Identity authentication method based on nonlinear signal characteristics and electronic device

Abstract

The application discloses an identity authentication method based on nonlinear signal characteristics and electronic equipment, communication signal data of a device to be authenticated is collected, IQ data corresponding to a frame preamble sequence is obtained, and is standardized to obtain standardized frame preamble IQ data, and a conventional physical layer characteristic value of the device to be authenticated is extracted; then the standardized frame preamble IQ data is converted into a target reference symbol, and a nonlinear signal characteristic value of the device is calculated; then the nonlinear signal characteristic value and the conventional physical layer characteristic value are combined; finally, the distance between the combined characteristic vector and a legal device characteristic vector is calculated, and the identity authentication result of the device to be authenticated is obtained according to the distance. The scheme introduces nonlinear signal characteristics, and combines the nonlinear signal characteristic value and the conventional physical layer characteristic value to form a combined characteristic vector containing more information of the device to be authenticated, so that the hardware characteristics of the device to be authenticated can be more comprehensively described, and the accuracy of identity authentication is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information security, and in particular to an identity authentication method based on nonlinear signal features and an electronic device. BACKGROUND

[0002] At present, wireless communication has become the main communication approach of the Internet, providing convenience and efficiency for massive device connection. However, differentiated wireless communication devices bring problems of authenticity of device identity and communication security, and due to the open channel transmission mechanism of wireless communication networks, they are vulnerable to threats such as illegal device access, man-in-the-middle attacks, and signal forgery.

[0003] Therefore, device identity authentication technology is not only a necessary means to maintain network order, but also an important guarantee for preventing illegal access and protecting user privacy. In related technologies, identity authentication technology based on physical layer features uses the inherent physical characteristics of wireless signals to achieve efficient and reliable device identity authentication without relying on additional keys.

[0004] However, conventional physical layer features in related technologies, such as carrier frequency offset, phase error, and amplitude error, still have certain limitations in practical applications. On the one hand, the number of these physical layer features is not large enough to fully characterize the hardware characteristics of devices; on the other hand, the authentication accuracy relying on these physical layer features still has deficiencies, making it difficult to meet the needs of high-security scenarios. SUMMARY

[0005] To solve the above problems in the prior art, the present application provides an identity authentication method based on nonlinear signal features and an electronic device. The technical problem to be solved by the present application is solved by the following technical solutions:

[0006] According to a first aspect of an embodiment of the present application, an identity authentication method based on nonlinear signal features is provided, the method comprising:

[0007] Collecting communication signal data of a device to be authenticated, obtaining in-phase component I and quadrature component Q corresponding to a frame preamble sequence thereof, and performing standardization processing to obtain standardized frame preamble IQ data;

[0008] Converting the standardized frame preamble IQ data into target reference symbols, calculating nonlinear signal feature values of the device to be authenticated based on the target reference symbols;

[0009] Based on the standardized frame preamble IQ data, extracting conventional physical layer feature values of the device to be authenticated;

[0010] Constructing and combining the nonlinear signal feature values and the conventional physical layer feature values to obtain a combined feature vector of the device to be authenticated;

[0011] Calculate the distance between the to-be-authenticated device feature vector and the legal device feature vector, and obtain the identity authentication result of the to-be-authenticated device according to the distance.

[0012] In an embodiment of the present application, the nonlinear signal feature value includes a correlation dimension CD, a Lyapunov exponent LE, a fractal dimension FD, and a Hurst exponent HE.

[0013] The conversion of the standardized frame preamble IQ data into the target reference symbol, and the calculation of the nonlinear signal feature value of the to-be-authenticated device based on the target reference symbol, include:

[0014] Rotating the phase of the standardized frame preamble IQ data to obtain a target reference symbol, and calculating the correlation dimension CD, the Lyapunov exponent LE, the fractal dimension FD, and the Hurst exponent HE of the to-be-authenticated device based on the target reference symbol.

[0015] In an embodiment of the present application, the target reference symbol includes an i-th sample point S(i) of a frame preamble sequence and a j-th sample point S(j) of the frame preamble sequence.

[0016] The calculation of the correlation dimension CD of the to-be-authenticated device based on the target reference symbol includes:

[0017] The correlation dimension CD is calculated by the formula

[0018] Wherein, Θ() represents a Heaviside step function, r k represents a pre-set threshold, L S(i),S(j) represents the Euclidean distance between S(i) and S(j), and N represents the number of sample points of the frame preamble sequence.

[0019] In an embodiment of the present application, the target reference symbol includes a t-th sample point S(t) of a frame preamble sequence.

