Smart community-oriented collaborative cognitive radio network security optimization method

By using a key verification method combined with blockchain and AlexNet convolutional neural network in the smart community, we detect and distinguish malicious users, and solve the problem of spectrum perception security in cognitive radio networks, improving the stability and security of the network , realizes efficient communication and device connection.

CN119031375APending Publication Date: 2024-11-26HANGZHOU GUANGMAI TECH +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411195002.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

In smart communities, cognitive radio networks face spectrum perception security risks, and malicious users may affect the accuracy of spectrum perception, resulting in a degradation of network performance.

Method used

Using a blockchain-based key verification method, device features are extracted through AlexNet convolutional neural network, and digital signature technology is used to distinguish trusted users from malicious users to ensure the security of spectrum perception.

Benefits of technology

It improves the stability and security of the entire community network, achieves more reliable and efficient communication, and ensures seamless connection and stable operation between devices.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119031375A_ABST
    Figure CN119031375A_ABST
Patent Text Reader

Abstract

The invention discloses a cooperative cognitive radio network security optimization method for a smart community. The method comprises the following steps: submitting detection data to a fusion center by all intelligent devices SU; creating blocks of all nodes in the smart community network by using a block chain technology; features of a key device PU are extracted through an AlexNet convolutional neural network, local data sensing is performed on an intelligent device SU node, and then a block chain verification device is utilized and a result is sent to a fusion center; according to the method, the MU is detected by using the digital signature technology, the trusted user and the malicious user are distinguished by using the secret key, and under the background of the smart community, the MU detection method based on the block chain can ensure the security of spectrum sensing and prevent the malicious user from interfering community equipment, so that the stability and security of the whole community network are improved. Through an efficient malicious user detection mechanism, the smart community can realize more reliable and efficient communication, and seamless connection and stable operation between devices are ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of wireless network, and in particular relates to a collaborative cognitive wireless network security optimization method for a smart community. Background Art

[0002] As the number of devices in smart communities increases, how to effectively utilize spectrum resources has become a pressing issue. Cognitive radio (CR) technology provides an effective solution, which can locate idle frequency bands of primary users (PUs) by sensing the environment, thereby enabling secondary users (SUs) to access these unused spectrum. The premise of this spectrum access is that the active SUs in the collaborative network will not interfere with the transmission of the PUs. One of the main functions of cognitive radio is spectrum sensing, and other functions include spectrum sharing, spectrum access, and spectrum mobility and control.

[0003] In smart communities, the implementation of CRN faces great challenges because it must cope with the ever-changing radio environment. The MAC layer of these users must be able to handle these tasks correctly, which increases the complexity of implementation compared to the current static spectrum allocation rules. Opportunistic spectrum access (OSA) is a concept that has emerged in recent years and aims to significantly improve spectrum utilization. SU must be able to dynamically find and seize opportunities within the available spectrum in multiple dimensions including time, frequency, code, etc. Therefore, the OSA protocol must have spectrum access and listening capabilities.

[0004] The Internet of Things has revolutionized the smart community, with a massive growth in the number of connected devices across the globe. This has led to huge challenges in meeting the spectrum requirements of these devices, such as seamless connectivity, scalability, and accessibility. Cognitive Radio (CR) technology is designed to meet this need as it exploits spectrum white spaces in licensed bands. Spectrum sensing is a key component of cognitive radio networks (CRNs), and security issues pose a risk to spectrum sensing. Malicious users (MUs) can affect the accuracy of spectrum sensing, especially in the case of collaborative spectrum sensing, where they send forged data to the fusion center. The presence of such malicious users can affect the performance of cognitive radios in systems that produce erroneous sensed data. Summary of the invention

[0005] The purpose of the present invention is to provide a collaborative cognitive wireless network security optimization method for smart communities, which uses keys to distinguish between trusted users and malicious users. In the context of smart communities, this blockchain-based MU detection method can ensure the security of spectrum sensing and prevent malicious users from interfering with community devices, thereby improving the stability and security of the entire community network to solve the problems raised in the above background technology.

