Distributed cooperative wireless access security method for satellite direct communication
Through the distributed collaborative wireless access security method, local clustering and model training are used to use multi-UAV collaboration, the problems of poor attack detection reliability and large computing overhead in satellite direct-connected mobile communication network are solved, and the high dynamic features are achieved and frequent switching of continuous attack detection in scenarios.
Patent Information
- Application Number
- CN202411241433.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-05
AI Technical Summary
There are problems in the satellite direct-connected mobile communication network with poor attack detection reliability, high computing overhead, and inability to continuously detect, especially in long-distance high-dynamic features and frequent switching scenarios.
Adopt distributed collaborative wireless access security method, use multi-UAV collaboration for local clustering and model training, combine K nearest neighbor kernel density and high-density nearest neighbor algorithm to generate atomic clusters, use Gaussian model parameters to estimate and aggregate them into a global model, and implement Incremental clustering algorithm to support continuous detection under frequent satellite switching conditions.
It effectively reduces the computing overhead and communication overhead, improves the accuracy and reliability of attack detection, and realizes continuous attack detection in a satellite direct-connected communication environment, suitable for high dynamic characteristics and frequent switching scenarios.
Smart Images

Figure CN118972852A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of satellite communications, and in particular relates to a distributed collaborative wireless access security method for satellite direct communication. Background Art
[0002] In satellite-connected mobile communication networks, satellite nodes have a large coverage area, a large number of service terminals, and long wireless transmission links, facing very serious wireless attack problems such as interference, deception, and distributed denial of service (DDoS). However, satellite node processing power and coverage time are limited, and there are challenges in attack detection and protection capabilities and efficiency.
[0003] At present, some studies have proposed attack detection technology based on upper-layer network features, that is, based on the traffic in the upper-layer network, using feature selection methods such as sequential forward to select important features that increase relevance and reduce complexity from the data set, and then using machine learning, deep learning and other methods to train the model to distinguish between abnormal and normal activities. In addition, some studies have tried to use physical layer features for attack detection, that is, using hardware features such as carrier frequency offset (CFO) or channel features such as channel state information (CSI), comparing them with the reference value of legitimate users to see whether they exceed the threshold to determine whether the user is legitimate or illegal. However, the reliability of single physical layer features is low, and the physical layer features used for detection have gradually expanded from single-dimensional physical layer features to multi-dimensional physical layer features. Further attack detection research has proposed the use of centralized machine learning methods to replace traditional threshold-based methods to effectively increase detection accuracy and reliability.
[0004] The above studies all use ground control centers to implement attack detection. Since the new generation of satellite nodes have certain processing capabilities, they are called regenerative mode satellites. If they can support local attack detection on the satellite, they will have better real-time performance. Moreover, under the trend of integrated development of air, space and land, satellite nodes can further collaborate with flexible, maneuverable and sensitive drones. Existing studies have shown that unmanned aerial vehicles (UAVs) can be used as quantum relays to effectively enhance the security of long-distance model transmission using a quantum-authorized federated learning framework.
[0005] At present, the existing technical solutions and their existing technical problems are as follows:
[0006] (1) Attack detection scheme based on upper-layer network characteristics
[0007] Attack detection solutions based on upper-layer network features select the most relevant features from a large number of traffic features through data selection algorithms, which increases the computational cost and complexity. At the same time, due to the increase in the number of network service terminals in the future, the concealment of attacks is enhanced. Existing attack detection based on upper-layer traffic features is difficult to effectively detect attacks, and even if an attack is detected, it takes a long time.
[0008] (2) Attack detection scheme based on physical layer characteristics
[0009] Attack detection solutions based on physical layer features use centralized machine learning to replace traditional threshold-based methods to increase the accuracy and reliability of attack detection. However, in the satellite direct mobile communication network environment, the existing attack detection based on physical layer features is difficult to apply. There are two specific reasons: first, the long link propagation distance makes it difficult to accurately measure the physical layer features, and attack detection has problems of poor reliability and low accuracy; second, the resources of satellite nodes are limited, and the existing attack detection technology based on centralized machine learning has a large computational overhead, which is difficult to afford for networks with limited node resources.
[0010] (3) At the same time, the above two existing technical solutions both use the ground control center to implement attack detection. However, in order to obtain the corresponding data, multiple communication transmissions are required, and the communication overhead and computational complexity are high. In addition, most of the existing attack detection technologies focus on attack detection solutions for static nodes, without considering the problem of frequent node switching, resulting in the inability of existing attack detection solutions to collect sufficient amounts of data, reducing detection accuracy, and increasing the difficulty of real-time continuous detection.
