Method and apparatus for verifying the legitimacy of a wireless device

Abstract

The present disclosure provides a method and apparatus for verifying the legitimacy of a wireless device. The method includes collecting an initial transient signal sequence transmitted after the wireless device is wirelessly connected to the connected device, where the initial transient signal sequence includes a first initial sub-signal sequence and a second initial sub-signal sequence; respectively determining a target signal mutation point on the first initial sub-signal sequence and the second initial sub-signal sequence, where the target signal mutation point represents a transient point that satisfies a mutation probability threshold; determining a target transient signal sequence from the initial transient signal sequence based on the two target signal mutation points; processing the target transient signal sequence by using a test mode decomposition model to obtain a target conversion signal sequence; processing the target conversion signal sequence by using a target fingerprint extraction model to obtain a device fingerprint identifier of the wireless device; and determining the legitimacy of the wireless device according to the similarity between the device fingerprint identifier and a reference fingerprint identifier in a database.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet of Things security technologies, and more particularly, to a method for verifying the legitimacy of wireless devices, a legitimacy verification device, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the progress of science and technology, a large number of Internet of Things terminal devices have entered people's production and life, bringing great convenience while also bringing security risks.

[0003] Internet of Things devices usually need to communicate with other devices, and Wi-Fi and Bluetooth are the most common communication methods. However, the current Wi-Fi and Bluetooth communication protocols have been proven not to be completely secure. Illegal attackers can steal user data through malicious connections and even control the device to cause more serious damage. For example, by modifying the device attributes such as the ID of an illegal device to those of a legal device, the attacker can steal data using the illegal device when the password is known.

[0004] The current security verification method is to prevent attackers from accessing by setting a password authentication protection mechanism. For example, a PIN code is used to establish a link key during Wi-Fi key and Bluetooth secondary pairing authentication. However, only setting a password protection mechanism is still not enough. Illegal access nodes and client devices may forge the passwords, SSIDs, or MAC / IP addresses of legal devices to perform various simulation and replay attacks. Therefore, how to verify the legitimacy of wireless devices is directly related to data security. Summary of the Invention

[0005] In view of this, embodiments of the present disclosure provide a method for verifying the legitimacy of wireless devices, a legitimacy verification device, an electronic device, a computer-readable storage medium, and a computer program product.

[0006] One aspect of the embodiments of the present disclosure provides a method for verifying the legitimacy of wireless devices, including:

[0007] Collecting an initial transient signal sequence transmitted after the above wireless device is wirelessly connected to a connected device, where the initial transient signal sequence includes a first initial sub-signal sequence and a second initial sub-signal sequence;

[0008] Determining a target signal mutation point on each of the first initial sub-signal sequence and the second initial sub-signal sequence, where the target signal mutation point represents a transient point that satisfies a mutation probability threshold;

[0009] Determining a target transient signal sequence from the initial transient signal sequence based on the two target signal mutation points;

[0010] Process the above-mentioned target transient signal sequence using an empirical mode decomposition model to obtain a target conversion signal sequence;

[0011] Process the above-mentioned target conversion signal sequence using a target fingerprint extraction model to obtain the device fingerprint identifier of the above wireless device;

[0012] Determine the legitimacy of the above wireless device according to the similarity between the above device fingerprint identifier and the reference fingerprint identifier in the database.

[0013] According to an embodiment of the present disclosure, determining a target signal mutation point on each of the above first initial sub-signal sequence and second initial sub-signal sequence includes:

[0014] For any one of the above first initial sub-signal sequence and second initial sub-signal sequence, divide the above sub-signal sequence into multiple target observation sequences;

[0015] For each of the above target observation sequences, process the above target observation sequence using a target signal mutation probability model to obtain multiple mutation point probabilities;

[0016] According to the multiple above mutation point probabilities corresponding to the above sub-signal sequence, determine the transient point with the largest mutation point probability as one of the above target signal mutation points.

[0017] According to an embodiment of the present disclosure, the above target signal mutation probability model is trained by the following method:

[0018] Use each first training sample to train an initial signal mutation probability model and output a predicted mutation probability, wherein the above training sample includes a training transient signal sequence, and the above initial signal mutation probability model is constructed according to Bayes' theorem;

[0019] Calculate a first loss result of the above initial signal mutation probability model according to the above predicted mutation probability;

[0020] Iteratively adjust the network parameters of the above initial signal mutation probability model according to the above first loss result to generate the above trained target signal mutation probability model.

[0021] According to an embodiment of the present disclosure, the above target observation sequence includes multiple transient points;

[0022] Wherein, the above processing the above target observation sequence using a target signal mutation probability model to obtain multiple mutation point probabilities includes:

[0023] Process each of the above transient points using the above target signal mutation probability model to obtain multiple of the above mutation point probabilities;

[0024] Among them, determining the target transient signal sequence from the above initial transient signal sequence based on the above two target signal mutation points includes:

[0025] Taking the positions of the two above target signal mutation points in the above initial transient signal sequence as endpoints respectively for cutting to obtain the above target transient signal sequence.

[0026] According to an embodiment of the present disclosure, processing the above target transient signal sequence by using the test mode decomposition model to obtain a target conversion signal sequence includes:

[0027] Processing the above target transient signal sequence by using the above test mode decomposition model to obtain a plurality of narrowband signal sequences, wherein the above narrowband signal sequences include a main narrowband signal sequence and a non-main narrowband signal sequence divided based on frequency;

[0028] Performing aliasing calculation on the above main narrowband signal sequence and the above non-main narrowband signal sequence to obtain an initial conversion signal sequence;

[0029] Performing Hilbert-Huang transform on the above initial conversion signal sequence to obtain the above target conversion signal sequence.