[0006] To achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a collaborative cognitive wireless network security optimization method for smart communities, comprising the following steps: S1: submitting detection data of all smart devices SU to the fusion center to determine the activity status of key devices PU; S2: using blockchain technology to create blocks of all nodes in the smart community network, distinguishing between primary device nodes and secondary device nodes, and ensuring network decentralization; S3: extracting the features of key devices PU through the AlexNet convolutional neural network, performing local data perception on the smart device SU node, and then using blockchain to verify the device and send the result to the fusion center; S4: using digital signature technology to detect malicious users MU, verifying device identity based on private keys and public keys, and judging trusted devices TU and malicious devices.

[0007] Preferably, when creating blocks of all nodes in the smart community network, the private key of each device node stores authentication code information, and the public key contains device status information, ensuring device identity uniqueness and network management monitoring.

[0008] Preferably, the performing local data sensing on the smart device SU node includes: using a deep learning model based on LSTM integrated with AlexNet to perform spectrum sensing, and performing local data sensing on each smart device SU node.

[0009] Preferably, the device identity verification based on the private key and the public key includes: verifying the identity of each node through a digital signature, and verifying that the device is one of the key device PU or the smart device SU.

[0010] Preferably, the verifying the identity of each node by digital signature includes: when the digital signature verification fails, the device is marked as a malicious device, and the model is evaluated according to the parameters.

[0011] Preferably, evaluating the model according to parameters comprises evaluating the following parameters:

[0012] False alarm probability: the ratio of the number of detections that fail to identify malicious users and trusted users;

[0013] Missed detection probability: the number of times a trusted user's identity authentication fails;

[0014] Malicious user MU detection probability: the number of malicious user MUs identified in valid iterations divided by the total number of iterations;

[0015] Trusted device TU detection probability: the ratio of the number of times the trusted user is accurately predicted to the total number of valid iterations.

[0016] Preferably, the expression of false alarm probability is:

[0017]

[0018] in, is the probability of false alarm based on blockchain, is the probability of malicious user detection based on blockchain, φ' MU is the number of times a malicious user fails to be detected and n is the number of iterations that can be called.

[0019] Preferably, the expression of missed detection probability is:

[0020]

[0021] φ' TU is the number of times a trusted user was not predicted.

[0022] Preferably, the expression of the detection probability of malicious user MU is:

[0023]

[0024] φ MU The number of times MU is predicted.

[0025] Preferably, the expression of the TU detection probability of a trusted device is:

[0026]

[0027] φ TU is the number of predicted TUs.

[0028] Technical effects and advantages of the present invention: Compared with the prior art, the collaborative cognitive wireless network security optimization method for smart communities proposed in the present invention has the following advantages:

[0029] The present invention uses a key to distinguish between trusted users and malicious users. In the context of smart communities, this blockchain-based MU detection method can ensure the security of spectrum sensing and prevent malicious users from interfering with community devices, thereby improving the stability and security of the entire community network. Through an efficient malicious user detection mechanism, smart communities can achieve more reliable and efficient communications, ensuring seamless connection and stable operation between devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a schematic diagram of LSTM spectrum sensing integrated with AlexNet of the present invention;

[0031] Figure 2 A schematic diagram of a cognitive radio network based on block chain according to the present invention;

[0032] Figure 3 The present invention is a flowchart of a collaborative cognitive wireless network security optimization method for smart communities. DETAILED DESCRIPTION

[0033] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0034] The present invention provides a collaborative cognitive wireless network security optimization method for smart communities, such as Figure 1 As shown, the following steps are included:

[0035] S1: Submit detection data of all intelligent devices SU to the fusion center to determine the activity status of key devices PU;

[0036] In a distributed smart community scenario, all smart devices SU submit their detection data to the fusion center, which then determines whether the key device PU is active based on certain rules. There are a large number of key devices PU and smart devices SU in a smart community network. Figure 2 As shown, even if the key device is dispersed with the smart device, the key device is still within its effective transmission range. In this collaborative sensing approach, all nodes work together to achieve the desired results. The listening phase starts with data listening and continues until a consensus decision is made as to whether the device is authentic or malicious.

[0037] S2: Use blockchain technology to create blocks of all nodes in the smart community network, distinguish between primary device nodes and secondary device nodes, and ensure network decentralization; when creating blocks of all nodes in the smart community network, the private key of each device node stores authentication code information, and the public key contains device status information to ensure device identity uniqueness and network management monitoring. Blockchain technology has been implemented in the smart community network, connecting key devices PU and smart devices SU in a peer-to-peer topology, making our network completely decentralized. For convenience, only one key device and N smart devices are employed, and each device is decentralized and connected to other devices.