[0011] In summary, this patent proposes a distributed collaborative wireless access security solution for satellite direct communication, which fundamentally solves the problems of poor attack detection reliability, inability to continuously detect, and high computational overhead caused by long-distance and high-dynamic characteristics in the mobile phone direct communication environment. Summary of the invention
[0012] In view of the problems existing in the prior art, the present invention provides a distributed cooperative wireless access security method for satellite direct communication.
[0013] The technical solution adopted by the present invention to solve the technical problem is as follows:
[0014] A distributed cooperative wireless access security method for satellite direct communication of the present invention comprises the following steps:
[0015] S1: Model training and updating stage;
[0016] S1.1: When the user communicates normally with the satellite base station, N u The drones move at a constant speed along a pre-set trajectory to monitor user access and collect data at the time T.tw Collect user signals internally and calculate the detection sample S(t) composed of RSS and CFO;
[0017] S1.2: The drone uses the detection sample S(t) as local data and uses the local clustering algorithm to combine the K nearest neighbor kernel density and high-density nearest neighbor to generate local clustering k l Atom clusters;
[0018] S1.3: Based on the clustered atomic clusters, the drone uses Gaussian model parameter estimation to generate a Gaussian model corresponding to each atomic cluster, and constructs a local model with the mean, covariance and number of samples of the Gaussian model, and sends the local model to the aggregation center;
[0019] S1.4: The aggregation center aggregates the local models into a global model and obtains K cluster sets;
[0020] S1.5: The aggregation center is a drone or a satellite; if the aggregation center is a drone, the global model needs to be sent to the satellite; if the aggregation center is a satellite, the global model does not need to be sent to the satellite;
[0021] S1.6: The satellite obtains the final K cluster sets C'={C'1,C'2,...,C' K}, C' K ={μ' K ,∑' K ,n' K},μ' K ,∑' K 、n' K Respectively represent the mean, covariance and number of samples of the Kth cluster;
[0022] S1.7: When the satellite switches, the source satellite will detect the attacker's global model parameter I 0 The target satellite uses the incremental clustering algorithm to update the global model and obtain the updated global model parameters I update ;
[0023] S2: attack detection phase;
[0024] S2.1: The satellite detects the attack and estimates the number of attackers through binary hypothesis testing;
[0025] S2.2: When the satellite switches, the source satellite will detect the attacker’s global model parameter I 0 The target satellite uses the incremental clustering algorithm in step S1.7 to update the global model and obtain the updated global model parameters I update , then perform attack detection and attacker number estimation according to step S2.1;
[0026] S2.3: When the number of drones N u When it is greater than or equal to 3, the attacker can be located.
[0027] Furthermore, in step S1.2, in the local clustering process, the detection samples S(t) are automatically divided into different clusters, and the detection samples in the same cluster are regarded as samples from the same user.
[0028] Furthermore, the specific implementation process of the local clustering algorithm is as follows:
[0029] ① All sample points in the drone data set use K nearest neighbor kernel density to represent the local density of each sample point, find high-density neighboring points based on the local density, and determine the core objects;
[0030] ② All sample points in the drone data set construct a graph g = (V, A) based on high-density neighbor points. Vertex V represents the sample point. Each directed edge in A points from a non-core object to its high-density neighbor point. A core object and its child nodes form an atomic cluster.
[0031] Furthermore, in step S1.3, the mean, covariance and number of samples of all Gaussian models are used to form a local model x represents the user's detection sample, μ i represents the mean of the ith atomic cluster, ∑ i represents the covariance of the ith atomic cluster.
[0032] Furthermore, in step S1.4, the specific implementation process of the aggregation center aggregating the local model into the global model is as follows:
[0033] ① The aggregation center calculates the model association value for each two Gaussian models i and j in the local model based on the KS statistic. The model association value of Gaussian models i and j is α i,j =Sup x |F i (x)-F j (x)|, where F i (x), F j (x) represents the distribution function of Gaussian models i and j respectively;
[0034] ② The aggregation center calculates the model association value by pairwise, and obtains a size of S 2 The correlation value matrix of the two models; if the correlation value of the two models satisfies Then the two Gaussian models belong to the same distribution. The two Gaussian models are merged, where α represents the significance level. The combined mean is μ ij =(ni μ i +n j μj ) / (n i +n j ), the combined covariance is n i and n j Respectively represent the number of samples of the i-th and j-th Gaussian models, μ i and μ j Represent the means of the i-th and j-th Gaussian models respectively, ∑ i and∑ j denote the covariance of the i-th and j-th Gaussian models respectively.
