CN116233844A - Physical layer equipment identity authentication method and system based on channel prediction - Google Patents

Physical layer equipment identity authentication method and system based on channel prediction Download PDF

Info

Publication number
CN116233844A
CN116233844A CN202310229817.5A CN202310229817A CN116233844A CN 116233844 A CN116233844 A CN 116233844A CN 202310229817 A CN202310229817 A CN 202310229817A CN 116233844 A CN116233844 A CN 116233844A
Authority
CN
China
Prior art keywords
state information
channel state
authentication
equipment
legal
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.)
Pending
Application number
CN202310229817.5A
Other languages
Chinese (zh)
Inventor
高贞贞
韩泊良
廖学文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Jiaotong University
Original Assignee
Xian Jiaotong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xian Jiaotong University filed Critical Xian Jiaotong University
Priority to CN202310229817.5A priority Critical patent/CN116233844A/en
Publication of CN116233844A publication Critical patent/CN116233844A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/06—Authentication
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/373—Predicting channel quality or other radio frequency [RF] parameters
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer Security & Cryptography (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

A physical layer equipment identity authentication method and system based on channel prediction, the method includes the following steps: channel state information of legal equipment at the authentication moment is predicted through a periodically updated long-short-term memory network; constructing a receiving domain around channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation; and estimating the channel state information of the received signal, if the channel state information of the received signal falls in the receiving domain, judging that the received signal is from legal equipment, otherwise, judging that the received signal is from illegal equipment. The periodically updated long-short-period memory network can adapt to the change of the learning environment, the invention can adapt to the dynamic scene well and does not need to acquire the channel information of an attacker in the implementation process. When the combined authentication is carried out by utilizing a plurality of subcarriers, the method can further improve the overall authentication performance by adopting the subcarrier interval selection strategy.

