WO2018119950A1

WO2018119950A1 - Access control method and apparatus

Info

Publication number: WO2018119950A1
Application number: PCT/CN2016/113259
Authority: WO
Inventors: 王洁
Original assignee: 深圳天珑无线科技有限公司
Priority date: 2016-12-29
Filing date: 2016-12-29
Publication date: 2018-07-05

Abstract

Provided are an access control method and apparatus, relating to the technical field of wireless communications. On the one hand, in the embodiments of the present application, the method comprises: constructing, according to an access request, a radio frequency fingerprint characteristic vector corresponding to an access device; then according to the radio frequency fingerprint characteristic vector and a radio frequency fingerprint library, obtaining a classification vector of the access device by means of a sparse classification model; then obtaining, according to the classification vector and a sparse reconstruction algorithm, a reconstruction vector corresponding to the classification vector; and finally, if the maximum element value in the reconstruction vector is greater than a pre-set threshold value, allowing the access of the access device. In this way, the radio frequency fingerprint information generated by a wireless routing device serves as the only characteristic, and then whether to allow the access of the access device is determined according to the uniqueness of the radio frequency fingerprint characteristic. Therefore, the technical solution provided by the embodiments of the present application can fundamentally solve the security risks caused by key leakage, and furthermore, there is no need to provide other third-party access authentication devices.

Description

Access control method and device

Technical field

The present application relates to the field of wireless communications technologies, and in particular, to an access control method and apparatus.

Background technique

With the development of wireless communication technology, the use rate of short-range wireless communication is also getting higher and higher. Among them, WIFI, as a technology that allows access devices to connect to a wireless local area network, has become one of the most commonly used short-range wireless communication methods. As the basic device of the WiFi network, the wireless routing device determines the performance of the WiFi network. Due to the openness of the wireless environment, any wireless terminal device in the vicinity of the wireless router can receive the wireless signal and access the WiFi network through the wireless router device, thereby affecting the security of the WiFi network. At present, the most common solution is to use the WPA-PSK/WPA2-PSK method to set the 8-64-bit key to achieve access authentication for the device to connect to the wireless router. This method is less secure and easy. A situation where a key is leaked.

On the basis of this, a person skilled in the art proposes a method for completing authentication by using a third-party authentication server. Specifically, the user equipment first logs in to the third-party authentication server, and simultaneously sends the wireless routing device identification information to be connected to the third-party authentication server. The third-party authentication server then generates an identification information to be sent to the wireless routing device and the user equipment, and the user equipment connects and logs in to the wireless routing device based on the flag information.

In the process of implementing the present application, the inventors found that at least the following problems exist in the prior art:

In the prior art, the method for dynamically generating an authentication code reduces the security risk caused by the password leakage to a certain extent, but is still essentially a key-based authentication mechanism, and does not fundamentally solve the network security risk caused by the key leakage. .

Summary of the invention

In view of this, the embodiment of the present application provides an access control method and apparatus, which are used to solve the network security problem caused by the secret routing key leakage of the wireless routing device based on the key access authentication mechanism in the prior art.

On the one hand, the embodiment of the present application provides an access control method, which is applied to a wireless routing device pre-equipped with a radio frequency fingerprint database, and the method includes:

Constructing a radio frequency fingerprint feature vector of the corresponding access device according to the access request;

Deriving a classification vector of the access device by using a sparse classification model according to the radio frequency fingerprint feature vector and the radio frequency fingerprint database;

Deriving a reconstruction vector corresponding to the classification vector according to the classification vector and the sparse reconstruction algorithm;

If the maximum element value in the reconstructed vector is greater than a preset threshold, the access device is allowed to access.

The aspect as described above and any possible implementation manner further provide an implementation manner, where the method further includes:

If the maximum element value in the reconstructed vector is less than or equal to the preset threshold, access device access is prohibited.