[0020] The calculation of the Lyapunov exponent LE of the to-be-authenticated device based on the target reference symbol includes:

[0021] The frame preamble sequence is time-delay embedded to obtain a high-dimensional embedded space sequence by the formula D(t) = [S(t), S(t+τ),..., S(t+(d-1)τ)];

[0022] Wherein, d represents the embedding dimension, τ represents the time delay, and t represents the time index.

[0023] The Lyapunov exponent LE is calculated by the formula ​Calculate the logarithmic growth rate (LE) k (p, q);

[0024] Where p represents the embedding point, q is the nearest neighbor of p, k represents the time step, and L D(p)，D(q) Let D(p) represent the Euclidean distance between D(q) and D(p).

[0025] Through formula Calculate the Lyapunov exponent LE;

[0026] Where m represents the maximum value of time step k, and N represents the number of sampling points in the frame preamble sequence.

[0027] In one embodiment of the present invention, calculating the fractal dimension FD of the device to be authenticated based on the target reference symbol includes:

[0028] Through formula Calculate the fractal dimension FD;

[0029] Where τ is the interval size, L S(τ),S(n) Let S(τ) represent the Euclidean distance between S(τ) and S(i), N represent the number of sampling points in the frame preamble sequence, S(τ) represent the τth sampling point in the frame preamble sequence, and S(i) represent the ith sampling point in the frame preamble sequence.

[0030] In one embodiment of the present invention, calculating the Hurst exponent (HE) of the device to be certified based on the target reference symbol includes:

[0031] Through formula Calculate the Hurst exponent HE;

[0032] Where τ is the interval size, L S(τ),s(i Let S(τ) represent the Euclidean distance between S(τ) and S(i), where S(τ) represents the τth sampling point of the frame preamble sequence and S(i) represents the ith sampling point of the frame preamble sequence.

[0033] In one embodiment of the present invention, the conventional physical layer characteristic values ​​include phase error PE, amplitude error AE, and carrier frequency offset CFO;

[0034] The process of constructing and combining the nonlinear signal feature values ​​and the conventional physical layer feature values ​​to obtain the combined feature vector to be authenticated includes:

[0035] The correlation dimension CD, the Lyapunov exponent LE, the fractal dimension FD, the Hurst exponent HE, the phase error PE, the amplitude error AE, and the carrier frequency offset CFO are normalized to obtain the dimensionless eigenvalue v.

[0036] The feature values v are merged by formula v = [v CD , v LE , v FD , v HE , v PE , v AE , v CFO ] to construct a combined feature vector to be authenticated.

[0037] wherein v CD represents a normalized correlation dimension CD, v LE represents a normalized Lyapunov exponent LE, v FD represents a normalized fractal dimension FD, v HE represents a normalized Hurst exponent HE, v PE represents a normalized phase error PE, v AE represents a normalized amplitude error AE, and v CFO represents a normalized carrier frequency offset CFO.

[0038] In an embodiment of the present application, the distance between the combined feature vector to be authenticated and a legal device feature vector is calculated, and an identity authentication result of the device to be authenticated is obtained according to the distance, comprising:

[0039] The distance between the combined feature vector to be authenticated and a legal device feature vector is calculated by a pre-constructed kNN classifier.

[0040] When the distance is less than a preset threshold, an identity authentication result indicating that the authentication is passed is output, otherwise an identity authentication result indicating that the authentication fails is output.

[0041] In an embodiment of the present application, the pre-construction of the kNN classifier comprises:

[0042] The communication signal data of the algorithmic device is collected, the in-phase component I and the quadrature component Q corresponding to the frame preamble sequence of the communication signal data are obtained, and standardized processing is performed to obtain standardized frame preamble IQ data of the legal device.

[0043] The standardized frame preamble IQ data of the legal device is converted, and the nonlinear signal feature values of the legal device are calculated based on the converted IQ data.

[0044] Based on the standardized frame preamble iQ data of the legal device, the conventional physical layer feature values of the legal device are extracted.

[0045] The nonlinear signal feature values of the legal device and the conventional physical layer feature values of the legal device are combined to obtain a combined feature vector of the legal device.

[0046] assigning a corresponding legal identity label to the combined feature vector of the legal device, to obtain a legal target parameter;

[0047] constructing the legal target parameters of multiple legal devices into a target parameter dataset, and constructing the kNN classifier based on the target parameter dataset.

[0048] According to a second aspect of the embodiment of the present application, an electronic device is provided, and the device comprises:

[0049] one or more processors;

[0050] a computer readable medium configured to store one or more programs;

[0051] When the one or more programs are executed by the one or more processors, the one or more processors implement the identity authentication method based on nonlinear signal features as described in the first aspect.