Description

Physical layer equipment identity authentication method and system based on channel prediction
Technical Field
The invention belongs to the technical field of communication, and relates to a physical layer equipment identity authentication method and system based on channel prediction.
Background
Communication technology is evolving at a high rate towards more access devices, more mass connections, and more widely used scenarios. The openness of the wireless channel, however, makes the communication device vulnerable to a wide variety of attacks, such as eavesdropping attacks, interference attacks, spoofing attacks, etc. A large amount of private, confidential information is transmitted in a wireless network, which places higher demands on the security of the wireless communication network. Device identity authentication is particularly important as a first step in securing communications.
Traditional device identity authentication is typically implemented using upper-layer key-based security mechanisms, such as challenge-response based mechanisms. The mechanism is based on mathematical calculation by utilizing an encryption technology on the premise of assuming limited calculation capability of an attacker, and ensures that the attacker cannot finish decryption within effective time by distributing key encryption. However, with the development of quantum computing and other technologies, the computing capability has made breakthrough progress, and the key is easily broken and stolen due to abundant computing resources. Meanwhile, the key-based upper security mechanism not only needs to perform complex operations such as encoding and decoding on the upper layer, but also needs to share and manage the key. The complex operation of the upper layers results in higher complexity, while the sharing and management of keys results in higher costs. In networks such as the internet of things, the internet of vehicles and unmanned aerial vehicles, terminal equipment generally has the characteristics of miniaturization and low power consumption. This makes conventional key-based security mechanisms difficult to implement in such large-scale heterogeneous and decentralized wireless networks.
Physical layer authentication is being widely studied as an effective complement to upper layer authentication schemes due to its low complexity, high accuracy characteristics. Physical layer authentication mainly uses the characteristic physical layer characteristics among wireless communication devices as the natural fingerprints of the identity of the wireless communication devices to perform identity authentication. Physical layer characteristics do not need to be specially generated due to endogenous characteristics, and high recognition accuracy can be obtained while low complexity is ensured due to uniqueness and characteristics which are difficult to imitate. At present, some studies on physical layer authentication by using machine learning and deep learning algorithms exist, for example, schemes for extracting two-dimensional channel characteristics according to channel state information and performing authentication by using an extreme learning machine are available; there have been schemes for device authentication using an adaptive matrix and convolutional neural network to automatically extract features; however, deep learning based schemes require channel information of illegal attackers as training samples and cannot adapt to dynamic scenarios. The existing authentication scheme based on Gaussian process regression can be well adapted to dynamic scenes and does not need channel information of illegal attackers as training, but the performance of the scheme is limited by a single kernel function form of Gaussian process regression.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provide a physical layer equipment identity authentication method and a physical layer equipment identity authentication system based on channel prediction, which can realize the identity authentication effect which does not need illegal attacker channel information and is suitable for dynamic environment.
In order to achieve the above purpose, the present invention has the following technical scheme:
a physical layer equipment identity authentication method based on channel prediction comprises the following steps:
channel state information of legal equipment at the authentication moment is predicted through a periodically updated long-short-term memory network;
constructing a receiving domain around channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation;
and estimating the channel state information of the received signal, if the channel state information of the received signal falls in the receiving domain, judging that the received signal is from legal equipment, otherwise, judging that the received signal is from illegal equipment.
As a preferable scheme, the periodically updated long-short-period memory network predicts the channel state information of the next moment by using the channel state information of d continuous moments;
the input x (n) to the long and short term memory network is expressed as:
Figure BDA0004119889770000021
in the formula ,
Figure BDA0004119889770000022
representing real channel state information on the m-th subcarrier at the n moment;
the labels corresponding to the inputs x (n) are:
Figure BDA0004119889770000023
tag y (n) is the channel state information on the m-th subcarrier at the next moment;
the whole training set is as follows:
X＝(x(1),x(2),…,x(N))