[0035] Furthermore, in step S1.7, the specific implementation process of the incremental clustering algorithm is as follows:
[0036] ① The drone is based on the source global model parameter I 0 Get the source global model represents the mean of the ith cluster, Represents the covariance of the i-th cluster, and uses this source global model as the new local model;
[0037] ②When a new sample x is collected q When, the UAV classifies the new data based on the source global model;
[0038] ③ The drone identifies outliers based on CB-MONNAD and records all outliers within the data collection time as O A ;
[0039] ④ The outlier O collected by the drone A As local data, the local clustering algorithm in step S1.2 is used to obtain Gaussian model of the new set of clusters;
[0040] ⑤ The drone updates and optimizes the parameters of the original cluster based on the non-outlier part of the new data to obtain an updated set of local model parameters;
[0041] ⑥ The aggregation center aggregates the local model to obtain the updated global model parameters. If the aggregation center is a drone, the updated local model parameter set is transmitted between adjacent drones. The drone performs local model aggregation to obtain updated global model parameters I update , and then transmit the global model to the satellite; if the aggregation center is a satellite, the drone will update the local model parameter set Sent to the satellite, the satellite performs local model aggregation to obtain the updated global model parameters I update .
[0042] Furthermore, in step ②, when a new sample x is collected q When the UAV classifies new data based on the source global model, the specific implementation process is as follows:
[0043] Calculate sample x q The posterior probability generated by each cluster set, sample x q The probability of being generated by the j-th cluster set is represents the mean of the j-th cluster set, represents the covariance of the j-th cluster set, λ q For sample x q The cluster number of the sample x q according to into the corresponding cluster, y qj Represents x q The probability of being generated by the j-th cluster set.
[0044] Furthermore, in step ③, the specific implementation process of the drone identifying outliers based on CB-MONNAD is as follows:
[0045] Assumptions is a cluster λ q The class-based K-distance is a dataset Sample x q and sample x p The distance between It satisfies the following two conditions: there are at least K samples So that dist(x q ,x' p )≤dist(x q ,x p )∧x' p ∈λ q , and there are at most K samples such that dist(x q ,x' p ) <dist(x q ,x p )∧x' p ∈λ q ,dist(x q ,x' p ) represents the sample x q and sample x' p The distance between q ,x p ) represents the sample x q and sample x p The distance between
[0046] Sample xq The class-based K-distance field contains samples x q The distance between A sample of is represented as:
[0047]
[0048] Sample x q The class-based local reachability density lrd(x q ) is expressed as:
[0049]
[0050] Sample x q The class-based local outlier factor LOF is expressed as:
[0051]
[0052] Drone calculates sample x based on LOF q The specific calculation formula of the CB-MONNAD score is as follows:
[0053]
[0054] If the CB-MONNAD score of the newly collected sample exceeds the specified threshold m , it is marked as an outlier, and all outliers within the data collection time are recorded as O A .
[0055] Furthermore, the specific implementation process of step S2.1 is as follows:
[0056] When the attack is a DDoS attack, if the number of samples of the received cluster is greater than the threshold θ, the cluster is a DDoS attack cluster, and the total number of DDoS attack clusters is regarded as the number of DDoS attackers, which is described as:
[0057] H0:n′ K ≤θ,
[0058] H1:n′ K >θ,
[0059] Among them, H0 represents the legitimate user, H1 represents the attacker, and the number of clusters that meet the attacker H1 condition is the number of attackers, n' K Indicates the number of samples of the received cluster;
[0060] When the attack is other attacks, the signal characteristics of the legitimate user are known, and the identity signature reference vector of the Kth legitimate user is A K , then the attack detection process is transformed into the clustering model mean and the reference vector A KFor comparison, it is expressed as:
[0061] H0:d(μ′ K ,A K )≤τ,
[0062] H1:d(μ ′ K,A K )>τ,
[0063] Where d(μ' K ,A K )=(μ' K ,A K )(∑' K ) -1 μ' K ,A K ) T, μ' K represents the mean of the received clusters, τ represents the threshold; the total number of deceptive clusters can be regarded as the number of deceptive attackers.
[0064] Furthermore, the threshold θ is related to the number of preambles sent by legitimate users and attackers during the data collection time, [T tw / T in ]<θ<[T tw / T ain ], T in and T ain Represents the time interval between two preamble transmissions of the legitimate user and the attacker, T tw Indicates the data collection time.
