CN112637834B - Fingerprint fusion identification method and device for wireless communication equipment - Google Patents
Fingerprint fusion identification method and device for wireless communication equipment Download PDFInfo
- Publication number
- CN112637834B CN112637834B CN202110261668.1A CN202110261668A CN112637834B CN 112637834 B CN112637834 B CN 112637834B CN 202110261668 A CN202110261668 A CN 202110261668A CN 112637834 B CN112637834 B CN 112637834B
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- characteristic
- channel
- wireless communication
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004891 communication Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000004927 fusion Effects 0.000 title claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 47
- 230000004044 response Effects 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 3
- 230000035939 shock Effects 0.000 claims description 2
- 238000004590 computer program Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 10
- 230000015654 memory Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007635 classification algorithm Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W8/00—Network data management
- H04W8/22—Processing or transfer of terminal data, e.g. status or physical capabilities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/10—Monitoring; Testing of transmitters
- H04B17/101—Monitoring; Testing of transmitters for measurement of specific parameters of the transmitter or components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/06—Authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Electromagnetism (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a fingerprint fusion identification method and a fingerprint fusion identification device of wireless communication equipment, wherein the fingerprint fusion identification method comprises the following steps: acquiring and identifying a device fingerprint and a channel fingerprint of wireless communication equipment; determining carrier frequency offset characteristics and amplitude characteristics of the device fingerprint; respectively transposing the carrier frequency offset characteristic and the amplitude characteristic to obtain a first carrier frequency offset characteristic and a first amplitude characteristic; converting the impulse response of the wireless communication channel into a time sequence; adding the historical characteristics and the future characteristics of the channel fingerprint after the first carrier frequency offset characteristics and the first amplitude characteristics to form a joint characteristic vector; training the combined feature vector; acquiring a channel fingerprint and an equipment fingerprint of equipment to be identified, and comparing the channel fingerprint and the equipment fingerprint with comparison fingerprints in a fusion fingerprint library to obtain a judgment result; on the basis of ensuring the traditional identity authentication and identification efficiency, the method improves the accuracy of joint judgment and reduces the misjudgment rate caused by singly using channel fingerprints or equipment fingerprints for identification.
Description
Technical Field
The invention relates to the field of artificial intelligence and information security, in particular to a fingerprint fusion identification method and device of wireless communication equipment.
Background
With the increasing number of mobile communication devices and the development of internet of things technology, wireless communication has become a crucial section of the communication field. However, due to the openness of the wireless network, compared with the traditional wired network, the wireless network is more vulnerable, the wireless network security protocol usually has a vulnerability and is easily attacked by statistical analysis and the like, and at present, a complete and practical security mechanism is not available for realizing the identity authentication of the wireless communication device so as to effectively identify authorized users and unauthorized users.
The existing fingerprint identification method of wireless communication equipment generally adopts radio frequency characteristics based on a transmitter analog circuit or channel-based characteristics, so that the hardware characteristics of the equipment can be extracted according to communication signals only when the communication equipment used by a sender has obvious hardware differences, otherwise, a receiver is easy to generate misjudgment. In addition, the channel-based characterization method may also generate misjudgment due to the wireless channel response and the influence of the surrounding environment.
Disclosure of Invention
In order to improve the accuracy of identity recognition and authentication of wireless communication equipment, the invention provides a fingerprint fusion recognition method and a fingerprint fusion recognition device of the wireless communication equipment, which realize the identity recognition and authentication of the wireless communication equipment, and meanwhile, the introduction and the improvement of an intelligent algorithm improve the accuracy of joint judgment on the basis of ensuring the recognition and judgment efficiency, and effectively reduce the misjudgment rate caused by the recognition by singly using channel fingerprints or equipment fingerprints.