wherein N represents the size of the training set, the corresponding label set is y= (Y (1), Y (2), …, Y (N)), and the output value of the network is recorded as
Figure BDA0004119889770000031
Minimizing the loss function by gradient descent method>
Figure BDA0004119889770000032
Updating network parameters to complete the training process;
after training of the network is completed, channel state information of the legal device at the detection time t+1 is predicted:
will be
Figure BDA0004119889770000033
Inputting the data into a trained network, wherein the obtained network output value is the predicted value of legal channel at time t+1
Figure BDA0004119889770000034
As a preferable scheme, the long-term and short-term memory network updated regularly takes the optimal weight with the minimum training loss value as the initial weight of the retraining every time in the last training process when the network is retrained, and the bias is initialized randomly so that the network is updated regularly to track the change of the environment, and the retraining interval is determined according to the change condition of a wireless channel.
As a preferable scheme, the bayesian parameter estimation estimates the prediction error range of legal channel state information at the detection moment so as to construct a legal receiving area; the step of constructing a receiving domain around channel state information of legal devices at the authentication time includes:
the prediction error is:
Figure BDA0004119889770000035
wherein ,
Figure BDA0004119889770000036
respectively representing predicted and real channel state information on the mth subcarrier at the time t+1; prediction error e (m) (t+1) is modeled as a mean value of μ (m) The variance is phi (m) Gaussian distribution of->
Figure BDA0004119889770000037
Figure BDA0004119889770000038
Bayesian estimation obtains prediction error estimation mu in training set according to training stage (m) and φ(m) ；
μ (m) and φ(m) The bayesian estimation values of (2) are respectively:
Figure BDA0004119889770000039
Figure BDA00041198897700000310
wherein ：
Figure BDA0004119889770000041
Figure BDA0004119889770000042
Figure BDA0004119889770000043
in the formula ,
Figure BDA0004119889770000044
for initialization constants, N is the size of the training set,
Figure BDA0004119889770000045
Figure BDA0004119889770000046
the receiving domain is constructed as the following expression:
Figure BDA0004119889770000047
wherein q is a parameter for determining the size of the receiving domain, and a q value is selected according to the false alarm rate requirement; the channel state information estimated from the received signal is considered to be from a legitimate device if it falls within the receiving domain, otherwise it is considered to be from an attacker.
As a preferable scheme, the physical layer equipment identity authentication method based on channel prediction utilizes channel state information on a plurality of subcarriers to carry out joint authentication, and the authentication process is as follows:
channel state information of legal equipment at the authentication moment is predicted on a plurality of subcarriers through a periodically updated long-short-period memory network respectively; constructing a receiving domain around the channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation;
and estimating the channel state information of the received signals on the plurality of subcarriers, if the channel state information of the received signals on all the subcarriers falls in a receiving domain, judging that the received signals come from legal equipment, otherwise, judging that the received signals come from illegal equipment.
As a preferable scheme, the plurality of subcarriers select subcarriers for authentication at a fixed interval Δd, and the interval Δd is determined according to the subcarrier correlation size.
A physical layer device identity authentication system based on channel prediction, comprising:
the legal equipment channel state information prediction module is used for predicting the channel state information of legal equipment at the authentication moment through a periodically updated long-short-period memory network;
the legal receiving domain construction module is used for constructing a receiving domain around the channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation;
and the judging module is used for estimating the channel state information of the received signal, judging that the received signal is from legal equipment if the channel state information of the received signal falls in the receiving domain, and judging that the received signal is from illegal equipment if the channel state information of the received signal falls in the receiving domain.
As a preferable scheme, the physical layer equipment identity authentication system based on channel prediction performs joint authentication by using channel state information on a plurality of subcarriers, and the authentication process is as follows:
channel state information of legal equipment at the authentication moment is predicted on a plurality of subcarriers through a periodically updated long-short-period memory network respectively; constructing a receiving domain around the channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation;
and estimating the channel state information of the received signals on the plurality of subcarriers, if the channel state information of the received signals on all the subcarriers falls in a receiving domain, judging that the received signals come from legal equipment, otherwise, judging that the received signals come from illegal equipment.
