluation indicator in the evaluation indicator set to each evaluation level in the quantitative evaluation set can be determined based on an evaluation indicator set constructed by the authentication results of the network access device and the behavioral characteristics of the network access device, and a quantitative evaluation set constructed by preset evaluation levels that reflect the frequency of occurrence of the evaluation indicators, to obtain a membership matrix, and based on the preset evaluation indicator weight set and the membership matrix, a credibility assessment vector can be determined, and based on the credibility assessment vector, the credibility of the network access device can be evaluated.
[0043] In an embodiment of the present invention, multiple evaluation indicators can be established in advance according to the authentication results of the network access device and the behavioral characteristics of the network access device to construct an evaluation indicator set. Based on expert knowledge, the established evaluation indicators may include: hierarchical authentication results, IP message accuracy, TCP message accuracy, data accuracy, and data crash rate. Optionally, the CRC checksum of the IP header and TCP header of the message in the traffic data can be detected to determine whether a transmission error occurs in the message, thereby obtaining the IP message accuracy and TCP message accuracy, and the data accuracy and data crash rate can be obtained according to the ACK and RESET in the TCP message flag. The constructed evaluation indicator set U = (u1, u2, u3, u4, u5), where u1 is the hierarchical authentication result, u2 is the IP message accuracy, u3 is the TCP message accuracy, u4 is the data accuracy, and u5 is the data crash rate.
[0044] In an embodiment of the present invention, an evaluation level reflecting the frequency of occurrence of the evaluation index can be preset, and a quantitative evaluation set can be constructed according to the preset evaluation level. For example, the constructed quantitative evaluation set V = (v1, v2, v3, v4, v5), wherein v1, v2, v3, v4, v5 represent level one, level two, level three, level four, and level five, respectively. The evaluation index, i.e., the hierarchical authentication result, the IP message correctness rate, the TCP message correctness rate, the data accuracy rate, and the data crash rate, can be quantified to the corresponding level by the preset evaluation level, and the quantification details can refer to the network security standard specification or the actual situation. In some optional examples, the quantification standard is a quantitative evaluation set as shown in Table 1.
[0045] Table 1
[0046] evaluate Level 1 Level 2 Level 3 Level 4 Level 5 Level m 1 2 3 4 5 <![CDATA[Y i (Frequency)]]> <![CDATA[y i >0.02]]> <![CDATA[0.02>and i >0.01]]> <![CDATA[0.01>and i >0.002]]> <![CDATA[0.002>and i >0.001]]> <![CDATA[y i <0.001]]>
[0047] In the embodiment of the present invention, the membership of each evaluation index in the evaluation index set to each evaluation level in the quantitative evaluation set can be determined according to the evaluation index set and the quantitative evaluation set to obtain a membership matrix. For example, the obtained membership matrix R, where r ij Represents each evaluation index set u in the evaluation index set U i For each evaluation level v in the quantitative evaluation set V j The membership degree of u i The fuzzy relationship from V to V is obtained, and the membership matrix R is obtained.
[0048]
[0049] Among them, S ijIt indicates the number of times the i-th evaluation index is rated as evaluation level j, and S indicates the total number of evaluations. According to the preset evaluation index weight set w and the membership matrix R, it is determined that the credibility evaluation vector b is a 1*5 vector, and the credibility of the network access device can be evaluated according to the credibility evaluation vector b.
[0050] b=wR (Formula 2)
[0051] Optionally, the element with the largest value in the credibility evaluation vector b is selected, and the selected element is matched with the preset trust level to determine the trust level of the network access device; or the sum of the products of each element in the credibility evaluation vector b and the preset scores of each corresponding evaluation level can be determined as the trust score Q of the network access device, and the trust score Q is matched with the preset trust level to determine the trust level of the network access device.