[0065] The beneficial effects of the present invention are:
[0066] The key point of the present invention is to introduce distributed clustering and multi-UAV collaboration to assist satellites in attack detection, and further design an incremental clustering method to achieve continuous detection under the condition of frequent satellite switching.
[0067] Compared with the prior art, the present invention has the following advantages:
[0068] (1) Compared with the current attack detection scheme based on upper-layer network features, the present invention uses the inherent channel feature received signal strength (RSS) in communication and the feature CFO based on equipment defects. It does not require a large amount of computing overhead and has low computing overhead. It can effectively detect attackers when the number of service terminals increases.
[0069] (2) Compared with the current attack detection scheme based on physical layer features, the present invention uses multi-node collaboration to collect data and enhances accuracy. At the same time, using distributed nodes to collaborate to complete training can effectively reduce computing overhead and solve the problem of limited satellite resources.
[0070] (3) Compared with the current solution of using ground control center to implement attack detection, the present invention implements attack detection on satellite, which reduces communication overhead and computational complexity. Considering the problem of frequent satellite switching, an incremental clustering algorithm is proposed. When the satellite switches, it can continue to train on the previously trained clustering model, which greatly simplifies the process of retraining the clustering model when the satellite switches, reduces computational overhead, realizes continuous detection, and increases the reliability of detection.
[0071] (4) The present invention uses multiple drones to perform local clustering based on multiple physical layer features. The drones or satellites aggregate all local models, and then use binary hypothesis testing based on the density characteristics of the attackers themselves to determine the legitimacy and illegality of the user. Physical layer features and multiple drones assist in data collection and feature estimation, which can accurately measure physical layer features and increase detection reliability.
[0072] (5) The present invention is suitable for attack detection of communication equipment in satellite direct communication scenarios. It has low cost, small computational overhead and delay, and can effectively detect attackers and achieve continuous detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0073] Figure 1 A distributed collaborative wireless access security solution for satellite direct communication.
[0074] Figure 2 The distributed collaborative wireless access security solution process for satellite direct communication.
[0075] Figure 3 This is the incremental clustering algorithm process. DETAILED DESCRIPTION
[0076] The present invention is further described in detail below in conjunction with the accompanying drawings.
[0077] like Figure 1As shown, in a distributed collaborative wireless access security method for satellite direct communication provided by the present invention, ground users are divided into attackers and legitimate users, and legitimate users communicate with satellite base stations through wireless channels (i.e., communication links in the figure). At the same time, there are attackers who attack satellites through attack links. Attackers may send deceptive signals to satellites as legitimate users (i.e., legitimate users hijacked in the figure) in an attempt to access the wireless network. They may also interfere with satellites by sending large amounts of signaling or user data, and even cause satellite resources to be exhausted, causing satellite base stations to be attacked by denial of service, resulting in wireless network congestion or even collapse. Multiple drones are responsible for continuous monitoring in a certain area and collecting signals sent by ground users through detection links, and assisting satellites in attack detection. Satellites communicate with ground users (hereinafter referred to as users) as base stations, detect attackers, and deny attackers access to the wireless network.
[0078] The distributed cooperative wireless access security method for satellite direct communication of the present invention is mainly divided into two stages, namely, a model training and updating stage, and an attack detection stage.
[0079] like Figure 2 As shown, a distributed cooperative wireless access security method for satellite direct communication of the present invention has the following specific implementation process:
[0080] 1. Model training and updating stage;
[0081] (1) When the user communicates normally with the satellite base station, N u Each drone moves at a constant speed along a pre-set trajectory to assist in monitoring the access status of users within its cell coverage and collect data at the data collection time T. tw The user's signal is collected to calculate the detection sample S(t) composed of the received signal strength (RSS) and carrier frequency offset (CFO) of the channel characteristics inherent in the communication.
[0082] (2) The drone uses the calculated detection sample S(t) as local data and generates k using the local clustering algorithm l The clustering process automatically divides the detection samples S(t) into different clusters. The detection samples in the same cluster can be regarded as samples from the same user. The local clustering algorithm combines the principles of K-nearest neighbor kernel density and high-density nearest neighbor for local clustering. The specific implementation process is as follows:
[0083] ① All sample points in the drone data set use K-nearest neighbor kernel density to represent the local density of each sample point, find high-density neighbor points based on the local density, and determine the core object. Among them, the core object refers to the sample point that has no high-density neighbors in the K-nearest neighborhood or the sample point with the maximum density in the K-nearest neighborhood.