In order to achieve the above object, an aspect of the present invention provides a fingerprint fusion identification method for a wireless communication device, including:
acquiring and identifying a device fingerprint and a channel fingerprint of wireless communication equipment;
determining carrier frequency offset characteristics and amplitude characteristics of the device fingerprint;
transposing the carrier frequency offset characteristic and the amplitude characteristic respectively to obtain a first carrier frequency offset characteristic and a first amplitude characteristic;
converting the impact response of a wireless communication channel into a time sequence, and determining a characteristic vector of the channel fingerprint according to the time sequence; wherein the feature vector comprises historical features and future features;
adding the historical characteristics and the future characteristics of the channel fingerprint after the first carrier frequency offset characteristics and the first amplitude characteristics to form a joint characteristic vector;
training the combined feature vector, and establishing a fusion fingerprint library by using the trained first feature vector;
and acquiring the channel fingerprint and the equipment fingerprint of the equipment to be identified, and comparing the channel fingerprint and the equipment fingerprint with the comparison fingerprint in the fusion fingerprint library to obtain a judgment result.
Optionally, the determining carrier frequency offset characteristics and amplitude characteristics of the device fingerprint further includes:
carrying out down-conversion and signal compensation on the signal of the device fingerprint, and detecting and intercepting identifiable signals;
and carrying out radio frequency fingerprint transformation on the identifiable signals, and calculating the carrier frequency offset characteristics and the amplitude characteristics of the signals.
Optionally, the training the first feature vector specifically includes:
extracting N samples from a sample set of the acquired wireless communication equipment to obtain a training set with the size of N, wherein N = μ M, M is the size of an original sample set, and μ is a value which enables the integrated learner formed by combining all the base learners to have the highest accuracy;
selecting any n characteristics from the combined characteristic vector, and selecting 1 characteristic from the n characteristics according to information gain to split nodes, wherein n = ceil [ sqrt (m) ]; wherein sqrt is an open square root function; ceil is an rounding-up function; m is the total number of the combined features;
and repeating the sub-segmentation until all the nodes are split, and forming the base learners with different classification performances.
Optionally, the repeating sub-dividing is performed until all the nodes are split, so as to form a base learner with different classification performances, and then the method further includes:
re-collecting a data set of a device fingerprint and a channel fingerprint of the wireless communication device as a test set of the base learner;
inputting the test set into the base learners to obtain the correct classification ratio CRt of each base learner to the test set data as the screening standard of the corresponding base learners;
screening the base learners by taking CRt < lambda as a standard, removing the base learners with poor performance, endowing the same weight to all the remaining base learners, detecting, classifying and counting sample data to obtain the category with the maximum total ticket number as the final category of the sample data; where λ is a value that maximizes the joint discrimination accuracy.
Optionally, the converting the impulse response of the wireless communication channel into a time sequence, and determining the eigenvector of the channel fingerprint according to the time sequence, further includes:
constructing new training data by intercepting data of different time windows on the shock response sequence;
and dividing each group of training data according to the historical characteristics and the future characteristics, taking each group of divided data as a group of characteristic values, and taking a set formed by all the characteristic values as a characteristic vector of a training set.
Optionally, the set of all feature values is used as a feature vector of a training set, and then the method further includes:
and adding corresponding prediction labels to each group of training data, and combining all the prediction labels to be used as labels of a training set.
On the other hand, the invention also provides a fingerprint fusion identification device of wireless communication equipment, which comprises:
a first acquisition unit for acquiring and identifying a device fingerprint and a channel fingerprint of a wireless communication device;
the determining unit is used for determining the carrier frequency offset characteristic and the amplitude characteristic of the device fingerprint;
the transposition unit is used for respectively transposing the carrier frequency offset characteristic and the amplitude characteristic to obtain a first carrier frequency offset characteristic and a first amplitude characteristic;
the conversion unit is used for converting the impact response of the wireless communication channel into a time sequence and determining the characteristic vector of the channel fingerprint according to the time sequence; wherein the feature vector comprises historical features and future features;
the adding unit is used for adding the historical characteristics and the future characteristics of the channel fingerprint after the first carrier frequency offset characteristics and the first amplitude characteristics to form a joint characteristic vector;
the training unit is used for training the combined feature vector and establishing a fusion fingerprint database by using the trained first feature vector;
and the second acquisition unit is used for acquiring the channel fingerprint and the equipment fingerprint of the equipment to be identified and comparing the channel fingerprint and the equipment fingerprint with the comparison fingerprint in the fusion fingerprint library to obtain a judgment result.