[0052]
[0053] Among them, δ j Indicates the preset scores of each evaluation level, such as 100, 80, 60, 40, 20, b j Represents the jth element in vector b. By scoring the trust of network access devices, we can not only obtain the credibility of the current message of the access device, but also give the trust level of the device more objectively by analyzing the historical trust score of the device. When the trust score of the device fluctuates greatly, the device authentication warning can be given in advance to improve the security of authentication. Therefore, sustainable trust evaluation of the device through trust scoring can avoid the problem that the legitimacy change of the device caused by the existing single authentication cannot be perceived in time. In addition, by continuously evaluating the trust level and credibility of the device, it can also provide theoretical support for operators to perform fine-grained permission allocation and access control on the device, and can perform fine-grained permission management according to business needs, so as to carry out subsequent security isolation, manual inspection and other disposal.
[0054] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a network security access authentication device provided by an embodiment of the present invention, the device is applied to electronic devices such as Figure 3 As shown, the network security access authentication device 300 may include:
[0055] The analysis module 310 is used to analyze the collected traffic data of the network access device to obtain target information.
[0056] The device classification module 320 is used to classify the target information based on a pre-trained clustering model to obtain the type of the target information.
[0057] The hierarchical authentication module 330 is used to authenticate the network access device based on the preset hierarchical authentication rules and according to the type of target information.
[0058] Optionally, the hierarchical authentication module 330 includes:
[0059] A judging unit, configured to judge whether the type of target information sent by the network access device at different times changes according to the type of the target information;
[0060] A first authentication unit, configured to authenticate the network access device according to the identity information of the network access device when the type of target information sent by the network access device at different times changes;
[0061] The second authentication unit is used to authenticate the network access device according to the centroid information of the type of the target information and predetermined reference information when the type of the target information sent by the network access device at different times does not change, wherein the reference information is the target information corresponding to the successfully authenticated network access device when the network access device is authenticated through identity identification information.
[0062] Optionally, the second authentication unit includes:
[0063] A first judgment subunit is used to determine a first similarity between the target information and the centroid information, and to determine whether the first similarity is less than a first preset threshold;
[0064] A first authentication subunit, configured to determine that the authentication of the network access device is successful when the first similarity is less than a first preset threshold;
[0065] A second judgment subunit is used to determine a second similarity between the target information and the predetermined reference information when the first similarity is greater than or equal to the first preset threshold, and to determine whether there is a second similarity less than the second preset threshold;
[0066] A second authentication subunit, configured to determine that the authentication of the network access device is successful when there is a second similarity less than a second preset threshold;
[0067] The first authentication unit is further configured to authenticate the network access device according to the identity information of the network access device when all the determined second similarities are greater than or equal to a second preset threshold.
[0068] Optionally, the network security access authentication device 300 may further include:
[0069] The trust evaluation module is used to evaluate the credibility of the network access device according to the authentication result of the network access device and the behavior characteristics of the network access device.
[0070] Optionally, the trust evaluation module 340 includes:
[0071] The data processing unit is used to determine the membership of each evaluation indicator in the evaluation indicator set to each evaluation level in the quantitative evaluation set according to the evaluation indicator set constructed by the authentication result of the network access device and the behavior characteristics of the network access device, and the quantitative evaluation set constructed by the preset evaluation level reflecting the frequency of occurrence of the evaluation indicator, so as to obtain a membership matrix; determine the credibility evaluation vector according to the preset evaluation indicator weight set and the membership matrix;
[0072] The credibility evaluation unit is used to evaluate the credibility of the network access device according to the credibility evaluation vector.
[0073] Optionally, the credibility evaluation unit is used to select the element with the largest value in the credibility evaluation vector; match the selected element with a preset trust level to determine the trust level of the network access device, and the trust level is used as the credibility of the network access device; or,
[0074] Optionally, the credibility assessment unit is used to determine the sum of the products of each element in the credibility assessment vector and the preset scores of each corresponding evaluation level as the trust score of the network access device; match the trust score with the preset trust level to determine the trust level of the network access device, and the trust level is used as the credibility of the network access device.
[0075] It is understandable that the network security access authentication device 300 of the embodiment of the present invention can implement the above Figure 1 , Figure 2 The various processes of the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.