[0084] ② All sample points in the drone data set construct a graph g = (V, A) based on high-density neighbor points. Vertex V represents the sample point. Each directed edge in A points from a non-core object to its high-density neighbor point. A core object and its child nodes form an atomic cluster.
[0085] (3) Based on the clustered atomic clusters, the drone uses Gaussian model parameter estimation to generate the Gaussian model corresponding to each atomic cluster, and the mean, covariance and number of samples of all Gaussian models constitute the local model x represents the user's detection sample, μ i represents the mean of the ith atomic cluster, ∑ i represents the covariance of the ith atomic cluster; and sends the local model to the aggregation center, where the aggregation center can be a drone or a satellite.
[0086] (4) The aggregation center aggregates the local models into a global model and obtains K cluster sets. The global model parameter set is I 0 ={μ 0 ,∑w,...,n 0},in, I 0 represents the global model parameter set of K cluster sets, μ 0 represents the mean set of K cluster sets, Represents the mean of each cluster set, ∑ 0 represents the covariance set of K cluster sets, Respectively represents the covariance of each cluster set, n 0 represents the sample number set of K cluster sets, Respectively represent the number of samples in each cluster set.
[0087] The specific implementation process of the aggregation center aggregating local models into a global model is as follows:
[0088] ① The aggregation center calculates the model association value for each two Gaussian models i and j in the local model based on the KS statistic. The model association value of Gaussian models i and j is α i,j =Sup x |F i (x)-F j (x)|, where F i (x), Fj (x) represent the distribution functions of Gaussian models i and j respectively.
[0089] ② The aggregation center calculates the model association value by pairwise, and obtains a size of S 2 The correlation value matrix of two models. If the correlation value of two models satisfies Then the two Gaussian models belong to the same distribution. The two Gaussian models are merged, where α represents the significance level. The combined mean is μ ij =(n i μ i +n j μ j ) / (n i +n j ), the combined covariance is Among them, n i and n j Respectively represent the number of samples of the i-th and j-th Gaussian models, μ i and μ j Represent the means of the i-th and j-th Gaussian models respectively, ∑ i and∑ j denote the covariance of the i-th and j-th Gaussian models respectively.
[0090] (5) If the aggregation center is a drone, the global model needs to be sent to the satellite. If the aggregation center is a satellite, the global model does not need to be sent to the satellite.
[0091] (6) The satellite obtains the final K cluster sets C'={C'1,C'2,...,C' K}, where C' K ={μ' K ,∑' K ,n' K}, where μ' K ,∑' K 、n' K They represent the mean, covariance and number of samples of the Kth cluster respectively.
[0092] (7) When the satellite switches, the source satellite will detect the attacker’s global model parameter I 0 (i.e., source global model parameters) are sent to the target satellite and the UAV, and the target satellite uses the incremental clustering algorithm to update the global model to obtain the updated global model parameters I update .
[0093] Among them, Figure 3 As shown in the figure, the specific implementation process of the incremental clustering algorithm is as follows:
[0094] ① The drone is based on the source global model parameter I 0 Get the source global model represents the mean of the ith cluster, Denote the covariance of the ith cluster and use this source global model as the new local model.
[0095] ②When a new sample x is collected q When , the drone classifies the new data based on the source global model. The specific implementation steps are: calculate the sample x q The posterior probability generated by each cluster set, sample x q The probability of being generated by the j-th cluster set is represents the mean of the j-th cluster set, represents the covariance of the j-th cluster set, λ q For sample x q The cluster number of the sample x q according to into the corresponding cluster, y qj Represents sample x q The probability of being generated by the j-th cluster set.
[0096] ③ The drone identifies outliers based on CB-MONNAD. The specific implementation process is as follows:
[0097] Assumptions is a cluster λ q The class-based K-distance is a dataset Sample x q and sample x p The distance between It satisfies the following two conditions: there are at least K samples So that dist(x q ,x' p )≤dist(x q ,x p )∧x' p ∈λ q , and there are at most K samples such that dist(x q ,x' p ) <dist(x q ,x p )∧x' p ∈λ q . Among them, dist(x q ,x' p ) represents the sample x q and sample x' p The distance between q ,x p ) represents the sample xq and sample x p The distance between.