An electronic device, comprising:
a memory storing at least one instruction; and the processor executes the instructions stored in the memory to realize the physical layer equipment identity authentication method based on channel prediction.
A computer readable storage medium storing a computer program which when executed by a processor implements the channel prediction based physical layer device identity authentication method.
Compared with the prior art, the invention has at least the following beneficial effects:
the channel state information of legal equipment at the authentication moment is predicted by using a periodically updated long-short-period memory network, the periodically updated long-short-period memory network can adapt to the change of a learning environment, a Bayesian parameter estimation is utilized, a receiving domain is constructed around the channel state information of the legal equipment at the authentication moment, the channel state information of a received signal is estimated, if the channel state information of the received signal falls in the receiving domain, the received signal is judged to come from the legal equipment, otherwise, the received signal is judged to come from illegal equipment, the channel information training of an attacker is not needed, and the better authentication performance can be obtained in a dynamic environment.
Furthermore, the invention uses the channel state information on a plurality of sub-carriers to carry out joint authentication, and when the authentication is carried out by using a plurality of sub-carriers, the authentication accuracy of the system can be further improved by adopting a sub-carrier interval selection strategy.
Drawings
Fig. 1 is a schematic diagram of a physical layer equipment identity authentication method based on channel prediction applied to a wireless network according to an embodiment of the present invention;
FIG. 2 is a graph showing the effect of channel prediction based on a periodically updated long-short-term memory network in accordance with an embodiment of the present invention;
FIG. 3 is a graph comparing authentication performance based on a Gaussian process regression scheme;
fig. 4 is an effect diagram of an exemplary carrier spacing selection strategy according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, one of ordinary skill in the art may also obtain other embodiments without undue burden.
Referring to fig. 1, an embodiment of the present invention proposes a physical layer device identity authentication method based on channel prediction, when the physical layer device identity authentication method is applied to a wireless network architecture, legal sending device Alice and legal receiving device Bob attempt to establish legal communication connection, however, a signal transmitted in a wireless channel may also be captured by Eve, where Eve may extract information such as an MAC address of Alice from the information camouflage as Alice identity to attack Bob. Bob extracts physical layer information from the received signal to judge the source of the signal, and judges whether the signal comes from legal sending equipment or illegal sending equipment.
Specifically, the physical layer equipment identity authentication method based on channel prediction comprises the following steps:
1) Predicting the channel state information of legal equipment at the detection moment by using a periodically updated long-short-period memory network:
the periodically updated long and short term memory network predicts the channel state information of the next time using the channel state information of d consecutive times, where d represents the number of times the channel state information is employed. The input x (n) of the network can be expressed as:
Figure BDA0004119889770000061
wherein ,
Figure BDA0004119889770000062
indicating channel state information on the m-th subcarrier at time n. The labels corresponding to x (n) are:
Figure BDA0004119889770000063
the tag y (n) is the channel state information on the mth subcarrier at the next moment.
The entire training set can thus be noted as x= (X (1), X (2), …, X (N)), where N represents the size of the training set.
The corresponding tag set is y= (Y (1), Y (2)) …, y (N)). The output value of the network is recorded as
Figure BDA0004119889770000071
Minimizing the loss function by gradient descent method>
Figure BDA0004119889770000072
Updating network parameters to complete the training process.
After training of the network is completed, channel state information of legal equipment at a detection time t+1 is predicted, namely:
Figure BDA0004119889770000073
inputting into the trained network, wherein the obtained network output value is the predicted value of legal channel at time t+1
Figure BDA0004119889770000074
The wireless channel changes over time due to movement of the device, etc., so the above network requires periodic training to avoid situations where network parameters are outdated and do not keep up with the wireless channel changes. In order to reduce training time, when the network retrains, the embodiment of the invention adopts the idea of incremental updating, and each time the network retrains, the optimal weight with the minimum training loss value in the previous training process is used as the initial weight of the retraining, and the bias is initialized randomly to train so that the network updates the change of the tracking environment periodically. The retraining interval may be determined based on the wireless channel variation.