The foregoing aspect, and any possible implementation manner, further provide an implementation manner, before the acquiring the radio frequency fingerprint feature vector of the access device, the method further includes:

Collecting an I/Q amplitude offset and a carrier frequency offset of the pre-authorized device under the M carrier modulated signals as a set of radio frequency fingerprint feature vectors of the pre-authorized device;

Adding a feature set of the radio frequency fingerprint formed by the N sets of radio frequency fingerprint feature vectors collected continuously to the current radio frequency fingerprint database;

Wherein M and N are integers greater than one.

The aspect as described above, and any possible implementation manner, further provide an implementation manner, the radio frequency fingerprint feature vector of the corresponding access device is configured according to the access request, including:

When receiving the access request of the access device, collecting the I/Q amplitude offset and the carrier frequency offset of the access device under the M carrier modulated signals in the current time period, as the radio frequency fingerprint of the access device Feature vector.

The aspect as described above, and any possible implementation manner, further providing an implementation manner, according to the radio frequency fingerprint feature vector and the radio frequency fingerprint database, obtaining a classification vector of the access device by using a sparse classification model includes:

according to

The model derives the classification vector of the access device, where

For the RF fingerprint feature vector, M is the RF fingerprint library, and C is the classification vector.

The aspect as described above, and any possible implementation manner, further provide an implementation manner, according to the classification vector and the sparse reconstruction algorithm, the reconstruction vector corresponding to the classification vector is:

According to the equations

The original reconstructed vector is obtained, where ∈ is the reconstructed noise,

Is the original reconstructed vector, which is a column vector composed of N*K elements, and K is the number of authorized devices in the radio frequency fingerprint library M;

Each successive N elements in the original reconstructed vector are sequentially added to obtain a reconstructed vector composed of K elements.

One of the above technical solutions has the following beneficial effects:

An access control method provided by an embodiment of the present application is applied to a wireless routing device pre-configured with a radio frequency fingerprint database, first constructing a radio frequency fingerprint feature vector of the corresponding access device according to the access request, and then based on the radio frequency fingerprint feature Vector and RF fingerprint database, the classification vector of the access device is obtained by sparse classification algorithm, and finally the classification vector is reconstructed by the sparse reconstruction algorithm. If the maximum element value in the reconstruction vector is greater than a preset threshold, the connection is allowed. Access to the device. Compared with the current access authentication method, the present application is based on the characteristics of the access terminal device's own radio frequency circuit. The wireless routing device generates a unique radio frequency fingerprint feature, which is used to determine whether the access device is allowed to access according to the uniqueness of the radio frequency fingerprint feature, thereby fundamentally solving the security risk caused by the secret key leakage, and also does not need to provide other Third-party access authentication device.

On the other hand, the embodiment of the present application provides an access control device, which is applied to a wireless routing device that is pre-equipped with a radio frequency fingerprint database, and the device includes:

a constructing module, configured to construct a radio frequency fingerprint feature vector of the corresponding access device according to the access request;

a first calculating module, configured to obtain, according to the radio frequency fingerprint feature vector and the radio frequency fingerprint library, a classification vector of the access device by using a sparse classification model;

a second calculating module, configured to obtain, according to the classification vector and the sparse reconstruction algorithm, a reconstruction vector corresponding to the classification vector;

The processing module is configured to allow the access device to access if the maximum element value in the reconstructed vector is greater than a preset threshold.

The above-mentioned aspect and any possible implementation manner further provide an implementation manner, where the processing module is further configured to:

The above-mentioned aspect and any possible implementation manner further provide an implementation manner, the device further includes:

An acquisition module, configured to collect an I/Q amplitude offset and a carrier frequency offset of the pre-authorized device under the M carrier modulated signals, as a set of radio frequency fingerprint feature vectors of the pre-authorized device;

Wherein M and N are integers greater than one.