[0052] Compared with the prior art, the present application has the following beneficial effects:

[0053] The identity authentication method based on nonlinear signal features and the electronic device provided by the embodiment of the present application, in the identity authentication, first collect the communication signal data of the device to be authenticated, obtain the in-phase component I and the quadrature component Q corresponding to the frame preamble sequence, and perform standardization processing to obtain the standardized frame preamble IQ data; then convert the standardized frame preamble IQ data into a target reference symbol, calculate the nonlinear signal feature value of the device to be authenticated based on the target reference symbol; in addition, based on the standardized frame preamble IQ data, the conventional physical layer feature value of the device to be authenticated is also extracted; then the nonlinear signal feature value and the conventional physical layer feature value are constructed and combined to obtain the combined feature vector of the device to be authenticated; finally, the distance between the combined feature vector and the legal device feature vector is calculated, and the identity authentication result of the device to be authenticated is obtained according to the distance. The present application expands the signal feature types of the device to be authenticated by introducing the nonlinear signal feature of the device to be authenticated, increases the identity authentication dimension, and forms the combined feature vector containing more information of the device to be authenticated by constructing and combining the nonlinear signal feature value and the conventional physical layer feature value, which can more comprehensively depict the hardware characteristics of the device to be authenticated, and improves the accuracy of the identity authentication.

[0054] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 is a step flow chart of an identity authentication method based on nonlinear signal features provided by the first embodiment of the present application;

[0056] Figure 2 is a flow chart of a method for constructing a kNN classifier according to Embodiment Two of the present application;

[0057] Figure 3 is a structural schematic diagram of an electronic device according to Embodiment Three of the present application. DETAILED DESCRIPTION

[0058] The present application will be further described in detail below with reference to specific embodiments, but the embodiments of the present application are not limited thereto.

[0059] Embodiment One

[0060] Referring to Figure 1 , a flow chart of steps of an identity authentication method based on nonlinear signal features according to Embodiment One of the present application is shown.

[0061] The text detection method of the present embodiment includes the following steps:

[0062] Step 101, collect the communication signal data of the device to be authenticated, obtain the in-phase component I and the quadrature component Q corresponding to the frame preamble sequence, and perform standardization processing to obtain the standardized frame preamble IQ data.

[0063] The device to be authenticated can be a wireless communication device, such as a mobile phone, a walkie-talkie, etc.

[0064] In the present embodiment, the communication signal data of the device to be authenticated can be collected by the following formula:

[0065] X0=[[I0,Q0],[I1,Q1],…,[I i ,Q i ],…,[I n ,Q n ]]

[0066] wherein i = 1, 2,..., n, n is the IQ sampling length of a complete data frame, and [I i , Q i ] is the value of the IQ at the i-th position of the IQ sampling data corresponding to the data frame.

[0067] When the in-phase component I and the quadrature component Q corresponding to the signal data frame preamble sequence are obtained and standardized, first, the IQ sampling data X corresponding to the frame preamble sequence of the signal data X0 is intercepted:

[0068] X=[[I0,Q0],[I1,Q1],…,[I i ,Q i ],…,[I N ,Q N ]]

[0069] wherein, i = 1, 2, …, N, N is the number of sampling points of the frame preamble sequence, [I i , Q i ] is the value of the IQ of the IQ sampling data of the frame preamble sequence at the i-th position.

[0070] Then, the above two-way orthogonal IQ sampling data is normalized:

[0071]

[0072] wherein, is the IQ sampling data after normalization, that is, the normalized frame preamble IQ data is obtained, mean is the mean value of the IQ sampling data, and std is the variance of the IQ sampling data.

[0073] Step 102, converting the normalized frame preamble IQ data into target reference symbols, and calculating the nonlinear signal characteristic value of the device to be authenticated based on the target reference symbols.

[0074] wherein, the nonlinear signal characteristic value of the device to be authenticated includes the correlation dimension CD, the Lyapunov exponent LE, the fractal dimension FD, and the Hurst exponent HE.

[0075] Specifically, when the normalized frame preamble IQ data is converted into target reference symbols, and the nonlinear signal characteristic value of the device to be authenticated is calculated based on the target reference symbols, the normalized frame preamble IQ data can be rotated in phase to obtain the target reference symbols; and then the correlation dimension CD, the Lyapunov exponent LE, the fractal dimension FD, and the Hurst exponent HE of the device to be authenticated are calculated based on the target reference symbols.

[0076] wherein, the target reference symbols include the i-th sampling point S(i) of the frame preamble sequence, the j-th sampling point S(j) of the frame preamble sequence, the t-th sampling point S(t) of the frame preamble sequence, and the τ-th sampling point S(τ) of the frame preamble sequence.

[0077] Further, when the correlation dimension CD of the device to be authenticated is calculated based on the target reference symbols, the correlation dimension CD is calculated by the formula wherein, Θ() represents the Heaviside step function, r k represents a pre-set threshold, L S(i),S(j) represents the Euclidean distance between S(i) and S(j), and N represents the number of sampling points of the frame preamble sequence.