2) Constructing a receiving domain around the legal device channel state information predicted at the detection moment by using Bayesian estimation for authentication:
when the receiving domain is constructed, the Bayesian estimation is utilized to estimate the prediction error range of the legal channel state information at the detection moment so as to construct the legal receiving domain. The prediction error is noted as:
Figure BDA0004119889770000075
wherein ,
Figure BDA0004119889770000076
respectively representing the predicted and real channel state information on the mth subcarrier at the time t+1. Prediction error e (m) (t+1) is modeled as a mean value of μ (m) The variance is phi (m) Gaussian distribution of->
Figure BDA0004119889770000077
Figure BDA0004119889770000078
Bayesian estimation mu of prediction error in training set obtained from training stage of meter (m) and φ(m) 。μ (m) and φ(m) The bayesian estimation of (2) is:
Figure BDA0004119889770000079
Figure BDA00041198897700000710
wherein ：
Figure BDA0004119889770000081
Figure BDA0004119889770000082
Figure BDA0004119889770000083
in the formula ,
Figure BDA0004119889770000084
for initialization constants, N is the size of the training set,
Figure BDA0004119889770000085
Figure BDA0004119889770000086
thus, the receiving domain may be constructed as:
Figure BDA0004119889770000087
where q is a parameter for determining the size of the receiving domain, and a suitable q value can be selected according to the false alarm rate requirement. Channel state information estimated from a received signal is considered to be from a legitimate device if it falls within the receiving domain, otherwise from an attacker.
In a possible implementation manner, the physical layer equipment identity authentication method based on channel prediction performs joint authentication by using channel state information on a plurality of subcarriers, and the authentication process is as follows:
3.1 Repeating steps 1) and 2) on a plurality of subcarriers respectively to conduct channel prediction and construct a receiving domain.
3.2 And judging by combining authentication results on a plurality of subcarriers, and if the channel state information estimated from the received signals on all the subcarriers falls in the receiving domain, judging that the method is legal, otherwise, judging that the method is illegal.
The selection of a plurality of sub-carriers can further improve the authentication accuracy of the system by adopting a sub-carrier interval selection strategy, namely, the sub-carriers with stronger independence are selected for authentication at a fixed interval delta D.
The interval Δd may be determined according to the employed subcarrier correlation size. The interval Δd should take a larger value when the subcarrier correlation is larger, and the interval Δd should take a smaller value when the subcarrier correlation is smaller.
Simulation results show that the method can obtain a better equipment identity authentication effect in a dynamic scene. Meanwhile, the authentication accuracy of the system can be further improved through the subcarrier interval selection strategy.
In order to verify the performance of the physical layer equipment identity authentication method based on channel prediction, the following simulation is carried out:
simulation conditions
The simulation experiment adopts Quasi Deterministic Radio Channel Generator (QuadriGa) channel generating software to generate a dynamic channel which is closer to an actual scene. In the simulation experiment, the center frequency is set to be 2.53GHz, the baseband bandwidth is 20MHz, the subcarrier number is 128, the BERLIN_ UMa _LOS scene is adopted as the scene, and the sampling number of each half wavelength is 4. The legitimate sending device Alice starts from 10m from Bob in the forward eastern direction at a constant speed principle Bob. The attacker Eve makes a uniform circular motion around Bob on a circle with a radius of 10 m. The long-term memory network adopts a two-layer network structure, and the number of neurons is 80 and 100 respectively. An Adam optimizer is adopted, and the initial learning rate is 1e-3. The web training stops 50 rounds and the batch size is 32.
Simulation content and result analysis
As can be seen from fig. 2, the channel prediction is performed by using the periodically updated long-short-term memory network, and the normalized Channel State Information (CSI) real value and the predicted value are very close, so that the channel of the composite device can be better predicted. The authentication performance pair of the method and the regression scheme based on the Gaussian process is shown in figure 3. The authentication performance is reflected by a false alarm rate and omission rate curve, and the lower the curve is, the better the authentication performance is. As can be seen from fig. 3, the authentication performance of the method in the dynamic scenario is better than that of the authentication scheme based on gaussian process regression. This is because the authentication scheme based on gaussian process regression predicts using a kernel function of a fixed form in the channel prediction stage, and does not necessarily represent the current environment well. The method of the invention adopts the periodically updated long-short-period memory network to carry out channel prediction, can self-adaptively learn the current environment, and obtains better channel prediction performance and further obtains better authentication effect. Fig. 4 illustrates the effect of the subcarrier spacing selection strategy employed in joint authentication using channel state information on multiple subcarriers. In fig. 4, the authentication effect of whether the subcarrier spacing selection policy is adopted or not when two subcarriers (m=2) and three subcarriers (m=3) are adopted is compared. It can be seen that the effect of using the subcarrier spacing selection strategy is better than not using the subcarrier spacing selection strategy, whether two or three subcarrier authentications are used. This is because the subcarrier spacing selection strategy can select the subcarrier with greater independence for authentication, and the authentication effect is better.