[0038] Through this distributed architecture, the smart community can ensure the efficiency and security of the network. All devices work together to monitor and make decisions, and use blockchain technology to achieve decentralized management to ensure the authenticity and security of data.

[0039] Blockchain creation is the creation of blocks for all nodes present in the smart community network. In a smart community, key devices are called master device nodes, while other smart devices are called secondary device nodes or smart device nodes. Algorithm 1 describes the pseudocode for the creation of PU and SU node blocks. These blocks will contain private keys with information about the authentication code, while the public key will contain information such as node status, general information, etc.

[0040] Algorithm 1: Create a block

[0041]

[0042] In this way, smart communities can use blockchain technology to ensure the security and authenticity of all devices. The private key of each device node stores the authentication code information to ensure the uniqueness and security of the device identity. The public key contains the status of the device and other general information, which facilitates the management and monitoring of the community network.

[0043] This block creation process provides a secure and reliable foundation for the smart community, enabling all devices to collaborate effectively in a decentralized network, share data, and jointly improve the community's intelligence level and user experience.

[0044] S3: Extract the features of key equipment PU through AlexNet convolutional neural network, perform local data perception on smart device SU node, and then use blockchain to verify the equipment and send the results to the fusion center;

[0045] Furthermore, a deep learning model based on LSTM integrated with AlexNet is used for spectrum sensing, and local data perception is performed in each smart device SU node.

[0046] Each primary user and secondary user will create a block and enter the blockchain system. Spectrum sensing will be completed through a deep learning model based on LSTM integrated with AlexNet, as shown below: Figure 1 , which is also a schematic diagram of a blockchain-based cognitive radio network.

[0047] The energy and feature statistics of key devices are extracted through the convolutional layer of the AlexNet structure of the convolutional neural network (CNN) model, and then local data perception is performed at each smart device node. After local data perception is performed at each SU node, the device is verified using blockchain technology, and then the results are sent to the fusion center. The fusion center applies the K-OUT-N rule to determine whether the data is valid. Algorithm 2 gives the pseudo code of LSTM integrated AlexNet.

[0048] Algorithm 2: LSTM with AlexNet

[0049]

[0050]

[0051] In this way, the smart community can use advanced machine learning and blockchain technology to ensure the accuracy and security of data. First, the convolutional layer of AlexNet is used to extract data features of key devices, and then local data perception is performed at each smart device node. Next, the authenticity of the device is verified through blockchain technology to ensure the credibility of the data. Finally, the fusion center applies the K-OUT-N rule to synthesize the perception results of each node and judge the validity of the data.

[0052] This integrated approach provides a reliable and secure data perception process for smart communities, combining the powerful capabilities of CNN and LSTM to ensure that various smart devices in the community can work together efficiently and securely, improving the intelligence level and user experience of the entire smart community.

[0053] S4: Use digital signature technology to detect malicious users MU, verify device identity based on private keys and public keys, and determine trusted devices TU and malicious devices.

[0054] After CNN-based block creation and local data sensing, the next step is to detect malicious users (MUs). Detection is done through digital signatures. The device is verified to be a key device PU or a smart device SU based on the private and public keys associated with each node. It should be noted that whenever the digital signature is verified, the device will be verified and referred to as a trusted device TU, while if the signature is not verified, the verification fails and such a malicious device or user will be referred to as a MU. Whenever a node is identified as a MU, the model is evaluated based on the following parameters.

[0055] In this way, the smart community can effectively detect and isolate malicious devices to ensure the security and reliability of the network. In the local data perception stage, CNN is used to extract device features, and then the device identity is verified through blockchain technology. If the digital signature is verified, the device is considered a trusted device, otherwise it is marked as a malicious device.

[0056] This digital signature-based verification method provides a powerful security mechanism for smart communities, which can detect and handle potential security threats in a timely manner and ensure the safe operation of various smart devices in the community. As long as the node is identified as MU, the model will be evaluated based on the following parameters.

[0057] Further, the identity of each node is verified by a digital signature, and the device is verified to be one of the key device PU or the smart device SU. The identity of each node is verified by a digital signature, including: when the digital signature verification fails, the device is marked as a malicious device, and according to the parameter evaluation model, the parameter evaluation model includes evaluating the following parameters:

[0058] False alarm probability: the ratio of the number of detections that fail to identify malicious users and trusted users; the expression of false alarm probability is:

[0059]

[0060] in, is the probability of false alarm based on blockchain, is the probability of malicious user detection based on blockchain, φ' MU is the number of times a malicious user fails to be detected and n is the number of iterations that can be called.