[0076] In addition, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program can achieve the above-mentioned Figure 1 , Figure 2 The various processes of the method embodiment shown can achieve the same technical effect, and to avoid repetition, they will not be described again here.
[0077] See also Figure 4 As shown, an embodiment of the present invention further provides an electronic device 40 , including a bus 41 , a transceiver 42 , an antenna 43 , a bus interface 44 , a processor 45 and a memory 46 .
[0078] In the embodiment of the present invention, the electronic device 40 further includes: a program or instruction stored in the memory 46 and executable on the processor 45. Optionally, when the program or instruction is executed by the processor 45, the following steps may be implemented:
[0079] Analyze the collected traffic data of network access devices to obtain target information;
[0080] Classifying the target information based on a pre-trained clustering model to obtain the type of the target information;
[0081] Based on preset hierarchical authentication rules, the network access device is authenticated according to the type of the target information.
[0082] It is understandable that when the computer program is executed by the processor 45, the above Figure 1 , Figure 2 The various processes of the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.
[0083] exist Figure 4 In the embodiment, a bus architecture (represented by bus 41) is shown, and bus 41 may include any number of interconnected buses and bridges, and bus 41 links together various circuits including one or more processors represented by processor 45 and memory represented by memory 46. Bus 41 may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 44 provides an interface between bus 41 and transceiver 42. Transceiver 42 may be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. Data processed by processor 45 is transmitted on a wireless medium via antenna 43, and further, antenna 43 also receives data and transmits the data to processor 45.
[0084] The processor 45 is responsible for managing the bus 41 and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management and other control functions. The memory 46 can be used to store data used by the processor 45 when performing operations.
[0085] Optionally, the processor 45 may be a CPU, an ASIC, an FPGA or a CPLD.
[0086] The embodiment of the present invention further provides a computer-readable storage medium having a program or instruction stored thereon, which can implement the above-mentioned Figure 1 , Figure 2 The various processes of the method embodiment shown can achieve the same technical effect, and to avoid repetition, they will not be described again here.
[0087] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0088] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.
[0089] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0090] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a service classification device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0091] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A network security access authentication method, characterized in that: include: Analyze the collected traffic data of network access devices to obtain target information; Classifying the target information based on a pre-trained clustering model to obtain the type of the target information; authenticating the network access device based on a preset hierarchical authentication rule and according to the type of the target information; The authenticating the network access device based on the preset hierarchical authentication rules and according to the type of the target information includes: determining, according to the type of the target information, whether the type of the target information sent by the network access device at different times changes; If the type of target information sent by the network access device at different times changes, authenticating the network access device according to the identity information of the network access device; If the type of target information sent by the network access device at different times does not change, the network access device is authenticated based on the centroid information of the type of the target information and predetermined benchmark information; wherein, the benchmark information is the target information corresponding to the successfully authenticated network access device when the network access device is authenticated through identity identification information.
2. The method according to claim 1, characterized in that The authenticating the network access device according to the centroid information of the type to which the target information belongs and predetermined reference information includes: Determining a first similarity between the target information and the centroid information, and determining whether the first similarity is less than a first preset threshold; If the first similarity is less than a first preset threshold, determining that the authentication of the network access device is successful; or, If the first similarity is greater than or equal to a first preset threshold, determining a second similarity between the target information and all predetermined reference information, and determining whether there is a second similarity less than a second preset threshold; If there is a second similarity that is less than the second preset threshold, it is determined that the authentication of the network access device is successful; or, if the determined second similarities are greater than or equal to the second preset threshold, the network access device is authenticated according to the identity identification information of the network access device.
3. The method according to claim 1 or 2, characterized in that The method further comprises: Performing a credibility assessment on the network access device based on the authentication result of the network access device and the behavior characteristics of the network access device.