In the fingerprint fusion recognition apparatus of the wireless communication device, optionally, the determining unit includes:
the preprocessing module is used for carrying out down-conversion and signal compensation on the signal of the device fingerprint, and detecting and intercepting identifiable signals;
and the calculation module is used for carrying out radio frequency fingerprint transformation on the identifiable signals and calculating the carrier frequency offset characteristics and the amplitude characteristics of the signals.
In the fingerprint fusion recognition apparatus of the wireless communication device, optionally, the conversion unit includes:
a construction module for constructing new training data by intercepting data of different time windows on the impulse response sequence;
and the dividing module is used for dividing each group of training data according to the historical characteristics and the future characteristics, the divided data of each group serve as a group of characteristic values, and a set formed by all the characteristic values serves as a characteristic vector of the training set.
In the fingerprint fusion recognition apparatus of the wireless communication device, optionally, the training unit includes:
the extraction module is used for extracting N samples from the collected sample set of the wireless communication equipment to obtain a training set with the size of N, wherein N = mu M, M is the size of the original sample set, and mu is a value which enables the integrated learner formed by combining all the base learners to have the highest accuracy;
a selecting module, configured to select n arbitrary features from the joint feature vector, and select 1 feature from the n features according to information gain to perform node splitting, where n = ceil [ sqrt (m) ]; wherein sqrt is an open square root function; ceil is an rounding-up function; m is the total number of the combined features;
and the segmentation module is used for repeatedly performing sub-segmentation until all the nodes are split, so as to form the base learners with different classification performances.
Compared with the prior art, the invention has the beneficial effects that: the fingerprint fusion identification method has the advantages that the device fingerprint based on the radio frequency characteristics of the analog circuit of the transmitter and the channel fingerprint based on the channel characteristics are fused, so that the misjudgment rate caused by the identification by independently using the channel fingerprint or the device fingerprint is reduced; in addition, the traditional intelligent classification algorithm is introduced and improved on the basis, and the accuracy of the joint judgment of the device fingerprint and the channel fingerprint is improved on the basis of ensuring the identification efficiency of the original algorithm.
Drawings
FIG. 1 is a flow chart of a fingerprint fusion identification method of a wireless communication device in the present invention;
FIG. 2 is a work frame diagram of the present invention;
fig. 3 is a structural diagram of a fingerprint fusion recognition device of a wireless communication device in the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present embodiment provides a fingerprint fusion identification method for a wireless communication device, including the following steps:
s10: acquiring and identifying a device fingerprint and a channel fingerprint of wireless communication equipment;
for the convenience of understanding, the embodiment takes a WiFi 802.11n TL-WDR5620 wireless router as an example to illustrate a specific implementation of the method of the present invention, and the USRP extracts and identifies the device fingerprint of the router.
In other embodiments, the device fingerprint extraction method based on the constellation locus diagram can also be used for generating the device fingerprint extraction method and then transferring the device fingerprint extraction method to a joint decision feature vector for classification and identification.
S20: determining carrier frequency offset characteristics and amplitude characteristics of the device fingerprint;
specifically, the step S10 of partitioning the DATA of the signal frame in the device fingerprint of the wireless communication device obtained in the step S10 and mapping the partitioned DATA onto 48 of the 52 subcarriers, wherein the subcarriers with sequence numbers { -21, -7,7,21} do not bear DATA bits specifically includes the following sub-steps:
firstly, using short preamble symbol k of physical layer frame head of OFDM signal frameshort64=[-24,-20,-16,-12,-8,-4,4,8,12,16,20]The signal frame is captured by the spectral feature of (1);
then, calculating the carrier frequency deviation characteristics
，
Wherein M is the calculation length, k belongs to { -21, -7,7,21}, and X isi(k) The complex vector of the frequency spectrum obtained after FFT conversion is carried out on each OFDM symbol, avg is an averaging function,
(x) Representing the phase of the computed complex number x [ ]]Representing the nearest integer to the elements in the bracket, and {. represents the bracket.