An aspect of the foregoing, and any possible implementation, further provide an implementation, where the constructing module is specifically configured to:

An aspect of the foregoing, and any possible implementation manner, further provide an implementation manner, where the first computing module is specifically configured to:

according to

The model derives the classification vector of the access device, where

The foregoing aspect and any possible implementation manner further provide an implementation manner, where the two computing modules are specifically configured to:

According to the equations

One of the above technical solutions has the following beneficial effects:

The access control device provided in the embodiment of the present application is applied to a wireless routing device pre-equipped with a radio frequency fingerprint database. First, the constructing module constructs a radio frequency fingerprint feature vector of the corresponding access device according to the access request, and the first computing module Based on the radio frequency fingerprint feature vector and the radio frequency fingerprint database, the classification vector of the access device is obtained by a sparse classification algorithm, and then the first calculation module reconstructs the classification vector by a sparse reconstruction algorithm. Finally, the processing module is When the maximum element value in the reconstructed vector is greater than the preset threshold, the access device is allowed to access. Compared with the current access authentication device, the present application is based on the characteristics of the radio circuit of the access terminal device and is generated by the wireless routing device. The unique radio frequency fingerprint feature is used to determine whether the access device is allowed to access according to the uniqueness of the radio frequency fingerprint feature, thereby fundamentally solving the security risk caused by the key leakage, and does not need to provide other third-party access. Enter the certified device.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present application. One of ordinary skill in the art can also obtain other drawings based on these drawings without paying for inventive labor.

1 is a schematic flow chart of Embodiment 1 of the present application;

2 is a schematic flowchart of an authorization phase of the second embodiment of the present application;

3 is a schematic flowchart of an access phase in Embodiment 2 of the present application;

4 is a schematic structural view of Embodiment 4 of the present application.

detailed description

For a better understanding of the technical solutions of the present application, the embodiments of the present application are described in detail below with reference to the accompanying drawings.

It should be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

The terms used in the embodiments of the present application are for the purpose of describing particular embodiments only, and are not intended to limit the application. The singular forms "a", "the", and "the" The ground indicates other meanings.

It should be understood that the term "and/or" as used herein is merely an association describing the associated object, indicating that there may be three relationships, for example, A and/or B, which may indicate that A exists separately, while A and B, there are three cases of B alone. In addition, the character "/" in this article generally indicates that the contextual object is an "or" relationship.

It should be understood that although the terms first, second, third, etc. may be used to describe the computing modules in the embodiments of the present application, these computing modules should not be limited to these terms. These terms are only used to distinguish computing modules from one another. For example, the first computing module may also be referred to as a second computing module without departing from the scope of the embodiments of the present application. Similarly, the second computing module may also be referred to as a first computing module.

Depending on the context, the word "if" as used herein may be interpreted as "when" or "when" or "in response to determining" or "in response to detecting." Similarly, depending on the context, the phrase "if determined" or "if detected (conditions or events stated)" may be interpreted as "when determined" or "in response to determination" or "when detected (stated condition or event) "Time" or "in response to a test (condition or event stated)".

Embodiment 1

An embodiment of the present application provides an access control method. Referring to FIG. 1 , it is a schematic flowchart of a method provided by an embodiment of the present application. As shown in FIG. 1 , the method includes the following steps:

S101. Construct a radio frequency fingerprint feature vector of the corresponding access device according to the access request.

Specifically, when receiving the access request of the access device, collecting an I/Q amplitude offset and a carrier frequency offset of the access device under the M carrier modulated signals in the current time period, as an access device RF fingerprint feature vector. RF fingerprint feature vector of the access device

able to pass

Performing a representation, wherein ΔIQ _M is an I/Q amplitude offset of the access device under the M carrier modulated signals in the current time period, and Δf _M is a carrier of the access device under the M carrier modulated signals in the previous time period Frequency offset.

S102. Obtain a classification vector of the access device by using a sparse classification model according to the radio frequency fingerprint feature vector and the radio frequency fingerprint database.

It should be noted that, before the S101, the wireless fingerprint device controls the wireless routing device to enter the authorization mode by the web control interface of the wireless routing device, and the wireless routing device searches for the pre-authorization device connected to itself, and then authorizes by the following steps:

1) collecting an I/Q amplitude offset and a carrier frequency offset of the pre-authorized device under the M carrier modulated signals as a set of radio frequency fingerprint feature vectors of the pre-authorized device;

2) adding the feature set of the radio frequency fingerprint formed by the N sets of radio frequency fingerprint feature vectors collected continuously to the current radio frequency fingerprint database;

Wherein M and N are integers greater than one.