[0098] Sample x q The class-based K-distance field contains samples x q The distance between A sample of is represented as:
[0099]
[0100] Sample x q The class-based local reachability density lrd(x q ) can be expressed as:
[0101]
[0102] Sample x q The class-based local outlier factor LOF is given by:
[0103]
[0104] Drone calculates sample x based on LOF q The specific calculation formula of the CB-MONNAD score is as follows:
[0105]
[0106] If the CB-MONNAD score of the newly collected sample exceeds the specified threshold m , it is marked as an outlier, and all outliers within the data collection time are recorded as O A .
[0107] ④ The outlier O collected by the drone A As local data, the local clustering algorithm in step (2) is used to obtain Gaussian model for the new set of clusters.
[0108] ⑤ The drone updates and optimizes the parameters of the original cluster based on the non-outlier part of the new data to obtain an updated set of local model parameters. It can be expressed as in, μ update represents the updated local model mean set, Respectively represent the updated The mean of the clusters, ∑ update represents the updated local model covariance set, Respectively represent the updated The covariance of the clusters, n update Represents the updated local model sample number set, Respectively represent the updated The number of samples in a cluster.
[0109] ⑥ The aggregation center aggregates the local model to obtain the updated global model parameters. If the aggregation center is a drone, the updated local model parameter set is transmitted between adjacent drones. The drone uses step (5) to aggregate the local model to obtain the updated global model parameters I update , and then transmit the global model to the satellite. If the aggregation center is a satellite, the drone will update the local model parameter set The satellite performs local model aggregation through step (5) to obtain the updated global model parameters I update , assuming that k1 clusters are obtained after aggregation of the aggregation center, I update ={μ 1 ,∑ 1 ,n 1},in, μ 1 represents the updated global model mean set, Respectively represent the updated means of k1 clusters, ∑ 1 represents the updated global model covariance set, represents the updated covariance of k1 clusters, n 1 represents the new set of global model samples, Represents the number of samples in the updated k1 clusters.
[0110] An incremental clustering algorithm adopted in the present invention can continue training on a previously trained clustering model when the satellite is switched, which greatly simplifies the process of retraining the clustering model when the satellite is switched, reduces the computational overhead, realizes continuous detection, and increases network reliability.
[0111] At the same time, the present invention adopts a distributed clustering algorithm for multi-UAV and satellite collaboration. Multiple UAVs perform local clustering, and UAVs or satellites aggregate all local models to form a global model, which significantly reduces the communication overhead and computational complexity associated with transmitting large amounts of raw data and solves the problem of limited satellite resources.
[0112] 2. Attack detection phase;
[0113] (1) The satellite detects the attack and estimates the number of attackers through binary hypothesis testing;
[0114] If it is a DDoS attack, the attack detection method is specifically described as follows: If the number of samples of the received cluster is greater than the threshold θ, then the cluster is a DDoS attack cluster, and the total number of DDoS attack clusters can be regarded as the number of DDoS attackers. The process can be described as:
[0115] H0:n′ K ≤θ,
[0116] H1:n′ K >θ,
[0117] Among them, H0 represents the legitimate user, H1 represents the attacker, and the number of clusters that meet the attacker H1 condition is the number of attackers, n' K represents the number of samples of the received cluster. The threshold θ is related to the number of preambles sent by legitimate users and attackers during the data collection time. [T tw / T in ]<θ<[T tw / T ain ], where T in and T ain Represents the time interval between two preamble transmissions of the legitimate user and the attacker, T tw Indicates the data collection time.
[0118] If it is another attack (such as a spoofing attack), the signal characteristics of the legitimate user need to be known. The attack detection method is described as follows: The identity signature reference vector of the Kth legitimate user is A K , the clustering model mean reflects the statistical characteristics of the user detection sample and is a stable observation value. Then the attack detection process is transformed into the clustering model mean and the reference vector A K For comparison, it is expressed as:
[0119] H0:d(μ′ K ,A K )≤τ,
[0120] H1:d(μ′ K ,A K )>v,
[0121] Where d(u' K ,A K )=(μ' K ,A K )(∑' K ) -1 (μ' K ,A K ) T , μ' K represents the mean of the received clusters, and τ represents the threshold. The total number of deceptive clusters can be regarded as the number of deceptive attackers.
[0122] (2) When the satellite switches, the source satellite will detect the attacker’s global model parameter I 0 The target satellite uses the incremental clustering algorithm in step (7) of the model training and updating phase to update the global model and obtain the updated global model parameters I update ,Then perform attack detection and estimate the number of attackers ,according to step (1) of the attack detection phase.
[0123] (3) When the number of drones N u When it is greater than or equal to 3, the attacker can be located.