[0078] In the calculation of Lyapunov exponent LE of the to-be-authenticated device based on the target reference symbol, first, the frame preamble sequence can be time-delay embedded by the formula D(t) = [S(t), S(t+τ),..., S(t+(d-1)τ)] to obtain a high-dimensional embedded space sequence; wherein d represents the embedding dimension, τ represents the time delay, and t represents the time index. Secondly, the logarithmic growth rate LE can be calculated by the formula k (p, q); wherein p represents the embedding point, q is the nearest neighbor point of p, k represents the time step, and L D(p)，D(q) represents the Euclidean distance between D(p) and D(q). Then the Lyapunov exponent LE can be calculated by the formula ; wherein m represents the maximum value of the time step k, and N represents the number of sampling points of the frame preamble sequence.

[0079] In the calculation of the fractal dimension FD of the to-be-authenticated device based on the target reference symbol, the fractal dimension FD can be calculated by the formula ; wherein τ is the interval size, and L S(τ),S(n) represents the Euclidean distance between S(τ) and S(i), N represents the number of sampling points of the frame preamble sequence, S(τ) represents the τth sampling point of the frame preamble sequence, and S(i) represents the ith sampling point of the frame preamble sequence.

[0080] In the calculation of the Hurst exponent HE of the to-be-authenticated device based on the target reference symbol, the Hurst exponent HE can be calculated by the formula ; wherein τ is the interval size, and L S(τ),S(i) represents the Euclidean distance between S(τ) and S(i), S(τ) represents the τth sampling point of the frame preamble sequence, and S(i) represents the ith sampling point of the frame preamble sequence.

[0081] In this embodiment, the nonlinear signal characteristic values of the to-be-authenticated device, i.e., the correlation dimension CD, the Lyapunov exponent LE, the fractal dimension FD, and the Hurst exponent HE, are introduced, which can describe the hardware characteristics of the to-be-authenticated device from more dimensions compared with the prior art. The complex dynamic characteristics hidden in the device hardware are introduced into the authentication system, which expands the dimension of the feature vector used in identity authentication, helps to build a richer and more comprehensive feature space, and thus enhances the robustness of the features.

[0082] In step 103, the conventional physical layer characteristic values of the to-be-authenticated device are extracted based on the standardized frame preamble IQ data.

[0083] ​In the embodiment, the conventional physical layer characteristic values include phase error PE, amplitude error AE and carrier frequency offset CFO. Based on the normalized frame preamble IQ data obtained in step 101, the phase error PE, the amplitude error AE and the carrier frequency offset CFO of the device to be authenticated can be calculated.

[0084] Specifically, the phase error PE is calculated as follows:

[0085]

[0086] wherein N represents the number of sampling points of the frame preamble sequence, and Δθ i represents the phase difference between adjacent sampling points i and i+1 in the normalized frame preamble IQ data.

[0087] The amplitude error AE is calculated as follows:

[0088]

[0089] wherein S k is the amplitude value of the kth frequency point of the normalized frame preamble IQ data after Fast Fourier Transform (FFT), μ is the average value of the amplitudes of all frequency points, and N represents the number of sampling points of the frame preamble sequence.

[0090] The carrier frequency offset CFO is calculated as follows:

[0091]

[0092] wherein ∠() represents the phase angle of a complex number (i.e. the normalized frame preamble IQ data in the embodiment), represents the conjugate complex number of the i th sampling point of a complex signal sequence, S(i) represents the i th sampling point in the complex signal sequence (i.e. the normalized frame preamble IQ data sequence), and N represents the number of sampling points of the frame preamble sequence.

[0093] Obviously, the above step 102 and step 103 can be executed in any order.

[0094] Step 104, constructing and combining the non-linear signal characteristic values and the conventional physical layer characteristic values to obtain the combined feature vector to be authenticated.

[0095] The non-linear signal characteristic values and the conventional physical layer characteristic values of the device to be authenticated are calculated through step 102 and step 103, and then the non-linear signal characteristic values and the conventional physical layer characteristic values can be constructed and combined to obtain a multi-dimensional combined feature vector.

[0096] Specifically, the correlation dimension CD, the Lyapunov exponent LE, the fractal dimension FD, the Hurst exponent HE, the phase error PE, the amplitude error AE, and the carrier frequency offset CFO can be normalized to obtain dimensionless characteristic values v: wherein v is the normalized characteristic value, v' is the original characteristic value (i.e., the correlation dimension CD, the Lyapunov exponent LE, the fractal dimension FD, the Hurst exponent HE, the phase error PE, the amplitude error AE, and the carrier frequency offset CFO), m is the mean of the characteristic values, and s is the standard deviation of the characteristic values.