Therefore, it can be known that, in summary, the physical layer equipment identity authentication method based on channel prediction provided by the embodiment of the invention can be well adapted to dynamic scenes, and the channel information of an attacker does not need to be acquired in the implementation process. When the combined authentication is carried out by utilizing a plurality of subcarriers, the method can further improve the overall authentication performance by adopting the subcarrier interval selection strategy.
The invention also provides a physical layer equipment identity authentication system based on channel prediction, which comprises:
the legal equipment channel state information prediction module is used for predicting the channel state information of legal equipment at the authentication moment through a periodically updated long-short-period memory network;
the legal receiving domain construction module is used for constructing a receiving domain around the channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation;
and the judging module is used for estimating the channel state information of the received signal, judging that the received signal is from legal equipment if the channel state information of the received signal falls in the receiving domain, and judging that the received signal is from illegal equipment if the channel state information of the received signal falls in the receiving domain.
In one possible implementation manner, the physical layer equipment identity authentication system based on channel prediction performs joint authentication by using channel state information on a plurality of subcarriers, and the authentication process is as follows:
channel state information of legal equipment at the authentication moment is predicted on a plurality of subcarriers through a periodically updated long-short-period memory network respectively; constructing a receiving domain around the channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation;
and estimating the channel state information of the received signals on the plurality of subcarriers, if the channel state information of the received signals on all the subcarriers falls in a receiving domain, judging that the received signals come from legal equipment, otherwise, judging that the received signals come from illegal equipment.
The embodiment of the invention also provides electronic equipment, which comprises:
a memory storing at least one instruction; and the processor executes the instructions stored in the memory to realize the physical layer equipment identity authentication method based on channel prediction.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the physical layer equipment identity authentication method based on channel prediction when being executed by a processor.
The instructions stored in the memory may be partitioned into one or more modules/units, which are stored in a computer-readable storage medium and executed by the processor to perform the channel prediction-based physical layer device identity authentication method of the present invention, for example. The one or more modules/units may be a series of computer readable instruction segments capable of performing a specified function, which describes the execution of the computer program in a server.
The electronic equipment can be a smart phone, a notebook computer, a palm computer, a cloud server and other computing equipment. The electronic device may include, but is not limited to, a processor, a memory. Those skilled in the art will appreciate that the electronic device may also include more or fewer components, or may combine certain components, or different components, e.g., the electronic device may also include input and output devices, network access devices, buses, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may be an internal storage unit of the server, such as a hard disk or a memory of the server. The memory may also be an external storage device of the server, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the server. Further, the memory may also include both an internal storage unit and an external storage device of the server. The memory is used to store the computer readable instructions and other programs and data required by the server. The memory may also be used to temporarily store data that has been output or is to be output.
It should be noted that, because the content of information interaction and execution process between the above module units is based on the same concept as the method embodiment, specific functions and technical effects thereof may be referred to in the method embodiment section, and details thereof are not repeated herein.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing device/terminal apparatus, recording medium, computer Memory, read-Only Memory (ROM), random access Memory (RAM, random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims (10)