[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein, but these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A distributed cooperative wireless access security method for satellite direct communication, characterized in that: The following steps are involved: S1: Model training and updating stage; S1.1: When the user communicates normally with the satellite base station, N u The drones move at a constant speed along a pre-set trajectory to monitor user access and collect data at the time T. tw Collect user signals internally and calculate the detection sample S(t) composed of RSS and CFO; S1.2: The drone uses the detection sample S(t) as local data and uses the local clustering algorithm to combine the K nearest neighbor kernel density and high-density nearest neighbor to generate local clustering k l Atom clusters; S1.3: Based on the clustered atomic clusters, the drone uses Gaussian model parameter estimation to generate a Gaussian model corresponding to each atomic cluster, and constructs a local model with the mean, covariance and number of samples of the Gaussian model, and sends the local model to the aggregation center; S1.4: The aggregation center aggregates the local models into a global model and obtains K cluster sets; S1.5: The aggregation center is a drone or a satellite; if the aggregation center is a drone, the global model needs to be sent to the satellite; if the aggregation center is a satellite, the global model does not need to be sent to the satellite; S1.6: The satellite obtains the final K cluster sets C'={C'1,C'2,...,C' K }, C' K ={μ' K ,∑' K ,n' K },μ' K ,∑' K 、n' K Respectively represent the mean, covariance and number of samples of the Kth cluster; S1.7: When the satellite switches, the source satellite will detect the attacker's global model parameter I 0 The target satellite uses the incremental clustering algorithm to update the global model and obtain the updated global model parameters I update ; S2: attack detection phase; S2.1: The satellite detects the attack and estimates the number of attackers through binary hypothesis testing; S2.2: When the satellite switches, the source satellite will detect the attacker’s global model parameter I 0 The target satellite uses the incremental clustering algorithm in step S1.7 to update the global model and obtain the updated global model parameters I update , then perform attack detection and attacker number estimation according to step S2.1; S2.3: When the number of drones N u When it is greater than or equal to 3, the attacker can be located.
2. A distributed cooperative wireless access security method for satellite direct communication according to claim 1, characterized in that: In step S1.2, in the local clustering process, the detection samples S(t) are automatically divided into different clusters, and the detection samples in the same cluster are regarded as samples from the same user.
3. The distributed cooperative wireless access security method for satellite direct communication according to claim 1, characterized in that: The specific implementation process of the local clustering algorithm is as follows: ① All sample points in the drone data set use K nearest neighbor kernel density to represent the local density of each sample point, find high-density neighboring points based on the local density, and determine the core objects; ② All sample points in the drone data set construct a graph g = (V, A) based on high-density neighbor points. Vertex V represents the sample point. Each directed edge in A points from a non-core object to its high-density neighbor point. A core object and its child nodes form an atomic cluster.
4. The distributed cooperative wireless access security method for satellite direct communication according to claim 1, characterized in that: In step S1.3, the mean, covariance and number of samples of all Gaussian models are used to form a local model x represents the user's detection sample, μ i represents the mean of the ith atomic cluster, Σ i represents the covariance of the ith atomic cluster.
5. The distributed cooperative wireless access security method for satellite direct communication according to claim 1, characterized in that: In step S1.4, the specific implementation process of the aggregation center aggregating the local model into a global model is as follows: ① The aggregation center calculates the model association value for each two Gaussian models i and j in the local model based on the KS statistic. The model association value of Gaussian models i and j is α i,j =Sup x |F i (x)-F j (x)|, where F i (x), F j (x) represents the distribution function of Gaussian models i and j respectively; ②) The aggregation center calculates the model association value by pairwise, and obtains a size of S 2 The correlation value matrix of the two models; if the correlation value of the two models satisfies Then the two Gaussian models belong to the same distribution. The two Gaussian models are merged, where α represents the significance level. The combined mean is μ ij =(n i μ i +n j μ j ) / (n i +n j ), the combined covariance is n i and n j Respectively represent the number of samples of the i-th and j-th Gaussian models, μ i and μ j Represent the means of the i-th and j-th Gaussian models respectively, ∑ i and∑ j denote the covariance of the i-th and j-th Gaussian models respectively.