S30: transposing the carrier frequency offset characteristic and the amplitude characteristic respectively to obtain a first carrier frequency offset characteristic and a first amplitude characteristic;
specifically, transposing the extracted 12 groups of carrier frequency offset characteristics and amplitude characteristics through a transposition function reshape (-1, 1) in python, and splicing the transposed amplitude characteristics and frequency offset characteristics to form a characteristic vector as a device fingerprint of the wireless communication device;
in other embodiments, the extracted device fingerprint of the wireless communication device is trained, and the training model is saved by a model saving function dump in python;
in other embodiments, the device fingerprint of the device to be identified is collected and compared to the reference fingerprint of the device it purports to be, to determine if its identity matches.
S40: converting the impact response of a wireless communication channel into a time sequence, and determining a characteristic vector of the channel fingerprint according to the time sequence;
specifically, in the present implementation, the impulse response of the router TL-WDR5620 is collected by intercepting data of different time windows on historical data, and then manually dividing each set of data into historical features and future features.
It should be noted that, in this embodiment, the historical feature and the future feature are divided according to the time of data acquisition, the first N-1 data of the currently acquired data is used as the historical data, and the nth data is used as the future data, where N is the length of the group of data.
S50: adding the historical characteristics and the future characteristics of the channel fingerprint after the first carrier frequency offset characteristics and the first amplitude characteristics to form a joint characteristic vector;
specifically, predictive signatures are constructed for each set of data, including historical signature (predictive signature A) [ 0.74980.74840.74710.7457 ] and future signature (predictive signature B) [0.7444] and predictive Target [0], respectively. And then all the obtained prediction features are combined to be used as training set features, all the prediction targets are combined to be used as training set targets, and a machine learning model is constructed.
S60: training the combined feature vector, and establishing a fusion fingerprint library by using the trained first feature vector;
in this embodiment, the collecting of the sample set M =165 and the number of features M =18 of the router TL-WDR5620 specifically includes the following sub-steps:
extracting N samples from an original sample set in a manner of sampling back to obtain a training set with the size of N, wherein N =1.2M =198, and M is the size of the original sample set;
selecting arbitrary n characteristics from the combined characteristic vector of the device fingerprint and the channel fingerprint, wherein n = ceil [ sqrt (m) ] =5, m is the total number of the combined characteristics, and selecting 1 characteristic from the 5 characteristics to split nodes according to information gain;
repeatedly performing sub-segmentation until all nodes are split, and forming a base learner with different classification performances;
in addition, the obtained training set is randomly selected in a replacement manner, which may result in poor performance of the generated base learner, and therefore, the trained base learners need to be tested and screened, and the voting results of each base learner are integrated to make final decisions. The step of screening the base learner comprises:
firstly, a data set of a device fingerprint and a channel fingerprint of wireless communication equipment is collected again to be used as a test set of a base learner;
secondly, inputting the test set into the base learners to obtain the correct classification ratio CRt of each base learner to the test set data, and using the ratio CRt as the screening standard of the corresponding base learners;
and finally, screening the base learners by taking CRt <0.25 as a standard, endowing the same weight to all the remaining base learners, detecting, classifying and counting sample data to obtain the class with the maximum total ticket number as the final class of the sample data.
S70: and acquiring the channel fingerprint and the equipment fingerprint of the equipment to be identified, and comparing the channel fingerprint and the equipment fingerprint with the comparison fingerprint in the fusion fingerprint library to obtain a judgment result.
Fig. 2 shows a working frame diagram of a method for fusing fingerprint identification of wireless communication devices according to the present invention. The wireless communication equipment to be identified sends a radio frequency signal, the general software radio receiving device is connected with a computer host through a gigabit network cable to collect the signal, and the equipment characteristic and the channel characteristic of the router are extracted to establish a combined characteristic vector. The improved intelligent algorithm classifies the joint features and compares the joint features with the comparison fingerprints in the fingerprint database to obtain a joint judgment result.