For example, if there are currently K authorized devices, the RF fingerprint database M can be expressed as

among them,

Indicates the Nth group radio frequency fingerprint feature vector of the kth authorized device.

It should be noted that the sparse classification model is used.

Line, in which,

To request the radio frequency fingerprint feature vector of the access device, M is a radio frequency fingerprint database, and C is a classification vector for requesting access devices.

S103. Obtain a reconstruction vector corresponding to the classification vector according to the classification vector.

It should be noted that, after the classification vector is obtained in S102, the classification vector is reconstructed by a sparse reconstruction algorithm to obtain a reconstruction vector. The specific steps include:

1) According to the equations

2) Adding successively N consecutive elements in the original reconstructed vector to obtain a reconstructed vector composed of K elements.

S104. If the maximum element value in the reconstructed vector is greater than a preset threshold, the access device is allowed to access.

It should be noted that the setting range of the preset threshold η is (0.8, 1), if the reconstruction vector

The maximum element value in the medium is greater than the preset threshold η, allowing the access device to be accessed; if the vector is reconstructed

The maximum element value in the medium is less than or equal to the preset threshold η, and the access device is prohibited from being accessed.

Therefore, if the maximum element value in the reconstructed vector is less than or equal to the preset threshold, the access device is prohibited from accessing.

The technical solution of the embodiment of the present application has the following beneficial effects:

An access control method provided by an embodiment of the present application is applied to a wireless routing device pre-configured with a radio frequency fingerprint database, first constructing a radio frequency fingerprint feature vector of the corresponding access device according to the access request, and then based on the radio frequency fingerprint feature Vector and RF fingerprint database, the classification vector of the access device is obtained by the sparse classification model, and finally the classification vector is reconstructed by the sparse reconstruction algorithm. If the maximum element value in the reconstruction vector is greater than the preset threshold, the connection is allowed. Access to the device. Compared with the current access control method, the present application generates a unique radio frequency fingerprint feature according to the characteristics of the radio circuit of the access terminal device, and determines whether the access device is allowed to be connected according to the uniqueness of the radio frequency fingerprint feature. Into, and thus fundamentally solve the security risks caused by the secret key leakage, and there is no need to provide other third-party access authentication devices.

It should be noted that the terminals involved in the embodiments of the present application may include, but are not limited to, a personal computer (PC), a personal digital assistant (PDA), a wireless handheld device, a tablet computer, and a tablet computer. Mobile phones, MP3 players, MP4 players, etc.

It should be noted that the execution body of S101 to S104 may be an access control device, and the device The application unit may be located in the application of the local terminal, or may be a plug-in or a software development kit (SDK) in the application of the local terminal, which is not specifically limited in this embodiment of the present application.

It is to be understood that the application may be an application (nativeApp) installed on the terminal, or may be a web application (webApp) of the browser on the terminal, which is not limited by the embodiment of the present application.

Embodiment 2

Based on the access control method provided in the foregoing Embodiment 1, the embodiment of the present application further illustrates the method of the present application by using a specific terminal device. First, select 3 Huawei Mate7 mobile phones, 3 Apple iphone6 mobile phones, 3 Nexus mobile phones, 2 Thinkpad X240 computers, 2 Ipad3s as mobile terminal devices, and then use USRP supporting 802.11n as a wireless routing device. For OFDM communication, each test carrier uses 16QAM modulation.

As shown in FIG. 2, the web control interface of the wireless routing device controls the wireless routing device to enter the authorization mode, and the wireless routing device searches for the pre-authorization device connected to itself, and then performs authorization by the following steps:

1) collecting an I/Q amplitude offset and a carrier frequency offset of the pre-authorized device under 30 carrier modulated signals as a set of radio frequency fingerprint feature vectors of the pre-authorized device;

2) using the feature set of the radio frequency fingerprint formed by the 10 sets of radio frequency fingerprint feature vectors collected continuously as the radio frequency fingerprint library;

At present, a total of 13 authorized devices constitute a radio frequency fingerprint database M, and the radio frequency fingerprint database M can be expressed as

There are 130 sets of radio frequency fingerprint feature data in the RF fingerprint database M.