6. A distributed cooperative wireless access security method for satellite direct communication according to claim 1, characterized in that: In step S1.7, the specific implementation process of the incremental clustering algorithm is as follows: ① The drone is based on the source global model parameter I 0 Get the source global model represents the mean of the ith cluster, Represents the covariance of the i-th cluster, and uses this source global model as the new local model; ②When a new sample x is collected q When, the UAV classifies the new data based on the source global model; ③ The drone identifies outliers based on CB-MONNAD and records all outliers within the data collection time as O A ; ④ The outlier O collected by the drone A As local data, the local clustering algorithm in step S1.2 is used to obtain Gaussian model of the new set of clusters; ⑤ The drone updates and optimizes the parameters of the original cluster based on the non-outlier part of the new data to obtain an updated set of local model parameters; ⑥ The aggregation center aggregates the local model to obtain the updated global model parameters. If the aggregation center is a drone, the updated local model parameter set is transmitted between adjacent drones. The drone performs local model aggregation to obtain updated global model parameters I update , and then transmit the global model to the satellite; if the aggregation center is a satellite, the drone will update the local model parameter set Sent to the satellite, the satellite performs local model aggregation to obtain the updated global model parameters I update .
7. A distributed cooperative wireless access security method for satellite direct communication according to claim 6, characterized in that: In step ②, when a new sample x is collected q When the UAV classifies new data based on the source global model, the specific implementation process is as follows: Calculate sample x q The posterior probability generated by each cluster set, sample x q The probability of being generated by the j-th cluster set is represents the mean of the j-th cluster set, represents the covariance of the j-th cluster set, λ q For sample x q The cluster number of the sample x q according to into the corresponding cluster, y qj Represents sample x q The probability of being generated by the j-th cluster set.
8. The distributed cooperative wireless access security method for satellite direct communication according to claim 6, characterized in that: In step ③, the specific implementation process of the drone identifying outliers based on CB-MONNAD is as follows: Assumptions is a cluster λ q The class-based K-distance is a dataset Sample x q and sample x p The distance between It satisfies the following two conditions: there are at least K samples So that dist(x q ,x' p )≤dist(x q ,x p )∧x' p ∈λ q , and there are at most K samples such that dist(x q ,x' p ) <dist(x q ,x p )∧x' p ∈λ q ,dist(x q ,x' p ) represents the sample x q and sample x' p The distance between q ,x p ) represents the sample x q and sample x p The distance between Sample x q The class-based K-distance field contains samples x q The distance between A sample of is represented as: Sample x q The class-based local reachability density lrd(x q ) is expressed as: Sample x q The class-based local outlier factor LOF is expressed as: Drone calculates sample x based on LOF q The specific calculation formula of the CB-MONNAD score is as follows: If the CB-MONNAD score of the newly collected sample exceeds the specified threshold m , it is marked as an outlier, and all outliers within the data collection time are recorded as O A .
9. The distributed cooperative wireless access security method for satellite direct communication according to claim 1, characterized in that: The specific implementation process of step S2.1 is as follows: When the attack is a DDoS attack, if the number of samples of the received cluster is greater than the threshold θ, the cluster is a DDoS attack cluster, and the total number of DDoS attack clusters is regarded as the number of DDoS attackers, which is described as: <h2 style=";text-align:left;direction:ltr">H0:n′<h2 style=";text-align:left;direction:ltr"> K <h2 style=";text-align:left;direction:ltr"> ≤θ, H1:n′ K >i, Among them, H0 represents the legitimate user, H1 represents the attacker, and the number of clusters that meet the attacker H1 condition is the number of attackers, n' K Indicates the number of samples of the received cluster; When the attack is other attacks, the signal characteristics of the legitimate user are known, and the identity signature reference vector of the Kth legitimate user is A K , then the attack detection process is transformed into the clustering model mean and the reference vector A K For comparison, it is expressed as: H0:d(μ′ K ,A K )≤τ, H1:d(μ′ K ,A K )>t, Where d(μ' K ,A K )=(μ' K ,A K )(∑' K ) -1 (μ' K ,A K ) T , μ' K represents the mean of the received clusters, τ represents the threshold; the total number of deceptive clusters can be regarded as the number of deceptive attackers.
10. A distributed cooperative wireless access security method for satellite direct communication according to claim 9, characterized in that: The threshold θ is related to the number of preambles sent by the legitimate user and the attacker during the data collection time, [Ttw / Tin]<θ<[Ttw / Tain], Tin and Tain represent the time interval between two preamble transmissions by the legitimate user and the attacker respectively, and Ttw represents the data collection time.
Citation Information
Patent Citations
Unmanned aerial vehicle access control method based on attribute authentication
CN105491025A
Method for resisting DDoS attack based on physical layer attributes
CN114567884A
Method and device for identifying low earth orbit satellite network attack based on distributed federated learning
CN117411683A
Federated learning method and system for decentralized local aggregation of low earth orbit satellite network
CN117709485A