The fingerprint fusion identification method has the advantages that the device fingerprint based on the radio frequency characteristics of the analog circuit of the transmitter and the channel fingerprint based on the channel characteristics are fused, so that the misjudgment rate caused by the identification by independently using the channel fingerprint or the device fingerprint is reduced; in addition, the traditional intelligent classification algorithm is introduced and improved on the basis, and the accuracy of the joint judgment of the device fingerprint and the channel fingerprint is improved on the basis of ensuring the identification efficiency of the original algorithm.
Referring to fig. 3, the present embodiment further provides a fingerprint fusion recognition apparatus for a wireless communication device, including:
a first acquisition unit 100 for acquiring and identifying a device fingerprint and a channel fingerprint of a wireless communication device; it should be noted that, since the specific obtaining manner and the process are already described in detail in step S10 of the fingerprint fusion identification method of the wireless communication device, they are not described herein again.
A determining unit 200, configured to determine a carrier frequency offset characteristic and an amplitude characteristic of the device fingerprint; in some embodiments, the determination unit 200 comprises a pre-processing module for down-converting and signal compensating the signal of the device fingerprint, detecting and intercepting the identifiable signal; and the calculation module is used for carrying out radio frequency fingerprint transformation on the identifiable signals and calculating the carrier frequency offset characteristics and the amplitude characteristics of the signals. It should be noted that, since the specific determination method and process are already described in detail in step S20 of the fingerprint merging identification method of the wireless communication device, they are not described herein again.
A transposing unit 300, configured to transpose the carrier frequency offset characteristic and the amplitude characteristic respectively to obtain a first carrier frequency offset characteristic and a first amplitude characteristic; it should be noted that, since the specific transposing method and the process are already described in detail in step S30 of the fingerprint merging identification method of the wireless communication device, they are not described herein again.
A converting unit 400, configured to convert an impulse response of a wireless communication channel into a time sequence, and determine a feature vector of the channel fingerprint according to the time sequence; in some embodiments, the translation unit 400 includes a construction module for constructing new training data by truncating data of different time windows on the impulse response sequence; and the dividing module is used for dividing each group of training data according to the historical characteristics and the future characteristics, the divided data of each group serve as a group of characteristic values, and a set formed by all the characteristic values serves as a characteristic vector of the training set. In addition, since the specific conversion method and process are already described in detail in step S40 of the fingerprint fusion identification method of the wireless communication device, they are not described herein again.
A adding unit 500, configured to add the historical characteristic and the future characteristic of the channel fingerprint after the first carrier frequency offset characteristic and the first amplitude characteristic to form a joint feature vector; since the specific joining method and procedure are already described in detail in step S50 of the fingerprint fusion identification method of the wireless communication device, they are not described herein again.
A training unit 600, configured to train the joint feature vector, and establish a fused fingerprint library by using the trained first feature vector; in some embodiments, the training unit 600 includes an extraction module, configured to extract N samples from the collected sample set of the wireless communication device, resulting in a training set with a size of N, N = μ M, where M is the size of the original sample set, and μ is a value that maximizes the accuracy of the ensemble learner formed by combining all the basis learners; a selecting module, configured to select n arbitrary features from the joint feature vector, and select 1 feature from the n features according to information gain to perform node splitting, where n = ceil [ sqrt (m) ]; wherein sqrt is an open square root function; ceil is an rounding-up function; m is the total number of the combined features; and the segmentation module is used for repeatedly performing sub-segmentation until all the nodes are split, so as to form the base learners with different classification performances.
Since the specific training method and procedure are already described in detail in step S60 of the fingerprint fusion recognition method of the wireless communication device, they are not described herein again.
A second obtaining unit 700, configured to obtain a channel fingerprint and an apparatus fingerprint of an apparatus to be identified, and compare the channel fingerprint and the apparatus fingerprint with a comparison fingerprint in the fused fingerprint library to obtain a decision result; since the specific determination method and process are already described in detail in step S70 of the fingerprint fusion identification method of the wireless communication device, they are not described herein again.