[0030] According to an embodiment of the present disclosure, processing the above target conversion signal sequence by using the target fingerprint extraction model to obtain the device fingerprint identifier of the above wireless device includes:

[0031] Processing the above target conversion signal sequence by using the above target fingerprint extraction model to obtain the passive fingerprint identifier of the above wireless device;

[0032] Generating the above device fingerprint identifier according to the active fingerprint identifier and the passive fingerprint identifier of the above wireless device, wherein the above active fingerprint identifier includes the attribute identifier of the above wireless device, and the above attribute identifier includes at least one of the following: serial number of the wireless device, IP address, gateway address, media access control address, digital signal sequence processing version.

[0033] According to an embodiment of the present disclosure, the above target fingerprint extraction model is trained in the following manner:

[0034] Obtaining a training sample set, wherein the above training sample set includes a plurality of second training samples, the above second training samples include training conversion signal sequences and label data corresponding to the above training conversion signal sequences, and the above label data includes passive fingerprint identifiers of legitimate devices;

[0035] For each of the above second training samples, inputting the above training conversion signal sequence into the initial fingerprint extraction model to output a predicted fingerprint identifier;

[0036] Calculate a loss function based on the above predicted fingerprint identifier and the above tag data to obtain a second loss result;

[0037] Iteratively adjust the network parameters of the above initial fingerprint extraction model according to the above second loss result to generate the above trained target fingerprint extraction model.

[0038] According to an embodiment of the present disclosure, determining the legality of the above wireless device according to the similarity between the above device fingerprint identifier and the reference fingerprint identifier in the database includes:

[0039] Calculate the similarity between the above device fingerprint identifier and the above reference fingerprint identifier by using any one of the chaotic polynomial expansion method and the above target fingerprint extraction model, wherein the device attribute identifier corresponding to the above reference fingerprint identifier is the same as the attribute identifier of the above wireless device;

[0040] When the above similarity meets the similarity threshold, determine the above wireless device as a legal device;

[0041] When the above similarity does not meet the similarity threshold, determine the above wireless device as an illegal device.

[0042] According to an embodiment of the present disclosure, the method for verifying the legality of a wireless device further includes:

[0043] Perform filtering processing on the above initial transient signal sequence to obtain a filtered initial transient signal sequence, so as to determine the above target signal mutation point by using the above filtered initial transient signal sequence; and / or

[0044] When it is determined that the above wireless device is an illegal device, send a control instruction to the above connected device so that the above connected device disconnects the connection with the above wireless device in response to the above control instruction; and / or

[0045] When it is determined that the above wireless device is a legal device, determine the device fingerprint identifier of the above wireless device as a new reference fingerprint identifier and store it in the above database.

[0046] Another aspect of the embodiments of the present disclosure provides a device for verifying the legality of a wireless device, including:

[0047] An acquisition module for acquiring an initial transient signal sequence transmitted after the above wireless device is wirelessly connected to the connected device, wherein the above initial transient signal sequence includes a first initial sub-signal sequence and a second initial sub-signal sequence;

[0048] A first determination module for determining a target signal mutation point on each of the above first initial sub-signal sequence and the second initial sub-signal sequence, wherein the above target signal mutation point represents a transient point that satisfies the mutation probability threshold;

[0049] A second determination module, configured to determine a target transient signal sequence from the initial transient signal sequence based on two above-mentioned target signal mutation points;

[0050] A processing module, configured to process the target transient signal sequence by using an empirical mode decomposition model to obtain a target conversion signal sequence;

[0051] An extraction module, configured to process the target conversion signal sequence by using a target fingerprint extraction model to obtain the device fingerprint identifier of the wireless device;

[0052] A comparison module, configured to determine the legitimacy of the wireless device according to the similarity between the device fingerprint identifier and a reference fingerprint identifier in a database.

[0053] Another aspect of the embodiments of the present disclosure provides an electronic device, including: one or more processors; a memory, configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described above.

[0054] Another aspect of the embodiments of the present disclosure provides a computer-readable storage medium, storing computer-executable instructions, where the instructions are used to implement the method as described above when executed.

[0055] Another aspect of the embodiments of the present disclosure provides a computer program product, where the computer program product includes computer-executable instructions, and the instructions are used to implement the method as described above when executed.

[0056] According to the embodiments of the present disclosure, by collecting an initial transient signal sequence of a wireless device when the wireless device is already connected, cropping based on target signal mutation points to determine a target transient signal sequence, converting the target transient signal sequence, and calculating the similarity between the device fingerprint identifier corresponding to the target conversion signal sequence and a reference fingerprint identifier in a database to determine the legitimacy of the wireless device, at least partially overcoming the technical problem in the related art that an attacker uses a tampered wireless device to steal data, and achieving the technical effect of improving the security of data. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, the above and other objects, features and advantages of the present disclosure will become clearer. In the drawings:

[0058] Figure 1 Schematically shows a flowchart of a method for verifying the legitimacy of a wireless device according to an embodiment of the present disclosure;

[0059] Figure 2 Schematically shows a flowchart of a method for obtaining a target signal mutation point according to an embodiment of the present disclosure;

[0060] Figure 3 Schematically shows a schematic diagram of a target conversion signal sequence according to an embodiment of the present disclosure;

[0061] Figure 4 Schematically shows a flowchart for determining the legitimacy of a wireless device according to an embodiment of the present disclosure;

[0062] Figure 5 Schematically shows a schematic diagram of a filtered initial transient signal sequence according to an embodiment of the present disclosure;

[0063] Figure 6 Schematically shows a block diagram of a legitimacy verification device for a wireless device according to an embodiment of the present disclosure; and

[0064] Figure 7 Schematically shows a block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure. Detailed implementation manners

[0065] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, for the sake of explanation, many specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. However, it is obvious that one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts of the present disclosure.

[0066] The terms used herein are merely for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0067] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0068] In the case of using expressions such as "at least one of A, B, and C", generally, it should be interpreted according to the meaning that those skilled in the art usually understand this expression (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0069] Embodiments of the present disclosure provide a method and apparatus for verifying the legitimacy of a wireless device. The method includes collecting an initial transient signal sequence transmitted after the wireless device is wirelessly connected to a connected device, where the initial transient signal sequence includes a first initial sub-signal sequence and a second initial sub-signal sequence; respectively determining a target signal mutation point on the first initial sub-signal sequence and the second initial sub-signal sequence, where the target signal mutation point represents a transient point that satisfies a mutation probability threshold; determining a target transient signal sequence from the initial transient signal sequence based on the two target signal mutation points; processing the target transient signal sequence using a test mode decomposition model to obtain a target conversion signal sequence; processing the target conversion signal sequence using a target fingerprint extraction model to obtain a device fingerprint identifier of the wireless device; and determining the legitimacy of the wireless device according to the similarity between the device fingerprint identifier and a reference fingerprint identifier in a database.

[0070] Figure 1 Schematically shows a flowchart of a method for verifying the legitimacy of a wireless device according to an embodiment of the present disclosure.

[0071] As Figure 1 shown, the method for verifying the legitimacy of a wireless device includes operations S101 to S106.

[0072] In operation S101, collect an initial transient signal sequence transmitted after the wireless device is wirelessly connected to a connected device, where the initial transient signal sequence includes a first initial sub-signal sequence and a second initial sub-signal sequence.

[0073] In operation S102, respectively determine a target signal mutation point on the first initial sub-signal sequence and the second initial sub-signal sequence, where the target signal mutation point represents a transient point that satisfies a mutation probability threshold.

[0074] In operation S103, determine a target transient signal sequence from the initial transient signal sequence based on the two target signal mutation points.

[0075] In operation S104, process the target transient signal sequence using a test mode decomposition model to obtain a target conversion signal sequence.

[0076] In operation S105, process the target conversion signal sequence using a target fingerprint extraction model to obtain a device fingerprint identifier of the wireless device.

[0077] In operation S106, the legitimacy of the wireless device is determined according to the similarity between the device fingerprint identifier and the reference fingerprint identifier in the database.

[0078] According to an embodiment of the present disclosure, the device fingerprint identifier is a unique feature reflected in the signal generated based on the hardware characteristics of the device. During the wireless connection process, the characteristics generated by this fingerprint identifier change over time, but the amplitude of the change is small within a certain time period. For example, within one month, the generated device fingerprint identifier may have a difference of 5% - 10%.

[0079] According to an embodiment of the present disclosure, the wireless device may include a Bluetooth device, a WiFi connection device, and a device wirelessly connected via Bluetooth or WiFi, such as a mobile phone, a computer, a Bluetooth speaker, etc. The device to be connected may be a mobile phone, a router, a network card, etc.

[0080] According to an embodiment of the present disclosure, when the wireless device is connected to the device to be connected, an initial transient signal sequence transmitted by the wireless device is collected. The initial transient signal sequence includes a first half signal sequence and a second half signal sequence, which are respectively a first initial sub-signal sequence and a second initial sub-signal sequence. A target signal mutation point is determined on each of the first initial sub-signal sequence and the second initial sub-signal sequence. The target signal mutation point is a transient point deviating from the standard deviation of the initial transient signal sequence and satisfies a mutation probability threshold, where the mutation probability threshold is set according to actual requirements and may be 0.8, for example.

[0081] According to an embodiment of the present disclosure, the initial transient signal sequence is cut using the two target signal mutation points as the starting point and the ending point to obtain a target transient signal sequence. The target transient signal sequence is processed using an empirical mode decomposition model to obtain a target transformed signal sequence. The target transformed signal sequence is processed using a target fingerprint extraction model to obtain the device fingerprint identifier of the wireless device. The similarity between the device fingerprint identifier and the reference fingerprint identifier of the device pre-stored in the database is calculated, and based on the similarity, it is determined whether the wireless device is the device stored in the database. If the similarity is small, it can be determined that the wireless device does not belong to the device stored in the database, and the wireless device can be determined as an illegal device; otherwise, it is determined as a legal device.

[0082] It should be noted that the reference fingerprint identifier of the device stored in the database refers to the one that has passed legal authentication. This reference fingerprint identifier corresponds to the device. The wireless device may be a device that has been illegally tampered with. The wireless device may have exactly the same information such as the device ID as the legal device. To prevent attackers from using the tampered wireless device to connect to the connected device to steal data, the legality verification method of the wireless device disclosed in the present disclosure can be used to verify the wireless device.

[0083] According to an embodiment of the present disclosure, when the wireless device is already connected, an initial transient signal sequence of the wireless device is collected, trimmed based on the target signal mutation point to determine a target transient signal sequence, and the target transient signal sequence is converted. The similarity between the device fingerprint identifier corresponding to the target conversion signal sequence and the reference fingerprint identifier in the database is calculated to determine the legality of the wireless device. Therefore, at least partially, the technical problem that attackers use tampered wireless devices to steal data in the related art is overcome, and the technical effect of improving data security is achieved.

[0084] Figure 2 A flowchart of a method for obtaining a target signal mutation point according to an embodiment of the present disclosure is schematically shown.

[0085] As Figure 2 shown, a target signal mutation point is determined on the first initial sub-signal sequence and the second initial sub-signal sequence respectively, including operations S201 to S203.

[0086] In operation S201, for any one of the first initial sub-signal sequence and the second initial sub-signal sequence, the sub-signal sequence is divided into multiple target observation sequences.

[0087] In operation S202, for each target observation sequence, the target signal mutation probability model is used to process the target observation sequence to obtain multiple mutation point probabilities.

[0088] In operation S203, according to the multiple mutation point probabilities corresponding to the sub-signal sequence, the transient point with the maximum mutation point probability is determined as a target signal mutation point.

[0089] According to an embodiment of the present disclosure, each sub-signal sequence is evenly divided into multiple target observation sequences. Among them, each target observation sequence includes multiple transient points. A transient point refers to a point that deviates from the standard deviation of the initial transient signal sequence. Using the target signal mutation probability model to process the target observation sequence, the mutation point probability of each transient point can be obtained. For the multiple mutation point probabilities in each sub-signal sequence, the transient point with the maximum mutation point probability is determined as the target signal mutation point. Thus, when two target signal mutation points are obtained, the target transient signal sequence can be determined from the initial transient signal sequence.

[0090] According to an embodiment of the present disclosure, the target signal mutation probability model is trained by the following operations:

[0091] Use each first training sample to train the initial signal mutation probability model, and output a predicted mutation probability. Wherein, the training sample includes a training transient signal sequence, and the initial signal mutation probability model is constructed according to Bayes' theorem.

[0092] Calculate the first loss result of the initial signal mutation probability model according to the predicted mutation probability.

[0093] Iteratively adjust the network parameters of the initial signal mutation probability model according to the first loss result to generate the trained target signal mutation probability model.

[0094] According to an embodiment of the present disclosure, during the training process of the target signal mutation probability model, first construct the initial signal mutation probability model based on Bayes' theorem, use the first training sample to train the initial signal mutation probability model, calculate the first loss result according to the predicted mutation probability output by the initial signal mutation probability model during the training process, and iteratively adjust the network parameters of the initial signal mutation probability model according to the first loss result to obtain the trained target signal mutation probability model.

[0095] According to an embodiment of the present disclosure, the target observation sequence includes multiple transient points.

[0096] Among them, using the target signal mutation probability model to process the target observation sequence to obtain multiple mutation point probabilities includes the following operations:

[0097] Use the target signal mutation probability model to process each transient point to obtain multiple mutation point probabilities. According to an embodiment of the present disclosure, each mutation point probability corresponds to a transient point, and based on the magnitude of the mutation point probability of the transient point in each sub-signal sequence, the transient point with the largest mutation point probability is determined as a target signal mutation point.

[0098] According to an embodiment of the present disclosure, determining the target transient signal sequence from the initial transient signal sequence based on two target signal mutation points includes the following operations: respectively cut with the positions of the two target signal mutation points in the initial transient signal sequence as endpoints to obtain the target transient signal sequence.

[0099] Figure 3 Schematically shows a schematic diagram of the target conversion signal sequence according to an embodiment of the present disclosure.

[0100] According to an embodiment of the present disclosure, using the empirical mode decomposition model to process the target transient signal sequence to obtain the target conversion signal sequence includes the following operations:

[0101] Processing the target transient signal sequence using an empirical mode decomposition model to obtain multiple narrowband signal sequences, where the narrowband signal sequences include a main narrowband signal sequence and a non-main narrowband signal sequence divided based on frequency.

[0102] Performing an aliasing calculation on the main narrowband signal sequence and the non-main narrowband signal sequence to obtain an initial conversion signal sequence.

[0103] Performing a Hilbert-Huang transform on the initial conversion signal sequence to obtain a target conversion signal sequence.

[0104] According to an embodiment of the present disclosure, processing the target transient signal sequence using an empirical mode decomposition (EMD) model can obtain a main narrowband signal sequence and a non-main narrowband signal sequence divided based on frequency. At the same time, the empirical mode decomposition model can perform an aliasing calculation on the main narrowband signal sequence and the non-main narrowband signal sequence to obtain an initial conversion signal sequence. Performing a Hilbert-Huang (HHT) transform on this initial conversion signal sequence gives Figure 3 the target conversion signal sequence shown. Processing the target conversion signal sequence using a target fingerprint extraction model to obtain the device fingerprint identifier of the wireless device, and then determining the legitimacy of the wireless device based on the similarity between the device fingerprint identifier and the reference fingerprint identifier in the database.

[0105] According to an embodiment of the present disclosure, processing the target conversion signal sequence using a target fingerprint extraction model to obtain the device fingerprint identifier of the wireless device includes the following operations:

[0106] Processing the target conversion signal sequence using a target fingerprint extraction model to obtain the passive fingerprint identifier of the wireless device. Generating a device fingerprint identifier based on the active fingerprint identifier and the passive fingerprint identifier of the wireless device, where the active fingerprint identifier includes the attribute identifier of the wireless device, and the attribute identifier includes at least one of the following: the serial number of the wireless device, the IP address, the gateway address, the media access control address (MAC), and the digital signal sequence processing version (DSP version).

[0107] According to an embodiment of the present disclosure, the passive fingerprint identifier can be a feature vector, for example, a 20-dimensional feature vector.

[0108] According to an embodiment of the present disclosure, processing the target conversion signal sequence using a target fingerprint extraction model to obtain the passive fingerprint identifier of the wireless device, and splicing the passive fingerprint identifier with the attribute identifier of the wireless device itself to obtain a device fingerprint identifier that can characterize the wireless device.

[0109] According to an embodiment of the present disclosure, preferably, a media access control address can be selected as the active fingerprint identifier of the present disclosure.

[0110] According to an embodiment of the present disclosure, the target fingerprint extraction model is trained through the following operations:

[0111] Obtain a training sample set, where the training sample set includes a plurality of second training samples, and the second training sample includes a training conversion signal sequence and label data corresponding to the training conversion signal sequence, and the label data includes the passive fingerprint identifier of a legitimate device.

[0112] For each second training sample, input the training conversion signal sequence into the initial fingerprint extraction model to output a predicted fingerprint identifier.

[0113] Calculate a loss function based on the predicted fingerprint identifier and the label data to obtain a second loss result.

[0114] Iteratively adjust the network parameters of the initial fingerprint extraction model according to the second loss result to generate a trained target fingerprint extraction model.

[0115] According to an embodiment of the present disclosure, the initial fingerprint extraction model may include a three-layer autoencoder network. First, randomly initialize the weights of each layer of the initial fingerprint extraction model, and then set the sizes of the hidden layer parameters of the three-layer autoencoder network to 500, 100, and 20 respectively, so as to obtain a 20-dimensional feature vector.

[0116] According to an embodiment of the present disclosure, when training the target fingerprint extraction model using the second training sample, the initial fingerprint extraction model can output a predicted fingerprint identifier for each training conversion signal sequence. The predicted fingerprint identifier belongs to one kind of passive fingerprint. Calculate the second loss result according to the predicted fingerprint identifier and the label data, and then iteratively adjust the network parameters of the initial fingerprint extraction model according to the second loss result to generate a trained target fingerprint extraction model.

[0117] It should be noted that the initial fingerprint extraction model may not only include a three-layer autoencoder network, but also include autoencoder networks with other numbers of layers. The sizes of the hidden layer parameters of each layer of the autoencoder network can be specifically set according to actual needs.

[0118] Figure 4 Schematically shows a flowchart for determining the legitimacy of a wireless device according to an embodiment of the present disclosure.

[0119] As Figure 4 shown, determine the legitimacy of the wireless device according to the similarity between the device fingerprint identifier and the reference fingerprint identifier in the database, including the following operations:

[0120] Calculate the similarity between the device fingerprint identifier and the reference fingerprint identifier by using either the Polynomial Chaos Expansions (PCE) or the target fingerprint extraction model, where the device attribute identifier corresponding to the reference fingerprint identifier is the same as the attribute identifier of the wireless device.

[0121] When the similarity meets the similarity threshold, determine the wireless device as a legal device.

[0122] When the similarity does not meet the similarity threshold, determine the wireless device as an illegal device.

[0123] According to an embodiment of the present disclosure, the similarity threshold is specifically set according to the actual situation. For example, it can be 0.8. Both the device attribute identifier and the attribute identifier can be at least one of the serial number, IP address, gateway address, Media Access Control (MAC) address, and Digital Signal Processing (DSP) version of the wireless device.

[0124] In one embodiment, the chaos polynomial expansion method can be used to calculate the similarity between the device fingerprint identifier and the reference fingerprint identifier. For example, when the calculated similarity is 0.7, since this similarity is less than the similarity threshold, the wireless device can be determined as an illegal device. When the calculated similarity is 0.85, since this similarity is greater than the similarity threshold, the wireless device can be determined as a legal device.

[0125] In another embodiment, the target fingerprint extraction model can be used to calculate the similarity. Specifically, input the device fingerprint identifier and the reference fingerprint identifier into the target fingerprint extraction model, and the target fingerprint extraction model can output the similarity between the two, so as to determine the legitimacy of the wireless device according to this similarity.

[0126] It should be noted that the method for calculating the similarity is not limited to the above two methods, and other methods can also be used for similarity calculation.

[0127] Figure 5 Schematically shows a schematic diagram of the filtered initial transient signal sequence according to an embodiment of the present disclosure.

[0128] According to an embodiment of the present disclosure, the method for verifying the legitimacy of a wireless device further includes at least one of the following operations:

[0129] Perform filtering processing on the initial transient signal sequence to obtain a filtered initial transient signal sequence, so as to determine the target signal mutation point by using the filtered initial transient signal sequence.

[0130] When it is determined that the wireless device is an illegal device, send a control instruction to the connected device so that the connected device disconnects from the wireless device in response to the control instruction.

[0131] When it is determined that the wireless device is a legal device, determine the device fingerprint identifier of the wireless device as the new reference fingerprint identifier and store it in the database.

[0132] According to an embodiment of the present disclosure, in order to obtain a more accurate initial transient signal sequence and reduce the interference of environmental noise, a low-pass filter can be used to filter the initial transient signal sequence to obtain the filtered initial transient signal sequence as shown in Figure 5 . Among them, the low-pass filter can use the low-pass filter of the FDATool toolbox built in MATLAB, and the frequency band of the low-pass filter can be set to 2.4 GHz.

[0133] According to an embodiment of the present disclosure, in order to prevent data from being stolen by an attacker, when it is determined that the wireless device is an illegal device, a control instruction can be sent to the connected device so that the connected device disconnects from the wireless device in response to the control instruction.

[0134] According to an embodiment of the present disclosure, since the device fingerprint information changes over time, although the change amplitude is small, within a long time span, it is possible that the same wireless device is identified as an illegal device after this time period. Therefore, the device fingerprint identifier determined to be a legal device each time can be determined as the new reference fingerprint identifier, or the most recent device fingerprint identifier can be determined as the new reference fingerprint identifier after an interval of a preset time period. For example, the reference fingerprint can be updated every month.

[0135] In an exemplary embodiment, when the wireless device is a Bluetooth device, a signal collector can be used to collect the initial transient signal sequence at a sampling frequency of 500 MHz, the signal collection length is 100,000, and the corresponding collection time is 20 microseconds, and finally an initial transient signal sequence with a size of about 400 kb is obtained.

[0136] In another exemplary embodiment, when the wireless device is a WiFi device, the wireless device can be connected to an Intel 5300 Wi-Fi network card and operate in the IEEE 802.11n mode, with a center frequency of 2442 MHz and a bandwidth of 20 MHz. At this time, a signal collector can be used to collect the initial transient signal sequence at a sampling frequency of 5 g Hz, the restricted bandwidth range is 2422 - 2462 kHz, the signal collection length is 100,000, and the corresponding collection time is 20 microseconds, and finally an initial transient signal sequence with a size of about 400 kb is obtained.

[0137] In both of the above two embodiments, the USRP-2944 device can be used as a signal collector.

[0138] According to an embodiment of the present disclosure, the method for verifying the legitimacy of a wireless device may further include the following operations:

[0139] Obtain a verification training set of the same wireless device, where the verification training set includes a training set accounting for 75% and a test set accounting for 25%.

[0140] Use the training set to train the empirical mode decomposition model and the target fingerprint extraction model.

[0141] Use the method for verifying the legitimacy of a wireless device to verify each test sample in the test set to determine the legitimacy of the wireless device.

[0142] Determine the effectiveness of the legitimacy verification method according to the accuracy rate of legitimacy. Among them, the accuracy rate in this embodiment reaches 93%. It can be seen that the method for verifying the legitimacy of a wireless device according to the present disclosure can effectively identify a wireless device tampered with by an attacker and reduce the possibility of data being stolen.

[0143] Figure 6 Schematically shows a block diagram of a device for verifying the legitimacy of a wireless device according to an embodiment of the present disclosure.

[0144] As Figure 6 shown, the device 600 for verifying the legitimacy of a wireless device includes an acquisition module 610, a first determination module 620, a second determination module 630, a processing module 640, an extraction module 650, and a comparison module 660.

[0145] The acquisition module 610 is configured to acquire an initial transient signal sequence transmitted after the wireless device is wirelessly connected to the connected device, where the initial transient signal sequence includes a first initial sub-signal sequence and a second initial sub-signal sequence.

[0146] The first determination module 620 is configured to determine a target signal mutation point on each of the first initial sub-signal sequence and the second initial sub-signal sequence, where the target signal mutation point represents a transient point that satisfies the mutation probability threshold.

[0147] The second determination module 630 is configured to determine a target transient signal sequence from the initial transient signal sequence based on the two target signal mutation points.

[0148] The processing module 640 is configured to process the target transient signal sequence by using the empirical mode decomposition model to obtain a target transformed signal sequence.

[0149] An extraction module 650 is configured to process the target conversion signal sequence by using a target fingerprint extraction model to obtain a device fingerprint identifier of the wireless device.

[0150] A comparison module 660 is configured to determine the legitimacy of the wireless device according to the similarity between the device fingerprint identifier and a reference fingerprint identifier in the database.

[0151] According to an embodiment of the present disclosure, when the wireless device is already connected, an initial transient signal sequence of the wireless device is collected, trimmed based on a target signal mutation point to determine a target transient signal sequence, and the target transient signal sequence is converted. The similarity between the device fingerprint identifier corresponding to the target conversion signal sequence and the reference fingerprint identifier in the database is calculated to determine the legitimacy of the wireless device. Therefore, at least partially, the technical problem that an attacker uses a tampered wireless device to steal data in the related art is overcome, and the technical effect of improving the data security is achieved.

[0152] According to an embodiment of the present disclosure, the first determination module 620 includes a segmentation unit, a processing unit, and a determination unit.

[0153] The segmentation unit is configured to segment either the first initial sub-signal sequence or the second initial sub-signal sequence into a plurality of target observation sequences.

[0154] The processing unit is configured to process each target observation sequence by using a target signal mutation probability model to obtain a plurality of mutation point probabilities.

[0155] The determination unit is configured to determine, according to the plurality of mutation point probabilities corresponding to the sub-signal sequence, the transient point with the maximum mutation point probability as a target signal mutation point.

[0156] According to an embodiment of the present disclosure, the target signal mutation probability model is trained by a first training unit, a first calculation unit, a first calculation unit, and a first generation unit.

[0157] The first training unit is configured to train an initial signal mutation probability model by using each first training sample and output a predicted mutation probability. The training sample includes a training transient signal sequence, and the initial signal mutation probability model is constructed according to Bayes' theorem.

[0158] The first calculation unit is configured to calculate a first loss result of the initial signal mutation probability model according to the predicted mutation probability.

[0159] The first generation unit is configured to iteratively adjust the network parameters of the initial signal mutation probability model according to the first loss result to generate a trained target signal mutation probability model.

[0160] According to an embodiment of the present disclosure, the target observation sequence includes a plurality of transient points.

[0161] According to an embodiment of the present disclosure, the processing unit includes an obtaining subunit.

[0162] The obtaining subunit is configured to process each transient point by using the target signal mutation probability model to obtain a plurality of mutation point probabilities.

[0163] According to an embodiment of the present disclosure, the second determination module 630 includes a cutting unit.

[0164] The cutting unit is configured to perform cutting by using the positions of two target signal mutation points in the initial transient signal sequence as endpoints respectively to obtain a target transient signal sequence.

[0165] According to an embodiment of the present disclosure, the processing module 640 includes an obtaining unit, an operation unit, and a transformation unit.

[0166] The obtaining unit is configured to process the target transient signal sequence by using the empirical mode decomposition model to obtain a plurality of narrowband signal sequences, where the narrowband signal sequence includes a main narrowband signal sequence and a non-main narrowband signal sequence divided based on frequency.

[0167] The operation unit is configured to perform aliasing calculation on the main narrowband signal sequence and the non-main narrowband signal sequence to obtain an initial conversion signal sequence.

[0168] The transformation unit is configured to perform Hilbert-Huang transform on the initial conversion signal sequence to obtain a target conversion signal sequence.

[0169] According to an embodiment of the present disclosure, the extraction module 650 includes an extraction unit and a second generation unit.

[0170] The extraction unit is configured to process the target conversion signal sequence by using the target fingerprint extraction model to obtain the passive fingerprint identifier of the wireless device.

[0171] The second generation unit is configured to generate a device fingerprint identifier according to the active fingerprint identifier and the passive fingerprint identifier of the wireless device, where the active fingerprint identifier includes the attribute identifier of the wireless device, and the attribute identifier includes at least one of the following: the serial number of the wireless device, the IP address, the gateway address, the media access control address, and the digital signal sequence processing version.

[0172] According to an embodiment of the present disclosure, the target fingerprint extraction model is trained by an obtaining unit, a second training unit, a second calculation unit, and an iteration unit.

[0173] An acquisition unit for acquiring a training sample set, where the training sample set includes a plurality of second training samples, and the second training samples include a training conversion signal sequence and label data corresponding to the training conversion signal sequence, and the label data includes the passive fingerprint identifier of a legitimate device.

[0174] A second training unit for inputting the training conversion signal sequence into an initial fingerprint extraction model for each second training sample and outputting a predicted fingerprint identifier.

[0175] A second calculation unit for calculating a loss function based on the predicted fingerprint identifier and the label data to obtain a second loss result.

[0176] An iteration unit for iteratively adjusting the network parameters of the initial fingerprint extraction model according to the second loss result to generate a trained target fingerprint extraction model.

[0177] According to an embodiment of the present disclosure, the comparison module 660 includes a third calculation unit, a legitimate unit, and an illegal unit.

[0178] A third calculation unit for calculating the similarity between the device fingerprint identifier and the reference fingerprint identifier by using the chaotic polynomial expansion method, where the device attribute identifier corresponding to the reference fingerprint identifier is the same as the attribute identifier of the wireless device.

[0179] A legitimate unit for determining the wireless device as a legitimate device when the similarity meets the similarity threshold.

[0180] An illegal unit for determining the wireless device as an illegal device when the similarity does not meet the similarity threshold.

[0181] According to an embodiment of the present disclosure, the legitimacy verification device 600 of the wireless device further includes at least one of a filtering module, a control module, and an update module.

[0182] A filtering module for filtering the initial transient signal sequence to obtain a filtered initial transient signal sequence for determining the target signal mutation point by using the filtered initial transient signal sequence.

[0183] A control module for sending a control instruction to the connected device when it is determined that the wireless device is an illegal device, so that the connected device disconnects the connection with the wireless device in response to the control instruction.

[0184] An update module for determining the device fingerprint identifier of the wireless device as a new reference fingerprint identifier and storing it in the database when it is determined that the wireless device is a legitimate device.

[0185] Any of a plurality of modules, units, and subunits according to embodiments of the present disclosure, or at least part of the functions of any of them, may be implemented in one module. Any one or more of the modules, units, and subunits according to embodiments of the present disclosure may be split into multiple modules for implementation. Any one or more of the modules, units, and subunits according to embodiments of the present disclosure may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by any other reasonable way of integrating or packaging circuits, in hardware or firmware, or in any one of the three implementation manners of software, hardware, and firmware, or in a suitable combination of any of them. Alternatively, one or more of the modules, units, and subunits according to embodiments of the present disclosure may be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding functions may be executed.

[0186] For example, any of a plurality of the acquisition module 610, the first determination module 620, the second determination module 630, the processing module 640, the extraction module 650, and the comparison module 660 may be combined and implemented in one module / unit / subunit, or any one of the modules / units / subunits may be split into multiple modules / units / subunits. Alternatively, at least part of the functions of one or more of these modules / units / subunits may be combined with at least part of the functions of other modules / units / subunits and implemented in one module / unit / subunit. According to embodiments of the present disclosure, at least one of the acquisition module 610, the first determination module 620, the second determination module 630, the processing module 640, the extraction module 650, and the comparison module 660 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by any other reasonable way of integrating or packaging circuits, etc., in hardware or firmware, or in any one of the three implementation manners of software, hardware, and firmware, or in a suitable combination of any of them. Alternatively, at least one of the acquisition module 610, the first determination module 620, the second determination module 630, the processing module 640, the extraction module 650, and the comparison module 660 may be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding functions may be executed.

[0187] It should be noted that the legal verification device part in the embodiments of the present disclosure corresponds to the legal verification method part in the embodiments of the present disclosure. For the description of the legal verification device part, please refer to the legal verification method part specifically, and it will not be elaborated here.

[0188] Figure 7 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Figure 7 The shown electronic device is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0189] As Figure 7 shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage section 708 into a random access memory (RAM) 703. The processor 701 can include, for example, a general microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as an application specific integrated circuit (ASIC)), and so on. The processor 701 can also include on-board memory for caching purposes. The processor 701 can include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiments of the present disclosure.

[0190] In the RAM 703, various programs and data required for the operation of the electronic device 700 are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. The processor 701 performs various operations of the method flow according to the embodiments of the present disclosure by executing the programs in the ROM 702 and / or the RAM 703. It should be noted that the program can also be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 701 can also perform various operations of the method flow according to the embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0191] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, and the input / output (I / O) interface 705 is also connected to the bus 704. The system 700 may further include one or more of the following components connected to the I / O interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. The drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed so that a computer program read from it can be installed into the storage portion 708 as needed.

[0192] According to an embodiment of the present disclosure, the method flow according to the embodiment of the present disclosure may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes program codes for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication portion 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above-described functions defined in the system according to the embodiment of the present disclosure are performed. According to an embodiment of the present disclosure, the above-described systems, devices, apparatuses, modules, units, etc. may be implemented by computer program modules.

[0193] The present disclosure also provides a computer-readable storage medium, which may be included in the device / device / system described in the above embodiment; or may exist separately without being assembled into the device / device / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0194] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include but is not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0195] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include one or more memories other than the above-described ROM 702 and / or RAM 703 and / or ROM 702 and RAM 703.

[0196] Embodiments of the present disclosure further include a computer program product, which includes a computer program that contains program code for executing the method provided by the embodiments of the present disclosure. When the computer program product runs on an electronic device, the program code is used to cause the electronic device to implement the legitimacy verification method provided by the embodiments of the present disclosure.

[0197] When the computer program is executed by the processor 701, the above functions defined in the system / apparatus of the embodiments of the present disclosure are executed. According to an embodiment of the present disclosure, the above-described systems, apparatuses, modules, units, etc. may be implemented by computer program modules.

[0198] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium and downloaded and installed through the communication part 709, and / or installed from the removable medium 711. The program code included in the computer program may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0199] According to embodiments of the present disclosure, program code for executing the computer programs provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, such as Java, C++, Python, the "C" language, or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0200] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions. Those skilled in the art can understand that the features described in various embodiments and / or claims of the present disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in various embodiments and / or claims of the present disclosure can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present disclosure.

[0201] The above describes the embodiments of the present disclosure. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present disclosure.

Claims

1. A method for verifying the legitimacy of a wireless device, comprising: Collecting an initial transient signal sequence transmitted after the wireless device is wirelessly connected to a connected device, where the initial transient signal sequence includes a first initial sub-signal sequence and a second initial sub-signal sequence, and the first initial sub-signal sequence and the second initial sub-signal sequence are respectively the first half signal sequence and the second half signal sequence of the initial transient signal sequence; Determining a target signal mutation point on each of the first initial sub-signal sequence and the second initial sub-signal sequence, where the target signal mutation point represents a transient point that satisfies a mutation probability threshold; Determining a target transient signal sequence from the initial transient signal sequence based on the two target signal mutation points; Processing the target transient signal sequence using a test mode decomposition model to obtain a plurality of narrowband signal sequences, where the narrowband signal sequences include a main narrowband signal sequence and a non-main narrowband signal sequence divided based on frequency; Performing aliasing calculation on the main narrowband signal sequence and the non-main narrowband signal sequence to obtain an initial conversion signal sequence; Performing Hilbert-Huang transform on the initial conversion signal sequence to obtain a target conversion signal sequence; Processing the target conversion signal sequence using a target fingerprint extraction model to obtain the device fingerprint identifier of the wireless device; Determining the legitimacy of the wireless device according to the similarity between the device fingerprint identifier and a reference fingerprint identifier in a database.

2. The method according to claim 1, wherein The determining a target signal mutation point on each of the first initial sub-signal sequence and the second initial sub-signal sequence includes: For any one of the first initial sub-signal sequence and the second initial sub-signal sequence, dividing the sub-signal sequence into a plurality of target observation sequences; For each of the target observation sequences, processing the target observation sequence using a target signal mutation probability model to obtain a plurality of mutation point probabilities; According to the plurality of mutation point probabilities corresponding to the sub-signal sequence, determining the transient point with the largest mutation point probability as one of the target signal mutation points.

3. The method according to claim 2, wherein, The target signal mutation probability model is trained by the following method: Using each first training sample to train an initial signal mutation probability model and outputting a predicted mutation probability, where the first training sample includes a training transient signal sequence, and the initial signal mutation probability model is constructed according to Bayes' theorem; Calculating a first loss result of the initial signal mutation probability model according to the predicted mutation probability; Iteratively adjusting the network parameters of the initial signal mutation probability model according to the first loss result to generate the trained target signal mutation probability model.

4. According to the method of claim 2, the target observation sequence includes a plurality of transient points; Among them, The processing the target observation sequence using a target signal mutation probability model to obtain a plurality of mutation point probabilities includes: Using the target signal mutation probability model to process each of the transient points to obtain a plurality of the mutation point probabilities; Wherein, the determining a target transient signal sequence from the initial transient signal sequence based on the two target signal mutation points includes: Cut the initial transient signal sequence with the positions of the two target signal mutation points as endpoints respectively to obtain the target transient signal sequence.

5. The method according to claim 1, wherein Processing the target conversion signal sequence by using the target fingerprint extraction model to obtain the device fingerprint identifier of the wireless device includes: Processing the target conversion signal sequence by using the target fingerprint extraction model to obtain the passive fingerprint identifier of the wireless device; Generating the device fingerprint identifier according to the active fingerprint identifier and the passive fingerprint identifier of the wireless device, wherein the active fingerprint identifier includes the attribute identifier of the wireless device, and the attribute identifier includes at least one of the following: serial number of the wireless device, IP address, gateway address, media access control address, digital signal sequence processing version.

6. The method according to claim 1 or 5, wherein The target fingerprint extraction model is trained in the following manner: Obtain a training sample set, wherein the training sample set includes a plurality of second training samples, and the second training sample includes a training conversion signal sequence and label data corresponding to the training conversion signal sequence, and the label data includes the passive fingerprint identifier of a legal device; For each of the second training samples, input the training conversion signal sequence into the initial fingerprint extraction model to output a predicted fingerprint identifier; Calculate a loss function according to the predicted fingerprint identifier and the label data to obtain a second loss result; Iteratively adjust the network parameters of the initial fingerprint extraction model according to the second loss result to generate the trained target fingerprint extraction model.

7. The method according to claim 1, wherein Determining the legitimacy of the wireless device according to the similarity between the device fingerprint identifier and the reference fingerprint identifier in the database includes: Calculating the similarity between the device fingerprint identifier and the reference fingerprint identifier by using any one of the chaotic polynomial expansion method and the target fingerprint extraction model, wherein the device attribute identifier corresponding to the reference fingerprint identifier is the same as the attribute identifier of the wireless device; When the similarity meets the similarity threshold, determine the wireless device as a legal device; When the similarity does not meet the similarity threshold, determine the wireless device as an illegal device.

8. The method according to claim 1, further comprising: Performing filtering processing on the initial transient signal sequence to obtain a filtered initial transient signal sequence, so as to determine the target signal mutation point by using the filtered initial transient signal sequence; and / or When it is determined that the wireless device is an illegal device, sending a control instruction to the connected device so that the connected device disconnects the connection with the wireless device in response to the control instruction; and / or When it is determined that the wireless device is a legal device, determining the device fingerprint identifier of the wireless device as a new reference fingerprint identifier and storing it in the database.

9. A device for verifying the legitimacy of a wireless device, comprising: A collection module, configured to collect an initial transient signal sequence transmitted after the wireless device is wirelessly connected to the connected device, where the initial transient signal sequence includes a first initial sub-signal sequence and a second initial sub-signal sequence, and the first initial sub-signal sequence and the second initial sub-signal sequence are respectively the first half signal sequence and the second half signal sequence of the initial transient signal sequence; A first determination module, configured to determine a target signal mutation point on each of the first initial sub-signal sequence and the second initial sub-signal sequence, where the target signal mutation point represents a transient point that satisfies a mutation probability threshold; A second determination module, configured to determine a target transient signal sequence from the initial transient signal sequence based on the two target signal mutation points; A processing module, including: An obtaining unit, configured to process the target transient signal sequence by using an empirical mode decomposition model to obtain a plurality of narrowband signal sequences, where the narrowband signal sequences include a main narrowband signal sequence and a non-main narrowband signal sequence divided based on frequency; An operation unit, configured to perform aliasing calculation on the main narrowband signal sequence and the non-main narrowband signal sequence to obtain an initial conversion signal sequence; A transformation unit, configured to perform Hilbert-Huang transform on the initial conversion signal sequence to obtain a target conversion signal sequence; An extraction module, configured to process the target conversion signal sequence by using a target fingerprint extraction model to obtain a device fingerprint identifier of the wireless device; A comparison module, configured to determine the legitimacy of the wireless device according to the similarity between the device fingerprint identifier and a reference fingerprint identifier in a database.

Images