1. The physical layer equipment identity authentication method based on channel prediction is characterized by comprising the following steps:
channel state information of legal equipment at the authentication moment is predicted through a periodically updated long-short-term memory network;
constructing a receiving domain around channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation;
and estimating the channel state information of the received signal, if the channel state information of the received signal falls in the receiving domain, judging that the received signal is from legal equipment, otherwise, judging that the received signal is from illegal equipment.
2. The physical layer equipment identity authentication method based on channel prediction according to claim 1, wherein the periodically updated long-short-term memory network predicts channel state information at the next time by using channel state information at d consecutive times;
the input x (n) to the long and short term memory network is expressed as:
Figure FDA0004119889760000011
in the formula ,
Figure FDA0004119889760000012
representing real channel state information on the m-th subcarrier at the n moment;
the labels corresponding to the inputs x (n) are:
Figure FDA0004119889760000013
tag y (n) is the channel state information on the m-th subcarrier at the next moment;
the whole training set is as follows:
X＝(x(1)，x(2)，...，x(N))
wherein N represents the size of the training set, the corresponding label set is y= (Y (1), Y (2), and the output value of the network is recorded as y= (Y (2))
Figure FDA0004119889760000014
Minimizing the loss function by gradient descent method>
Figure FDA0004119889760000015
Updating network parameters to complete the training process;
after training of the network is completed, channel state information of the legal device at the detection time t+1 is predicted:
will be
Figure FDA0004119889760000016
Inputting the data into a trained network, wherein the obtained network output value is the predicted value of legal channel at time t+1
Figure FDA0004119889760000017
3. The physical layer equipment identity authentication method based on channel prediction according to claim 2, wherein the long-term and short-term memory network updated regularly uses the optimal weight with the minimum training loss value as the initial weight of the retraining every time the network is retrained, and the bias is initialized randomly so that the network is updated regularly to track the change of the environment, and the retrained interval is determined according to the change condition of the wireless channel.
4. The physical layer equipment identity authentication method based on channel prediction according to claim 1, wherein the bayesian parameter estimation estimates a prediction error range of legal channel state information at a detection moment so as to construct a legal receiving area; the step of constructing a receiving domain around channel state information of legal devices at the authentication time includes:
the prediction error is:
Figure FDA0004119889760000021
wherein ,
Figure FDA0004119889760000022
respectively representing predicted and real channel state information on the mth subcarrier at the time t+1; prediction error e (m) (t+1) is modeled as a mean value of μ (m) The variance is phi (m) Gaussian distribution of->
Figure FDA0004119889760000023
Figure FDA0004119889760000024
Bayesian estimation obtains prediction error estimation mu in training set according to training stage (m) and φ(m) ；
μ (m) and φ(m) The bayesian estimation values of (2) are respectively:
Figure FDA0004119889760000025
/>
Figure FDA0004119889760000026
wherein ：
Figure FDA0004119889760000027
Figure FDA0004119889760000028
Figure FDA0004119889760000029
in the formula ,
Figure FDA00041198897600000210
for initializing the constant, N is the size of the training set, +.>
Figure FDA00041198897600000211
Figure FDA00041198897600000212
The receiving domain is constructed as the following expression:
Figure FDA0004119889760000031
wherein q is a parameter for determining the size of the receiving domain, and a q value is selected according to the false alarm rate requirement; the channel state information estimated from the received signal is considered to be from a legitimate device if it falls within the receiving domain, otherwise it is considered to be from an attacker.
5. The physical layer equipment identity authentication method based on channel prediction according to claim 1, wherein the joint authentication is performed by using channel state information on a plurality of subcarriers, and the authentication process is as follows:
channel state information of legal equipment at the authentication moment is predicted on a plurality of subcarriers through a periodically updated long-short-period memory network respectively; constructing a receiving domain around the channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation;
and estimating the channel state information of the received signals on the plurality of subcarriers, if the channel state information of the received signals on all the subcarriers falls in a receiving domain, judging that the received signals come from legal equipment, otherwise, judging that the received signals come from illegal equipment.
6. The physical layer equipment identity authentication method based on channel prediction according to claim 5, wherein the plurality of subcarriers select subcarriers for authentication at a fixed interval Δd, and the interval Δd is determined according to the subcarrier correlation size.
7. A physical layer device identity authentication system based on channel prediction, comprising:
the legal equipment channel state information prediction module is used for predicting the channel state information of legal equipment at the authentication moment through a periodically updated long-short-period memory network;
the legal receiving domain construction module is used for constructing a receiving domain around the channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation;
and the judging module is used for estimating the channel state information of the received signal, judging that the received signal is from legal equipment if the channel state information of the received signal falls in the receiving domain, and judging that the received signal is from illegal equipment if the channel state information of the received signal falls in the receiving domain.
8. The physical layer equipment identity authentication system based on channel prediction according to claim 7, wherein the joint authentication is performed by using channel state information on a plurality of sub-carriers, and the authentication process is as follows:
channel state information of legal equipment at the authentication moment is predicted on a plurality of subcarriers through a periodically updated long-short-period memory network respectively; constructing a receiving domain around the channel state information of legal equipment at the authentication moment by using Bayesian parameter estimation;
and estimating the channel state information of the received signals on the plurality of subcarriers, if the channel state information of the received signals on all the subcarriers falls in a receiving domain, judging that the received signals come from legal equipment, otherwise, judging that the received signals come from illegal equipment.
9. An electronic device, comprising:
a memory storing at least one instruction; a kind of electronic device with high-pressure air-conditioning system
A processor executing instructions stored in the memory to implement the channel prediction based physical layer device identity authentication method of any one of claims 1 to 6.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the channel prediction based physical layer device identity authentication method of any one of claims 1 to 6.
CN202310229817.5A 2023-03-10 2023-03-10 Physical layer equipment identity authentication method and system based on channel prediction Pending CN116233844A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310229817.5A CN116233844A (en) 2023-03-10 2023-03-10 Physical layer equipment identity authentication method and system based on channel prediction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310229817.5A CN116233844A (en) 2023-03-10 2023-03-10 Physical layer equipment identity authentication method and system based on channel prediction