The device integrates the judgment results of the device fingerprint and the channel fingerprint based on the radio frequency characteristics and the channel characteristics of the analog circuit of the transmitter to realize the final combined judgment. The improvement of the intelligent algorithm greatly improves the accuracy of joint judgment on the basis of ensuring the training efficiency, and is particularly suitable for physical layer safety and identity recognition and authentication of wireless equipment.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium may store a program, and when the program is executed, the program includes some or all of the steps of the fingerprint fusion identification method of any wireless communication device described in the above method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a memory and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
An exemplary flow chart of a method for implementing a service chain according to an embodiment of the present invention is described above with reference to the accompanying drawings. It should be noted that the numerous details included in the above description are merely exemplary of the invention and are not limiting of the invention. In other embodiments of the invention, the method may have more, fewer, or different steps, and the order, inclusion, function, etc. of the steps may be different from that described and illustrated.
Claims (7)
1. A fingerprint fusion identification method of a wireless communication device is characterized by comprising the following steps:
acquiring and identifying a device fingerprint and a channel fingerprint of wireless communication equipment;
carrying out down-conversion and signal compensation on the signal of the device fingerprint, and detecting and intercepting identifiable signals;
carrying out radio frequency fingerprint transformation on the identifiable signal, and calculating the carrier frequency offset characteristic and the amplitude characteristic of the signal;
transposing the carrier frequency offset characteristic and the amplitude characteristic respectively to obtain a first carrier frequency offset characteristic and a first amplitude characteristic;
constructing new training data by intercepting data of different time windows on the shock response sequence;
dividing each group of training data according to historical characteristics and future characteristics, taking each group of divided data as a group of characteristic values, and taking a set formed by all the characteristic values as a characteristic vector of a training set; wherein the feature vector comprises historical features and future features;
adding the historical characteristics and the future characteristics of the channel fingerprint after the first carrier frequency offset characteristics and the first amplitude characteristics to form a joint characteristic vector;
training the combined feature vector, and establishing a fusion fingerprint library by using the trained first feature vector;
and acquiring the channel fingerprint and the equipment fingerprint of the equipment to be identified, and comparing the channel fingerprint and the equipment fingerprint with the comparison fingerprint in the fusion fingerprint library to obtain a judgment result.
2. The fingerprint fusion recognition method of claim 1, wherein the training of the joint feature vector specifically includes:
extracting N samples from the collected sample set of the wireless communication equipment to obtain a training set with the size of N, wherein N is mu M, and M is the size of the original sample set; wherein μ is a value that maximizes the accuracy of the ensemble learner formed by combining all the basis learners;
selecting any n characteristics from the combined characteristic vector, and selecting 1 characteristic from the n characteristics according to information gain to split nodes, wherein n is ceil [ sqrt (m) ]; wherein sqrt is an open square root function; ceil is an rounding-up function; m is the total number of the combined features;
and repeating the sub-segmentation until all the nodes are split, and forming the base learners with different classification performances.
3. The fingerprint fusion recognition method of claim 2, wherein the repeating of the sub-division is completed until all the nodes are split, so as to form the base learners with different classification performances, and then further comprising:
re-collecting a data set of a device fingerprint and a channel fingerprint of the wireless communication device as a test set of the base learner;
inputting the test set into the base learner to obtain the ratio CR of each base learner for correctly classifying the data of the test settAs a screening criterion for the corresponding base learner;
by CRt<The lambda is the standard to screen the base learners, remove the base learners with poor performance, endow the same weight to all the remaining base learners, detect, classify and count the sample data, and obtain the class with the maximum total ticket number as the final class of the sample data; where λ is a value that maximizes the joint discrimination accuracy.
4. The fingerprint fusion recognition method of claim 1, wherein after the set of all feature values is used as the feature vector of the training set, the method further comprises:
and adding corresponding prediction labels to each group of training data, and combining all the prediction labels to be used as labels of a training set.