[0061] Missed detection probability: The number of times a trusted user's identity authentication fails. The expression for missed detection probability is:

[0062]

[0063] φ' TU is the number of times a trusted user was not predicted.

[0064] Malicious user MU detection probability: the number of malicious user MUs identified in valid iterations divided by the total number of iterations; the expression for malicious user MU detection probability is:

[0065]

[0066] φ MU The number of times MU is predicted.

[0067] Trusted device TU detection probability: the ratio of the number of times the trusted user is accurately predicted to the total number of valid iterations. The expression of the trusted device TU detection probability is:

[0068]

[0069] φ TU is the number of predicted TUs.

[0070] In summary, the present invention uses keys to distinguish between trusted users and malicious users. In the context of smart communities, this blockchain-based MU detection method can ensure the security of spectrum sensing and prevent malicious users from interfering with community devices, thereby improving the stability and security of the entire community network. Through an efficient malicious user detection mechanism, smart communities can achieve more reliable and efficient communications, ensuring seamless connection and stable operation between devices.

[0071] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A collaborative cognitive wireless network security optimization method for smart communities. It is characterized in that The following steps are involved: S1: Submit detection data of all intelligent devices SU to the fusion center to determine the activity status of key devices PU; S2: Use blockchain technology to create blocks of all nodes in the smart community network, distinguish between primary device nodes and secondary device nodes, and ensure network decentralization; S3: Extract the features of key equipment PU through AlexNet convolutional neural network, perform local data perception on smart device SU node, and then use blockchain to verify the equipment and send the results to the fusion center; S4: Use digital signature technology to detect malicious users MU, verify device identity based on private keys and public keys, and determine trusted devices TU and malicious devices.

2. According to claim 1, a collaborative cognitive wireless network security optimization method for smart communities, Features: When creating blocks of all nodes in the smart community network, the private key of each device node stores authentication code information, and the public key contains device status information to ensure the uniqueness of device identity and network management monitoring.

3. According to the method for optimizing the security of a collaborative cognitive wireless network for a smart community according to claim 1, Features: The local data perception on the smart device SU node includes: using a deep learning model based on LSTM integrated with AlexNet to perform spectrum perception, and performing local data perception on each smart device SU node.

4. According to claim 1, a collaborative cognitive wireless network security optimization method for smart communities, Features: The device identity verification based on the private key and the public key includes: verifying the identity of each node through a digital signature, and verifying that the device is one of the key device PU or the smart device SU.

5. According to claim 4, a collaborative cognitive wireless network security optimization method for smart communities, Features: The identity of each node is verified by digital signature, including: when the digital signature verification fails, the device is marked as a malicious device, and the model is evaluated according to the parameters.

6. According to claim 5, a collaborative cognitive wireless network security optimization method for smart communities, Features: The parameter-based model evaluation includes evaluating the following parameters: False alarm probability: the ratio of the number of detections that fail to identify malicious users and trusted users; Missed detection probability: the number of times a trusted user's identity authentication fails; Malicious user MU detection probability: the number of malicious user MUs identified in valid iterations divided by the total number of iterations; Trusted device TU detection probability: the ratio of the number of times the trusted user is accurately predicted to the total number of valid iterations.

7. A collaborative cognitive wireless network security optimization method for smart communities according to claim 6, Features: The expression of false alarm probability is: in, is the probability of false alarm based on blockchain, is the probability of malicious user detection based on blockchain, φ' MU is the number of times a malicious user fails to be detected and n is the number of iterations that can be called.

8. According to claim 7, a collaborative cognitive wireless network security optimization method for smart communities, Features: The expression of missed detection probability is: φ' TU is the number of times a trusted user was not predicted.

9. A collaborative cognitive wireless network security optimization method for smart communities according to claim 8, Features: The expression of malicious user MU detection probability is: φ MU The number of times MU is predicted.

10. A collaborative cognitive wireless network security optimization method for smart communities according to claim 9, Features: The expression of the TU detection probability of a trusted device is: φ TU is the number of predicted TUs.