[0097] The above characteristic values v are then combined by the formula v = [v CD , v LE , v FD , v HE , v PE , v AE , v CFO ] to construct a combined feature vector v to be authenticated.

[0098] wherein v CD represents the normalized correlation dimension CD, v LE represents the normalized Lyapunov exponent LE, v FD represents the normalized fractal dimension FD, v HE represents the normalized Hurst exponent HE, v PE represents the normalized phase error PE, v AE represents the normalized amplitude error AE, and v CFO represents the normalized carrier frequency offset CFO.

[0099] Compared with the prior art identity authentication method relying only on conventional physical layer features, in the present embodiment, the nonlinear signal features: the correlation dimension CD, the Lyapunov exponent LE, the fractal dimension FD, and the Hurst exponent HE are introduced, which at least expands the feature vector by 4 dimensions; and by combining the nonlinear signal feature values and the conventional physical layer feature values, a combined feature vector containing more information of the device to be authenticated is formed, which can more comprehensively depict the hardware characteristics of the device to be authenticated; not only can the risk of misjudgment caused by a single inaccurate feature be reduced, but also the adaptability of the model to small samples and complex environments is improved, thereby significantly improving the authentication accuracy in various scenarios and meeting the needs of high-security applications.

[0100] Step 105, calculate the distance between the combined feature vector to be authenticated and the legal device feature vector, and obtain the identity authentication result of the device to be authenticated according to the distance.

[0101] Specifically, the distance between the combined feature vector to be authenticated and the feature vector of the legitimate device can be calculated using a pre-built kNN classifier.

[0102] If the combined feature vector to be authenticated is represented as v x The feature vector of a legitimate device is represented as v. i Then calculate v x With each v i Euclidean distance dis(v) x v i ):

[0103]

[0104] Among them, v x,k It is the combined feature vector v of the device to be certified. x The k-th eigenvalue, v i,k It is the feature vector v of a legitimate device. i The k-th eigenvalue; obviously, the value of k and v i The quantity can be set according to actual needs.

[0105] Then, based on the calculated Euclidean distance dis(v) x v i Based on the size of the feature vectors, m valid device feature vectors are selected according to the nearest neighbor principle to form a nearest neighbor set.

[0106] N m ={(v i1 y i1 ), (v i2 y i2 ), ..., (v im y im )}

[0107] And calculate the set of feature vectors to be authenticated {v x y x} and the nearest neighbor set N m The average distance of m feature vectors

[0108]

[0109] Where y i This represents the identity tag of the i-th legitimate device. This identity tag can be the device's identifier and / or serial number and / or device model, etc., which can be obtained from communication signals or customized. Similarly, the quantity k can also be set according to actual needs or experience.

[0110] When the distance is less than the preset threshold, an identity authentication result indicating that the authentication is passed is output, otherwise an identity authentication result indicating that the authentication is failed is output.

[0111] According to the calculated average distance The average distance is compared with a preset threshold β, if the average distance The device to be authenticated is determined as a "legal device", and an identity authentication result indicating that the authentication is passed, such as "authentication qualified" or "legal device" and the like, is output, and the identity tag corresponding to the device can also be output simultaneously.

[0112]

[0113] Wherein, δ() is a voting function:

[0114]

[0115] Otherwise, the device is marked as "illegal device", and a special tag is given An identity authentication result indicating that the authentication is failed, such as "illegal device" or "authentication failed" and the like, is output.

[0116] The identity authentication method based on the nonlinear signal feature provided by the embodiment of the present application, when performing identity authentication, first collects the communication signal data of the device to be authenticated, obtains the in-phase component I and the quadrature component Q corresponding to the frame preamble sequence, and performs standardization processing to obtain the standardized frame preamble IQ data; then the standardized frame preamble IQ data is converted into a target reference symbol, and the nonlinear signal feature value of the device to be authenticated is calculated based on the target reference symbol; in addition, the standardized frame preamble IQ data is also used to extract the conventional physical layer feature value of the device to be authenticated; then the nonlinear signal feature value and the conventional physical layer feature value are constructed and combined to obtain the combined feature vector of the device to be authenticated; finally, the distance between the combined feature vector and the legal device feature vector is calculated, and the identity authentication result of the device to be authenticated is obtained according to the distance. The present scheme introduces the nonlinear signal feature of the device to be authenticated, expands the signal feature types of the device to be authenticated, increases the identity authentication dimension, and constructs and combines the nonlinear signal feature value and the conventional physical layer feature value to form a combined feature vector containing more information of the device to be authenticated, which can more comprehensively depict the hardware characteristics of the device to be authenticated, and improves the accuracy of identity authentication.

[0117] Specifically, by adding the correlation dimension CD, Lyapunov exponent LE, fractal dimension FD and other nonlinear signal features in the feature vector of the wireless communication device, the complex dynamic characteristics implied in the device hardware are introduced into the authentication system, the dimension of the feature vector used in identity authentication is expanded, and the multi-dimensional features work together with the conventional physical layer features to enable the authentication process to build a richer and more comprehensive feature space, thereby enhancing the robustness of the features; and reducing the risk of misjudgment caused by inaccurate single features, improving the adaptability of the model to small samples and complex environments, thereby significantly improving the authentication accuracy in various scenarios, meeting the needs of high security applications, and can be widely used in wireless access security, industrial network management, self-organizing network protection and other scenarios.

[0118] Embodiment two

[0119] The pre-construction method of the kNN classifier is as follows, referring to Figure 2 , Figure 2 A flowchart of a method for constructing a kNN classifier is provided:

[0120] Step 201, collect the communication signal data of the legal device, obtain the in-phase component I and the quadrature component Q corresponding to the frame preamble sequence of the communication signal data, and perform standardization processing to obtain the standardized frame preamble IQ data of the legal device.

[0121] Step 202, convert the standardized frame preamble IQ data of the legal device, and calculate the nonlinear signal feature value of the legal device based on the converted IQ data.

[0122] Step 203, based on the standardized frame preamble IQ data of the legal device, extract the conventional physical layer feature value of the legal device.

[0123] Step 204, construct and combine the nonlinear signal feature value of the legal device and the conventional physical layer feature value of the legal device to obtain the combined feature vector of the legal device.

[0124] In this embodiment, the acquisition method of the standardized frame preamble IQ data of the legal device is similar to step 101, the calculation method of the nonlinear signal feature value and the conventional physical layer feature value of the legal device is similar to step 102 and step 103, and the construction of the combined feature vector of the legal device is similar to step 104, which will not be repeated here.

[0125] Step 205, assign a corresponding legal identity tag to the combined feature vector of the legal device to obtain the legal target parameter.

[0126] In this embodiment, the communication signals of multiple legal devices are collected, and the combined feature vector v of each legal device is obtained; then for the feature vector v of the i-th devicei Assign a corresponding legitimate identity tag y based on the identity information of the legitimate device. i Each data point is d i =(v i y i The valid objective parameter is represented as d. i =(v i y i ).

[0127] Step 206: Construct a target parameter dataset from the legal target parameters of multiple legal devices, and build a kNN classifier based on this target parameter dataset.

[0128] If M legitimate devices are collected, then the M legitimate target parameters obtained will be combined into a target parameter dataset D. The structure of the target parameter dataset is defined as D = {d} i |i=1,2,3,...,M}. Then, according to actual needs, the multiple target parameter datasets can be divided into training and test sets proportionally, for example, the ratio of training set to test set is 7:3.

[0129] Then, the training and test sets are input into the kNN classifier. Common loss functions or evaluation metrics for the kNN classifier, such as 0-1 loss function and cross-entropy loss, are used to judge the output of the kNN classifier, and the constructed kNN classifier is obtained.

[0130] Example 3

[0131] This invention also provides an electronic device, such as... Figure 3 As shown, it includes a processor 301, a communication interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304.

[0132] Memory 303 is used to store computer programs;

[0133] When processor 301 executes a program stored in memory 303, it performs the following steps:

[0134] The communication signal data of the device to be authenticated is collected, the in-phase component I and the quadrature component Q corresponding to the frame preamble sequence are obtained, and standardized processing is performed to obtain standardized frame preamble IQ data; the standardized frame preamble IQ data is converted into target reference symbols, and the nonlinear signal eigenvalue of the device to be authenticated is calculated based on the target reference symbols; the conventional physical layer eigenvalue of the device to be authenticated is extracted based on the standardized frame preamble IQ data; the nonlinear signal eigenvalue and the conventional physical layer eigenvalue are constructed and combined to obtain a combined eigenvalue vector to be authenticated; the distance between the combined eigenvalue vector to be authenticated and a legal device eigenvalue vector is calculated, and the identity authentication result of the device to be authenticated is obtained according to the distance.