5. A fingerprint fusion recognition device of a wireless communication device, comprising:
a first acquisition unit for acquiring and identifying a device fingerprint and a channel fingerprint of a wireless communication device;
the preprocessing module is used for carrying out down-conversion and signal compensation on the signal of the device fingerprint, and detecting and intercepting identifiable signals;
the calculation module is used for carrying out radio frequency fingerprint transformation on the identifiable signals and calculating the carrier frequency offset characteristics and the amplitude characteristics of the signals;
the transposition unit is used for respectively transposing the carrier frequency offset characteristic and the amplitude characteristic to obtain a first carrier frequency offset characteristic and a first amplitude characteristic;
a construction module for constructing new training data by intercepting data of different time windows on the impulse response sequence;
the dividing module is used for dividing each group of training data according to historical characteristics and future characteristics, the divided data of each group serve as a group of characteristic values, and a set formed by all the characteristic values serves as a characteristic vector of a training set; wherein the feature vector comprises historical features and future features;
the adding unit is used for adding the historical characteristics and the future characteristics of the channel fingerprint after the first carrier frequency offset characteristics and the first amplitude characteristics to form a joint characteristic vector;
the training unit is used for training the combined feature vector and establishing a fusion fingerprint library by using the trained first feature vector;
and the second acquisition unit is used for acquiring the channel fingerprint and the equipment fingerprint of the equipment to be identified and comparing the channel fingerprint and the equipment fingerprint with the comparison fingerprint in the fusion fingerprint library to obtain a judgment result.
6. The fingerprint fusion recognition apparatus of claim 5, wherein the training unit comprises:
the extraction module is used for extracting N samples from the collected sample set of the wireless communication equipment to obtain a training set with the size of N, wherein N is mu M, and M is the size of the original sample set; wherein μ is a value that maximizes the accuracy of the ensemble learner formed by combining all the basis learners;
a selecting module, configured to select n arbitrary features from the joint feature vector, and select 1 feature from the n features according to information gain to perform node splitting, where n ═ ceil [ sqrt (m) ]; wherein sqrt is an open square root function; ceil is an rounding-up function; m is the total number of the combined features;
and the segmentation module is used for repeatedly performing sub-segmentation until all the nodes are split, so as to form the base learners with different classification performances.
7. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of a method for fingerprint fusion recognition of a wireless communication device according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110261668.1A CN112637834B (en) | 2021-03-10 | 2021-03-10 | Fingerprint fusion identification method and device for wireless communication equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110261668.1A CN112637834B (en) | 2021-03-10 | 2021-03-10 | Fingerprint fusion identification method and device for wireless communication equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112637834A CN112637834A (en) | 2021-04-09 |
| CN112637834B true CN112637834B (en) | 2021-06-18 |
Family
ID=75297744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110261668.1A Active CN112637834B (en) | 2021-03-10 | 2021-03-10 | Fingerprint fusion identification method and device for wireless communication equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112637834B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239969B (en) * | 2021-04-15 | 2024-04-30 | 联合汽车电子有限公司 | Feature model establishment method, equipment fingerprint generation method and equipment identification method |
| WO2023113110A1 (en) * | 2021-12-15 | 2023-06-22 | Samsung Electronics Co., Ltd. | Method and system for authenticating wireless devices |
| CN114783006B (en) * | 2022-04-28 | 2024-07-19 | 东南大学 | Wireless device transient state and steady state device fingerprint extraction and identification method based on signal difference |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105635125A (en) * | 2015-12-25 | 2016-06-01 | 电子科技大学 | Physical layer combined authentication method based on RF fingerprint and channel information |