As shown in Figure 3, the wireless routing device enters the access mode. When requesting the access device to request access, determine whether to allow access by the following steps:

1) The wireless router responds and measures the radio frequency fingerprint feature vector of the access device according to the access request of the access device

It can be expressed as

2) Sparse classification model

Calculate the RF fingerprint feature vector

Corresponding classification vector C;

3) According to the equations

Is the original reconstructed vector, which is a column vector consisting of 130 elements;

4) Adding successively 10 elements in the original reconstructed vector to obtain a reconstructed vector composed of 13 elements

5) If the reconstruction vector

The test results were tested using the above 13 devices. Each device was randomly connected 100 times, and the total correct access rate reached 99%. At the same time, 4 Xiaomi mobile phones and 3 X230 laptops were used without authorization. Attempts to access the wireless router, all identified as illegal devices and prohibited access.

Embodiment 3

Based on the access control method provided in the foregoing embodiment, the embodiment of the present application further provides an apparatus embodiment for implementing the steps and methods in the foregoing method embodiments.

Please refer to FIG. 4 , which is a functional block diagram of a multi-antenna system correlation coefficient calculation apparatus according to an embodiment of the present application. As shown in Figure 4, the device comprises:

The constructing module 410 is configured to construct a radio frequency fingerprint feature vector of the corresponding access device according to the access request;

The first calculating module 420 is configured to pass the radio frequency fingerprint feature vector and the radio frequency fingerprint database. The classification vector of the access device is obtained by the sparse classification model;

a second calculating module 430, configured to obtain, according to the classification vector and the sparse reconstruction algorithm, a reconstruction vector corresponding to the classification vector;

The processing module 440 is configured to allow the access device to access if the maximum element value in the reconstructed vector is greater than a preset threshold.

In a specific implementation process, the processing module is further configured to:

In a specific implementation process, the device further includes:

Wherein M and N are integers greater than one.

In a specific implementation process, the constructing module is specifically configured to:

In a specific implementation process, the first computing module is specifically configured to:

according to

The model derives the classification vector of the access device, where

In a specific implementation process, the second computing module is specifically configured to:

According to the equations

One of the above technical solutions has the following beneficial effects:

The access control device provided in the embodiment of the present application is applied to a wireless routing device pre-equipped with a radio frequency fingerprint database. First, the constructing module constructs a radio frequency fingerprint feature vector of the corresponding access device according to the access request, and the first computing module Based on the radio frequency fingerprint feature vector and the radio frequency fingerprint database, the classification vector of the access device is obtained by a sparse classification algorithm, and then the first calculation module reconstructs the classification vector by a sparse reconstruction algorithm. Finally, the processing module is When the maximum element value in the reconstructed vector is greater than the preset threshold, the access device is allowed to access. Compared with the current access authentication device, the present application generates a unique radio frequency fingerprint feature through the wireless routing device according to the characteristics of the radio circuit of the access terminal device, and determines whether the access device is allowed to be connected according to the uniqueness of the radio frequency fingerprint feature. Into, and thus fundamentally solve the security risks caused by the secret key leakage, and there is no need to provide other third-party access authentication devices.

A person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the system, the device and the unit described above can refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.

In the several embodiments provided by the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined. Or it can be integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.

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, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

The above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present application. Part of the steps. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

The above is only the preferred embodiment of the present application, and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc., which are made within the spirit and principles of the present application, should be included in the present application. Within the scope of protection.

Claims

An access control method, which is applied to a wireless routing device pre-equipped with a radio frequency fingerprint database, the method comprising:

Constructing a radio frequency fingerprint feature vector of the corresponding access device according to the access request;

Deriving a classification vector of the access device by using a sparse classification model according to the radio frequency fingerprint feature vector and the radio frequency fingerprint database;

Deriving a reconstruction vector corresponding to the classification vector according to the classification vector and the sparse reconstruction algorithm;

If the maximum element value in the reconstructed vector is greater than a preset threshold, the access device is allowed to access.
The access control method according to claim 1, wherein the method further comprises:

If the maximum element value in the reconstructed vector is less than or equal to the preset threshold, access device access is prohibited.
The access control method according to claim 1, wherein before the obtaining the radio frequency fingerprint feature vector of the access device, the method further includes:

Collecting an I/Q amplitude offset and a carrier frequency offset of the pre-authorized device under the M carrier modulated signals as a set of radio frequency fingerprint feature vectors of the pre-authorized device;

Adding a feature set of the radio frequency fingerprint formed by the N sets of radio frequency fingerprint feature vectors collected continuously to the current radio frequency fingerprint database;

Wherein M and N are integers greater than one.
The access control method according to claim 3, wherein the constructing the radio frequency fingerprint feature vector of the corresponding access device according to the access request comprises:

When receiving the access request of the access device, collecting the I/Q amplitude offset and the carrier frequency offset of the access device under the M carrier modulated signals in the current time period, as the radio frequency fingerprint of the access device Feature vector.
The access control method according to claim 1, wherein the radio frequency finger is The eigenvector and the radio frequency fingerprint database, and the classification vector of the access device is obtained by the sparse classification model:

according to
The model derives the classification vector of the access device, where
For the RF fingerprint feature vector, M is the RF fingerprint library, and C is the classification vector.
The access control method according to claim 5, wherein the reconstruction vector corresponding to the classification vector is obtained according to the classification vector and the sparse reconstruction algorithm, including:

According to the equations
The original reconstructed vector is obtained, where ε is the reconstructed noise,
Is the original reconstructed vector, which is a column vector composed of N*K elements, and K is the number of authorized devices in the radio frequency fingerprint library M;

Each successive N elements in the original reconstructed vector are sequentially added to obtain a reconstructed vector composed of K elements.
An access control device, which is applied to a wireless routing device pre-equipped with a radio frequency fingerprint library, the device comprising:

a constructing module, configured to construct a radio frequency fingerprint feature vector of the corresponding access device according to the access request;

a first calculating module, configured to obtain, according to the radio frequency fingerprint feature vector and the radio frequency fingerprint library, a classification vector of the access device by using a sparse classification model;

a second calculating module, configured to obtain, according to the classification vector and the sparse reconstruction algorithm, a reconstruction vector corresponding to the classification vector;

The processing module is configured to allow the access device to access if the maximum element value in the reconstructed vector is greater than a preset threshold.
The access control device according to claim 7, wherein the processing module is further configured to:

If the maximum element value in the reconstructed vector is less than or equal to the preset threshold, access device access is prohibited.
The access control device according to claim 7, wherein the device further comprises:

An acquisition module, configured to collect an I/Q amplitude offset and a carrier frequency offset of the pre-authorized device under the M carrier modulated signals, as a set of radio frequency fingerprint feature vectors of the pre-authorized device;

Adding a feature set of the radio frequency fingerprint formed by the N sets of radio frequency fingerprint feature vectors collected continuously to the current radio frequency fingerprint database;

Wherein M and N are integers greater than one.
The access control device according to claim 8, wherein the constructing module is specifically configured to:

When receiving the access request of the access device, collecting the I/Q amplitude offset and the carrier frequency offset of the access device under the M carrier modulated signals in the current time period, as the radio frequency fingerprint of the access device Feature vector.
The access control device according to claim 1, wherein the first calculation module is specifically configured to:

according to
The model derives the classification vector of the access device, where
For the RF fingerprint feature vector, M is the RF fingerprint library, and C is the classification vector.
The access control device according to claim 11, wherein the two calculation modules are specifically configured to:

According to the equations
The original reconstructed vector is obtained, where ε is the reconstructed noise,
Is the original reconstructed vector, which is a column vector composed of N*K elements, and K is the number of authorized devices in the radio frequency fingerprint library M;

Each successive N elements in the original reconstructed vector are sequentially added to obtain a reconstructed vector composed of K elements.