4. The method according to claim 3, characterized in that The performing credibility assessment on the network access device according to the authentication result of the network access device and the behavior characteristics of the network access device includes: Determining, based on an evaluation indicator set constructed from an authentication result of the network access device and behavioral characteristics of the network access device, and a quantitative evaluation set constructed from preset evaluation levels reflecting the frequency of occurrence of the evaluation indicators, the membership of each evaluation indicator in the evaluation indicator set to each evaluation level in the quantitative evaluation set, thereby obtaining a membership matrix; Determining a credibility evaluation vector based on a preset evaluation index weight set and the membership matrix; The credibility of the network access device is evaluated according to the credibility evaluation vector.
5. The method according to claim 4, characterized in that The step of evaluating the credibility of the network access device according to the credibility evaluation vector includes: Selecting the element with the largest value in the credibility evaluation vector; Matching the selected element with a preset trust level to determine the trust level of the network access device, wherein the trust level serves as the credibility of the network access device; or Determining the sum of the products of each element in the credibility evaluation vector and the corresponding preset scores of each evaluation level as the trust score of the network access device; The trust score is matched with a preset trust level to determine the trust level of the network access device, and the trust level serves as the credibility of the network access device.
6. A network security access authentication device, characterized in that: include: The parsing module is used to parse the collected traffic data of the network access device to obtain the target information; a device classification module, configured to classify the target information based on a pre-trained clustering model to obtain the type of the target information; a hierarchical authentication module, configured to authenticate the network access device based on a preset hierarchical authentication rule and according to the type of the target information; The hierarchical authentication module includes: a judging unit, configured to judge, based on the type of the target information, whether the type of the target information sent by the network access device at different times changes; a first authentication unit, configured to authenticate the network access device according to the identity information of the network access device when the type of target information sent by the network access device at different times changes; The second authentication unit is used to authenticate the network access device according to the centroid information of the type of the target information and predetermined benchmark information when the type of the target information sent by the network access device at different times does not change, wherein the benchmark information is the target information corresponding to the successfully authenticated network access device when the network access device is authenticated through identity identification information.
7. The device according to claim 6, characterized in that The second authentication unit includes: a first judging subunit, configured to determine a first similarity between the target information and the centroid information, and to determine whether the first similarity is less than a first preset threshold; a first authentication subunit, configured to determine that authentication of the network access device is successful when the first similarity is less than a first preset threshold; a second judging subunit, configured to, when the first similarity is greater than or equal to a first preset threshold, determine a second similarity between the target information and all predetermined reference information, and to determine whether there is a second similarity less than a second preset threshold; a second authentication subunit, configured to determine that authentication of the network access device is successful when a second similarity less than a second preset threshold exists; The first authentication unit is further configured to authenticate the network access device according to the identity information of the network access device when the determined second similarities are both greater than or equal to a second preset threshold.
8. The device according to claim 6 or 7, characterized in that Also includes: The trust evaluation module is used to evaluate the credibility of the network access device based on the authentication result of the network access device and the behavior characteristics of the network access device.
9. The device according to claim 8, characterized in that The trust evaluation module includes: a data processing unit configured to determine, based on an evaluation indicator set constructed from an authentication result of the network access device and behavioral characteristics of the network access device, and a quantitative evaluation set constructed from preset evaluation levels reflecting the frequency of occurrence of the evaluation indicators, the membership of each evaluation indicator in the evaluation indicator set to each evaluation level in the quantitative evaluation set, thereby obtaining a membership matrix; and determine a credibility evaluation vector based on a preset evaluation indicator weight set and the membership matrix; A credibility evaluation unit is configured to evaluate the credibility of the network access device according to the credibility evaluation vector.
10. The device according to claim 9, characterized in that The credibility evaluation unit is configured to: select the element with the largest value in the credibility evaluation vector; match the selected element with a preset trust level to determine the trust level of the network access device, and use the trust level as the credibility of the network access device; or The credibility evaluation unit is used to: determine the sum of the products of each element in the credibility evaluation vector and the scores preset for each corresponding evaluation level as the trust score of the network access device; The trust score is matched with a preset trust level to determine the trust level of the network access device, and the trust level serves as the credibility of the network access device.
11. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the network security access authentication method according to any one of claims 1 to 5.
12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the network security access authentication method according to any one of claims 1 to 5 are implemented.