[0135] The identity authentication method based on nonlinear signal characteristics and the electronic device provided by the embodiments of the present application can be used for identity authentication. When identity authentication is performed, the communication signal data of the device to be authenticated is collected, the in-phase component I and the quadrature component Q corresponding to the frame preamble sequence are obtained, and standardized processing is performed to obtain standardized frame preamble IQ data; then the standardized frame preamble IQ data is converted into target reference symbols, and the nonlinear signal eigenvalue of the device to be authenticated is calculated based on the target reference symbols; in addition, the conventional physical layer eigenvalue of the device to be authenticated is extracted based on the standardized frame preamble IQ data; then the nonlinear signal eigenvalue and the conventional physical layer eigenvalue are constructed and combined to obtain a combined eigenvalue vector to be authenticated; finally, the distance between the combined eigenvalue vector to be authenticated and a legal device eigenvalue vector is calculated, and the identity authentication result of the device to be authenticated is obtained according to the distance. The present application introduces the nonlinear signal characteristics of the device to be authenticated, expands the signal characteristic types of the device to be authenticated, increases the identity authentication dimension, and constructs and combines the nonlinear signal eigenvalue and the conventional physical layer eigenvalue to form a combined eigenvalue vector containing more information of the device to be authenticated, which can more comprehensively depict the hardware characteristics of the device to be authenticated and improve the accuracy of identity authentication.

[0136] The communication bus mentioned above can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0137] The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0138] The memory can include a random access memory (RAM) and can also include a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0139] The processor described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc. It can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0140] The method provided by the embodiments of the present application can be applied to an electronic device. Specifically, the electronic device can be a desktop computer, a portable computer, a smart mobile terminal, a server, etc. Herein, no limitation is made, and any electronic device that can implement the present application belongs to the protection scope of the present application.

[0141] For the electronic device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the description of the method embodiments.

[0142] As another aspect, the embodiments of the present application also provide a computer readable medium having a computer program stored thereon, which is executed by a processor to implement the identity authentication method based on nonlinear signal features as described in the above embodiments.

[0143] It should be noted that the electronic device and the readable medium of the embodiments of the present application are the electronic device and the readable medium applying the above identity authentication method based on nonlinear signal features, and all the embodiments of the identity authentication method based on nonlinear signal features are applicable to the electronic device and the readable medium, and can achieve the same or similar beneficial effects.

[0144] By applying the terminal device provided by the embodiments of the present application, the proper nouns and / or fixed phrases can be displayed for the user to select, thereby reducing the user input time and improving the user experience.

[0145] The terminal device exists in various forms, including but not limited to:

[0146] (1) Mobile communication device: This type of device is characterized by having mobile communication function and providing voice and data communication as the main target. This type of terminal includes smart phone (e.g. iPhone), multimedia phone, functional phone, and low-end phone, etc.

[0147] (2) Ultra-mobile personal computer device: This type of device belongs to the category of personal computer and has computing and processing function, and generally has mobile Internet feature. This type of terminal includes PDA, MID and UMPC device, such as iPad.

[0148] (3) Portable entertainment device: This type of device can display and play multimedia content. This type of device includes audio and video player (e.g. iPod), hand-held game console, electronic book, and smart toy and portable car navigation device.

[0149] (4) Other electronic devices with data interaction function.

[0150] In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly specified.

[0151] Although the present application is described herein in conjunction with various embodiments, other variations of the disclosed embodiments can be understood and implemented by those skilled in the art through reading the description in conjunction with the accompanying drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. Measures described in mutually different dependent claims can be combined and produce beneficial results.

[0152] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, device (apparatus), or computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects, all of which are referred to as "modules" or "systems" herein. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The computer program is stored / distributed in a suitable medium, provided with other hardware, or as part of the hardware, and can also take other distribution forms, such as through the Internet or other wired or wireless telecommunication systems.

[0153] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flowsheet block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0154] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart or flowsheet block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0155] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flowsheet block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0156] The above description is further to the present application in conjunction with specific preferred embodiments, and cannot be deemed to limit the specific implementation of the present application to these descriptions. For those skilled in the art to which the present application pertains, without departing from the concept of the present application, a number of simple derivations or replacements can also be made, which should be deemed to fall within the protection scope of the present application.

Claims

1. A method of identity authentication based on nonlinear signal features, characterized in that, The method comprises: Collecting communication signal data of a device to be authenticated, obtaining in-phase component I and quadrature component Q corresponding to a frame preamble sequence of the communication signal data, and performing standardization processing to obtain standardized frame preamble IQ data; Converting the standardized frame preamble IQ data into target reference symbols, and calculating a nonlinear signal characteristic value of the device to be authenticated based on the target reference symbols; Extracting a conventional physical layer characteristic value of the device to be authenticated based on the standardized frame preamble IQ data; Constructing and combining the nonlinear signal characteristic value and the conventional physical layer characteristic value to obtain a combined characteristic vector of the device to be authenticated; Calculating a distance between the combined characteristic vector of the device to be authenticated and a legal device characteristic vector, and obtaining an identity authentication result of the device to be authenticated according to the distance; The nonlinear signal characteristic value comprises a correlation dimension CD, a Lyapunov exponent LE, a fractal dimension FD, and a Hurst exponent HE; The converting of the standardized frame preamble IQ data into target reference symbols and the calculating of the nonlinear signal characteristic value of the device to be authenticated based on the target reference symbols comprise: Rotating a phase of the standardized frame preamble IQ data to obtain target reference symbols, and calculating the correlation dimension CD, the Lyapunov exponent LE, the fractal dimension FD, and the Hurst exponent HE of the device to be authenticated based on the target reference symbols; The target reference symbol comprises the first sample point of a frame preamble sequence ; The calculating of the Lyapunov exponent LE of the device to be authenticated based on the target reference symbols comprises: By formula time delay embedding is performed on the frame preamble sequence to obtain a high-dimensional embedding space sequence; wherein, denotes the embedding dimension, denotes the time delay, denotes the time index; The logarithmic growth rate is calculated by the formula ​ wherein, denotes an embedding point, is a nearest neighbor point of k denotes a time step, denotes and the Euclidean distance between The Lyapunov exponent LE is calculated by the formula , wherein, denotes a time step k denotes a maximum value of denotes a number of sample points of a frame preamble sequence.

2. The method of claim 1, wherein, The target reference symbol comprises the first sample point of a frame preamble sequence , the first sample point of a frame preamble sequence ; The calculating of the correlation dimension CD of the device to be authenticated based on the target reference symbols comprises: The correlation dimension CD is calculated by the formula CD = log(N) / log(D) wherein denotes the Heaviside step function, denotes a pre-set threshold value, denotes the Euclidean distance between denotes the Euclidean distance between N denotes the number of sample points of the frame preamble sequence.

3. The method of claim 1, wherein, The calculating of the fractal dimension FD of the device to be authenticated based on the target reference symbols comprises: The fractal dimension FD is calculated by the formula FD = log(N) / log(1 / r) wherein denotes the Euclidean distance between denotes the number of sample points of the frame preamble sequence, denotes the sample point of the frame preamble sequence, denotes the sample point of the frame preamble sequence.​ 4. The method of claim 1, wherein, The calculating of the Hurst exponent HE of the device to be authenticated based on the target reference symbols comprises: The Hurst exponent HE is calculated by the formula , in, express The Euclidean distance between them Represents the first frame of the preamble sequence One sampling point, Represents the first frame of the preamble sequence One sampling point.

5. The method of claim 1, wherein, The conventional physical layer characteristic value comprises a phase error PE, an amplitude error AE, and a carrier frequency offset CFO; The constructing and combining of the nonlinear signal characteristic value and the conventional physical layer characteristic value to obtain the combined characteristic vector of the device to be authenticated comprises: normalizing the correlation dimension CD, the Lyapunov exponent LE, the fractal dimension FD, the Hurst exponent HE, the phase error PE, the amplitude error AE and the carrier frequency offset CFO to obtain dimensionless characteristic values ; The characteristic value is merged by formula The combined characteristic vector to be authenticated is constructed.​ wherein, denotes the normalized correlation dimension CD, denotes the normalized Lyapunov exponent LE, denotes the normalized fractal dimension FD, denotes the normalized Hurst exponent HE, denotes the normalized phase error PE, denotes the normalized amplitude error AE, denotes the normalized carrier frequency offset CFO.

6. The method of claim 1, wherein, The calculating of the distance between the combined characteristic vector of the device to be authenticated and the legal device characteristic vector, and the obtaining of the identity authentication result of the device to be authenticated according to the distance comprise: Calculating the distance between the combined characteristic vector of the device to be authenticated and the legal device characteristic vector through a pre-constructed kNN classifier; When the distance is less than a preset threshold, outputting an identity authentication result indicating that the authentication is passed, otherwise outputting an identity authentication result indicating that the authentication fails.

7. The method of claim 6, wherein, The pre-construction of the kNN classifier comprises: Collecting communication signal data of a legal device, obtaining in-phase component I and quadrature component Q corresponding to a frame preamble sequence of the communication signal data, and performing standardization processing to obtain standardized frame preamble IQ data of the legal device; Converting the standardized frame preamble IQ data of the legal device, and calculating a nonlinear signal characteristic value of the legal device based on the converted IQ data; Extracting a conventional physical layer characteristic value of the legal device based on the standardized frame preamble IQ data of the legal device; The nonlinear signal characteristic value of the legal device and the conventional physical layer characteristic value of the legal device are combined to obtain a combined characteristic vector of the legal device; A corresponding legal identity label is assigned to the combined characteristic vector of the legal device to obtain a legal target parameter; The legal target parameters of multiple legal devices are combined into a target parameter dataset, and the kNN classifier is constructed based on the target parameter dataset.

8. An electronic device, comprising: The device comprises: one or more processors; a computer readable medium configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the identity authentication method based on nonlinear signal characteristics as claimed in any one of claims 1-7.

Images