Publications (1)

Publication Number Publication Date
CN116233844A true CN116233844A (en) 2023-06-06

Family

ID=86569317

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310229817.5A Pending CN116233844A (en) 2023-03-10 2023-03-10 Physical layer equipment identity authentication method and system based on channel prediction

Country Status (1)

Country Link
CN (1) CN116233844A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116647843A (en) * 2023-06-16 2023-08-25 广东省通信产业服务有限公司 Method and system for zero-trust dynamic access authentication

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116647843A (en) * 2023-06-16 2023-08-25 广东省通信产业服务有限公司 Method and system for zero-trust dynamic access authentication
CN116647843B (en) * 2023-06-16 2024-02-09 广东省通信产业服务有限公司 Method and system for zero-trust dynamic access authentication

Similar Documents

Publication Publication Date Title
Qi et al. Privacy-preserving blockchain-based federated learning for traffic flow prediction
Kumar et al. TP2SF: A Trustworthy Privacy-Preserving Secured Framework for sustainable smart cities by leveraging blockchain and machine learning
Diro et al. Leveraging LSTM networks for attack detection in fog-to-things communications
Tewari et al. Cryptanalysis of a novel ultra-lightweight mutual authentication protocol for IoT devices using RFID tags
He et al. Attacking and protecting data privacy in edge–cloud collaborative inference systems
Kumar et al. P2tif: A blockchain and deep learning framework for privacy-preserved threat intelligence in industrial iot
Barbareschi et al. A PUF-based mutual authentication scheme for cloud-edges IoT systems
CN111639361A (en) Block chain key management method, multi-person common signature method and electronic device
Istiaque Ahmed et al. Machine learning for authentication and authorization in iot: Taxonomy, challenges and future research direction
US11599832B2 (en) Systems, circuits and computer program products providing a framework for secured collaborative training using hyper-dimensional vector based data encoding/decoding and related methods
Zhang et al. LSFL: A lightweight and secure federated learning scheme for edge computing
CN111581648B (en) Method of federal learning to preserve privacy in irregular users
CN116233844A (en) Physical layer equipment identity authentication method and system based on channel prediction
Li et al. DDoS mitigation based on space-time flow regularities in IoV: A feature adaption reinforcement learning approach
Momand et al. A systematic and comprehensive survey of recent advances in intrusion detection systems using machine learning: deep learning, datasets, and attack taxonomy
Khan et al. Blind faith: Privacy-preserving machine learning using function approximation
Smahi et al. BV-ICVs: A privacy-preserving and verifiable federated learning framework for V2X environments using blockchain and zkSNARKs
CN117216788A (en) Video scene identification method based on federal learning privacy protection of block chain
Hernandez-Ramos et al. Intrusion Detection based on Federated Learning: a systematic review
Yin et al. Ginver: generative model inversion attacks against collaborative inference
CN112347513B (en) Block chain node identity authentication method and system based on channel state information
Yoon et al. Pufgan: Embracing a self-adversarial agent for building a defensible edge security architecture
Raji et al. Secure forensic data transmission system in cloud database using fuzzy based butterfly optimization and modified ECC
CN116340986A (en) Block chain-based privacy protection method and system for resisting federal learning gradient attack
Jung et al. DeepAuditor: Distributed Online Intrusion Detection System for IoT devices via Power Side-channel Auditing

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