| CN106302397A (en) * | 2016-07-29 | 2017-01-04 | 北京北信源软件股份有限公司 | A kind of equipment identification system based on device-fingerprint |
| CN109660956A (en) * | 2018-12-12 | 2019-04-19 | 东南大学 | A kind of identification pseudo gps signal method based on radio-frequency fingerprint |
| CN111191703A (en) * | 2019-12-24 | 2020-05-22 | 北京百卓网络技术有限公司 | Method and system for analyzing wireless local area network flow |
| CN111385297A (en) * | 2020-03-04 | 2020-07-07 | 西安交通大学 | Wireless device fingerprint identification method, system, device and readable storage medium |
| CN111866876A (en) * | 2020-06-02 | 2020-10-30 | 东南大学 | Wireless equipment identification method and device based on frequency offset preprocessing and storage medium |
-
2021
- 2021-03-10 CN CN202110261668.1A patent/CN112637834B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105635125A (en) * | 2015-12-25 | 2016-06-01 | 电子科技大学 | Physical layer combined authentication method based on RF fingerprint and channel information |
| CN106302397A (en) * | 2016-07-29 | 2017-01-04 | 北京北信源软件股份有限公司 | A kind of equipment identification system based on device-fingerprint |
| CN109660956A (en) * | 2018-12-12 | 2019-04-19 | 东南大学 | A kind of identification pseudo gps signal method based on radio-frequency fingerprint |
| CN111191703A (en) * | 2019-12-24 | 2020-05-22 | 北京百卓网络技术有限公司 | Method and system for analyzing wireless local area network flow |
| CN111385297A (en) * | 2020-03-04 | 2020-07-07 | 西安交通大学 | Wireless device fingerprint identification method, system, device and readable storage medium |
| CN111866876A (en) * | 2020-06-02 | 2020-10-30 | 东南大学 | Wireless equipment identification method and device based on frequency offset preprocessing and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 基于设备与信道特征的物理层安全方法;李古月，等;《密码学报》;20200430;全文 * |
| 无线通信设备的射频指纹提取与识别方法;俞佳宝，等;《密码学报》;20161031;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112637834A (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112637834B (en) | Fingerprint fusion identification method and device for wireless communication equipment | |
| CN111181939B (en) | Network intrusion detection method and device based on ensemble learning | |
| CN107528832B (en) | Baseline construction and unknown abnormal behavior detection method for system logs | |
| CN111107102A (en) | Real-time network flow abnormity detection method based on big data | |
| CN106446877B (en) | A kind of radio-frequency fingerprint feature extraction and recognition methods based on signal amplitude sequence | |
| CN108282460B (en) | Evidence chain generation method and device for network security event | |
| CN112003869B (en) | Vulnerability identification method based on flow | |
| CN111050315B (en) | Wireless transmitter identification method based on multi-core two-way network | |
| CN109903053B (en) | Anti-fraud method for behavior recognition based on sensor data | |
| CN111695597A (en) | Credit fraud group recognition method and system based on improved isolated forest algorithm | |
| CN114492768A (en) | Twin capsule network intrusion detection method based on small sample learning | |
| CN111464510B (en) | Network real-time intrusion detection method based on rapid gradient lifting tree classification model | |
| CN113821793A (en) | Multi-stage attack scene construction method and system based on graph convolution neural network | |
| CN110545284A (en) | Domain name detection method and system for antagonistic network | |
| CN111310719B (en) | Unknown radiation source individual identification and detection method | |
| CN115577357A (en) | Android malicious software detection method based on stacking integration technology | |
| CN111600878A (en) | Low-rate denial of service attack detection method based on MAF-ADM | |
| CN113518073B (en) | Method for rapidly identifying bit currency mining botnet flow | |
| CN110414594B (en) | Encrypted flow classification method based on double-stage judgment | |
| CN117236699A (en) | Network risk identification method and system based on big data analysis | |
| CN111540381A (en) | Voice simulation modulation characteristic recognition method based on random forest | |
| CN115809426A (en) | Radiation source individual identification method and system | |
| CN116647844A (en) | Vehicle-mounted network intrusion detection method based on stacking integration algorithm | |
| CN115996148A (en) | MIMO OFDM communication-oriented electric power Internet of things physical layer equipment authentication method | |
| Shin et al. | Platform design and implementation for flexible data processing and building ML models of IDS alerts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |