Quantum key cloud security situation awareness prediction system and method

Abstract

The invention discloses a quantum key cloud security situation awareness prediction system, which comprises a data acquisition layer, a security situation evaluation layer, a security situation prediction layer and a security situation early warning layer, the invention also discloses a quantum key cloud security situation awareness prediction method which is realized based on the quantum key cloud security situation awareness prediction system. The invention discloses a quantum key cloud security situation awareness prediction system and a quantum key cloud security situation awareness prediction method, which are used for effectively evaluating and accurately predicting a quantum key cloud security situation by combining a quantum computer, a genetic algorithm and a simulated annealing algorithm, and greatly improving the security stability of a quantum key cloud platform. And a powerful guarantee is provided for protecting increasingly huge and complicated network space.

Description

Technical Field

[0001] The present invention relates to the technical field of quantum secure communication, and in particular to a quantum key cloud security situation awareness prediction system and method. Background Art

[0002] The basic principle of Quantum Key Distribution (QKD) is based on the interdisciplinary characteristics of cryptography, information theory, and quantum mechanics, and is currently a hot topic in the field of quantum cryptography research.

[0003] The development of quantum cryptography systems and the construction of quantum networks are becoming more and more perfect. Quantum cryptography technology is playing an increasingly important role in the field of commercial cryptography systems and information security. At present, the construction of key infrastructure with cloud as the core has become one of the important strategies to serve the country's economic and social development. At the same time, it is also facing increasingly serious security threats. The emergence and practical application of quantum cryptography technology has opened up a new path to ensure the security of cloud computing infrastructure, and quantum key cloud has since come into being.

[0004] The quantum cryptography cloud platform is of strategic significance for building a new line of defense for network security based on quantum secure communication. Faced with the needs of intelligent, high-speed and complex networks, the means of attack are becoming more and more complex. Traditional network security technologies are becoming increasingly incapable of coping, and network intrusions are inevitable.

[0005] Network security situation awareness technology collects and analyzes network security data from each device in the quantum key cloud platform, thereby evaluating the current network status, enabling quantum key cloud platform security administrators to have a more comprehensive understanding of the current network security status and predict future security trends based on the network security situation in the past.

[0006] However, the existing network security situation awareness prediction methods have low prediction accuracy and slow convergence speed. Moreover, the traditional neural network model is used for prediction, which has many model setting parameters and insufficient generalization performance, making it impossible to make effective predictions. Summary of the invention

[0007] In order to solve the problem of low prediction accuracy of existing network security situation awareness prediction methods, the present invention provides a quantum key cloud security situation awareness prediction system and method.

[0008] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0009] A quantum key cloud security situation perception prediction system includes a data acquisition layer, a security situation assessment layer, a security situation prediction layer and a security situation warning layer; wherein,

[0010] The data collection layer is used to collect data from the quantum key cloud platform to obtain a classical data set;

[0011] The security situation assessment layer is used to combine the quantum computer, genetic algorithm and simulated annealing algorithm to optimize the classical data set, obtain the prediction result of the classical data set, and evaluate the current security situation value of the quantum key cloud platform according to the prediction result of the classical data set;

[0012] The security situation prediction layer is used to combine the quantum computer, the genetic algorithm and the simulated annealing algorithm to optimize the current security situation value and the historical security situation value of the quantum key cloud platform to obtain the predicted situation value of the quantum key cloud platform;

[0013] The security situation warning layer is used to warn users of the current security situation of the quantum key cloud platform in real time based on the current security situation value and predicted situation value of the quantum key cloud platform.

[0014] In the above scheme, by combining quantum computers, genetic algorithms and simulated annealing algorithms, effective assessment and accurate prediction of the security situation of the quantum key cloud can be achieved, which greatly improves the security stability of the quantum key cloud platform and provides strong protection for the increasingly large and complex cyberspace.

[0015] Preferably, the data collection layer uses probes to collect data from the quantum key cloud platform.

[0016] Preferably, the probes include flow probes, log probes, asset probes and vulnerability probes.

[0017] Preferably, the quantum computer comprises an input layer, a hidden layer and an output layer:

[0018] The input layer is used to convert the input data into quantum state information and initialize the parameter weights on the quantum circuit;

[0019] The hidden layer is used to measure the quantum state information through a variational quantum circuit to obtain an output vector;

[0020] The output layer is used to map the output vector to obtain the prediction result of the input data.

[0021] Preferably, the specific steps of combining quantum computer, genetic algorithm and simulated annealing algorithm for optimization are:

[0022] A1: Randomly generate M individuals as the initial population, where each individual includes n parameter weights, and each parameter weight corresponds to a different node on the quantum circuit of the quantum computer input layer;

[0023] A2: Encode the location of parameter weights in each individual;

[0024] A3: Calculate the fitness value of each individual based on the input data and output data of the quantum computer;

[0025] A4: Determine whether the minimum fitness value is not greater than the preset minimum threshold;

[0026] If yes, execute step A10;

[0027] If not, proceed to step A5;

[0028] A5: Determine whether the current number of iterations reaches the preset maximum number of iterations;

[0029] If yes, execute step A10;

[0030] If not, proceed to step A6;

[0031] A6: Sort the fitness values ​​of each individual from small to large, retain the top-ranked individuals according to the preset ratio, and discard the bottom-ranked individuals;

[0032] A7: Cross the retained individuals to generate new individual combinations;

[0033] A8: Randomly mutate the codes of some individuals in the new individual combination;

[0034] A9: The mutated individuals are grouped into an intermediate population, and simulated annealing is performed on the intermediate population to obtain a new generation of population, and then return to step A3 for the next round of iteration;

[0035] A10: The individual with the smallest fitness value is taken as the optimal individual, and the optimization ends.

[0036] Preferably, in step A2, the positions of the parameter weights are binary-coded, the used parameter weight positions are coded as 1, and the unused parameter weight positions are coded as 0.

[0037] Preferably, in step A3, the fitness value is calculated by the following fitness function:

[0038]

[0039] Among them, X is the data input into the quantum computer, and Y is the predicted result of X.

[0040] Preferably, it also includes a data preprocessing layer for performing data normalization processing on the classic data set input into the security situation assessment layer.

[0041] Preferably, the security situation assessment layer is preset with a platform security level, and the current security situation value of the quantum key cloud platform is assessed according to the platform security level corresponding to the optimization result.

[0042] A quantum key cloud security situation awareness prediction method is implemented based on the quantum key cloud security situation awareness prediction system, comprising the following steps:

[0043] S1: Collect data from the quantum key cloud platform to obtain a classical data set;

[0044] S2: Optimize the classic data set to obtain the prediction results of the classic data set;

[0045] S3: Evaluate the current security situation value of the quantum key cloud platform based on the prediction results of the classical data set;

[0046] S4: Optimize the current security situation value and the historical security situation value of the quantum key cloud platform to obtain the predicted situation value of the quantum key cloud platform;

[0047] S5: Provide users with real-time warnings on the current security status of the quantum key cloud platform based on the current security status value and predicted status value of the quantum key cloud platform.

[0048] Beneficial technical effects of the present invention:

[0049] The present invention provides a quantum key cloud security situation perception and prediction system and method. By combining quantum computers, genetic algorithms and simulated annealing algorithms, effective evaluation and accurate prediction of the quantum key cloud security situation can be achieved, which greatly improves the security stability of the quantum key cloud platform and provides a strong guarantee for protecting the increasingly large and complex cyberspace. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a structural block diagram of a quantum key cloud security situation awareness prediction system of the present invention;

[0051] Figure 2 This is a flow chart of the optimization process performed by combining a quantum computer, a genetic algorithm and a simulated annealing algorithm in the present invention;

[0052] Figure 3 It is a flowchart of the implementation steps of the technical solution of the present invention;

[0053] Among them: 1. Data collection layer; 2. Security situation assessment layer; 3. Security situation prediction layer; 4. Security situation warning layer; 5. Data preprocessing layer. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments, but the scope of protection claimed in the present invention is not limited to the following specific embodiments.

[0055] Example 1

[0056] like Figure 1 As shown, a quantum key cloud security situation awareness prediction system includes a data acquisition layer 1, a security situation assessment layer 2, a security situation prediction layer 3 and a security situation warning layer 4; wherein,

[0057] The data collection layer 1 is used to collect data from the quantum key cloud platform to obtain a classical data set;

[0058] The security situation assessment layer 2 is used to combine the quantum computer, genetic algorithm and simulated annealing algorithm to optimize the classical data set, obtain the prediction result of the classical data set, and evaluate the current security situation value of the quantum key cloud platform according to the prediction result of the classical data set;

[0059] The security situation prediction layer 3 is used to combine the quantum computer, the genetic algorithm and the simulated annealing algorithm to optimize the current security situation value and the historical security situation value of the quantum key cloud platform to obtain the predicted situation value of the quantum key cloud platform;

[0060] The security situation warning layer 4 is used to warn users of the current security situation of the quantum key cloud platform in real time based on the current security situation value and predicted situation value of the quantum key cloud platform.

[0061] During the specific implementation process, by combining quantum computers, genetic algorithms and simulated annealing algorithms, we can effectively evaluate and accurately predict the security situation of the quantum key cloud, greatly improve the security stability of the quantum key cloud platform, and provide strong guarantees for protecting the increasingly large and complex cyberspace.

[0062] Example 2

[0063] A quantum key cloud security situation perception prediction system includes a data acquisition layer 1, a security situation assessment layer 2, a security situation prediction layer 3 and a security situation warning layer 4; wherein,

[0064] The data collection layer 1 is used to collect data from the quantum key cloud platform to obtain a classical data set;

[0065] More specifically, the data collection layer 1 uses probes to collect data from the quantum key cloud platform.

[0066] More specifically, the probes include flow probes, log probes, asset probes and vulnerability probes.

[0067] More specifically, it also includes a data preprocessing layer 5 for performing data normalization processing on the classic data set input into the security situation assessment layer 2.

[0068] The security situation assessment layer 2 is used to combine the quantum computer, genetic algorithm and simulated annealing algorithm to optimize the classical data set, obtain the prediction result of the classical data set, and evaluate the current security situation value of the quantum key cloud platform according to the prediction result of the classical data set;

[0069] More specifically, the security situation assessment layer 2 is preset with a platform security level, and the current security situation value of the quantum key cloud platform is assessed according to the platform security level corresponding to the optimization result.

[0070] The security situation prediction layer 3 is used to combine the quantum computer, the genetic algorithm and the simulated annealing algorithm to optimize the current security situation value and the historical security situation value of the quantum key cloud platform to obtain the predicted situation value of the quantum key cloud platform;

[0071] More specifically, the quantum computer includes an input layer, a hidden layer, and an output layer:

[0072] The input layer is used to convert the input data into quantum state information and initialize the parameter weights on the quantum circuit;

[0073] The hidden layer is used to measure the quantum state information through a variational quantum circuit to obtain an output vector;

[0074] The output layer is used to map the output vector to obtain the prediction result of the input data.

[0075] More specifically, if Figure 2 As shown, the specific steps of combining quantum computers, genetic algorithms and simulated annealing algorithms for optimization are:

[0076] A1: Randomly generate M individuals as the initial population, where each individual includes n parameter weights, and each parameter weight corresponds to a different node on the quantum circuit of the quantum computer input layer;

[0077] In actual implementation, the number of individuals in the population can be set according to the actual situation; the number of nodes of the quantum circuit of the input layer of the quantum computer is determined according to the input data, and each node corresponds to a parameter weight, thereby determining the number n of parameter weights;

[0078] A2: Encode the location of parameter weights in each individual;

[0079] More specifically, in step A2, the positions of the parameter weights are binary-coded, the used parameter weight positions are coded as 1, and the unused parameter weight positions are coded as 0.

[0080] A3: Calculate the fitness value of each individual based on the input data and output data of the quantum computer;

[0081] More specifically, in step A3, the fitness value is calculated by the following fitness function:

[0082]

[0083] Among them, X is the data input into the quantum computer, and Y is the predicted result of X.

[0084] In the specific implementation process, As the fitness function, the selected n parameter weights are set as a constraint condition to make the fitness value f reach a preset minimum threshold.

[0085] A4: Determine whether the minimum fitness value is not greater than the preset minimum threshold;

[0086] If yes, execute step A10;

[0087] If not, proceed to step A5;

[0088] A5: Determine whether the current number of iterations reaches the preset maximum number of iterations;

[0089] If yes, execute step A10;

[0090] If not, proceed to step A6;

[0091] A6: Sort the fitness values ​​of each individual from small to large, retain the top-ranked individuals according to the preset ratio, and discard the bottom-ranked individuals;

[0092] A7: Cross the retained individuals to generate new individual combinations;

[0093] A8: Randomly mutate the codes of some individuals in the new individual combination, for example, 0 becomes 1 or 1 becomes 0;

[0094] A9: The mutated individuals are grouped into an intermediate population, and simulated annealing is performed on the intermediate population to obtain a new generation of population, and then return to step A3 for the next round of iteration;

[0095] A10: The individual with the smallest fitness value is taken as the optimal individual, and the optimization ends.

[0096] The security situation warning layer 4 is used to warn users of the current security situation of the quantum key cloud platform in real time based on the current security situation value and predicted situation value of the quantum key cloud platform.

[0097] Example 3

[0098] like Figure 3 As shown, a quantum key cloud security situation awareness prediction method is implemented based on the quantum key cloud security situation awareness prediction system, including the following steps:

[0099] S1: Collect data from the quantum key cloud platform to obtain a classical data set;

[0100] S2: Optimize the classic data set to obtain the prediction results of the classic data set;

[0101] S3: Evaluate the current security situation value of the quantum key cloud platform based on the prediction results of the classical data set;

[0102] S4: Optimize the current security situation value and the historical security situation value of the quantum key cloud platform to obtain the predicted situation value of the quantum key cloud platform;

[0103] S5: Provide users with real-time warnings on the current security status of the quantum key cloud platform based on the current security status value and predicted status value of the quantum key cloud platform.

[0104] According to the disclosure and teaching of the above description, those skilled in the art to which the present invention belongs may also make changes and modifications to the above embodiments. Therefore, the present invention is not limited to the specific embodiments disclosed and described above, and some modifications and changes to the invention should also fall within the scope of protection of the claims of the present invention. In addition, although some specific terms are used in this specification, these terms are only for the convenience of description and do not constitute any limitation to the present invention.

Claims

1. A quantum key cloud security situation awareness prediction system, characterized in that: It includes data collection layer, security situation assessment layer, security situation prediction layer and security situation early warning layer; among them, The data collection layer is used to collect data from the quantum key cloud platform to obtain a classical data set; The security situation assessment layer is used to combine the quantum computer, genetic algorithm and simulated annealing algorithm to optimize the classical data set, obtain the prediction result of the classical data set, and evaluate the current security situation value of the quantum key cloud platform according to the prediction result of the classical data set; The security situation prediction layer is used to combine the quantum computer, the genetic algorithm and the simulated annealing algorithm to optimize the current security situation value and the historical security situation value of the quantum key cloud platform to obtain the predicted situation value of the quantum key cloud platform; The security situation warning layer is used to warn users of the current security situation of the quantum key cloud platform in real time based on the current security situation value and predicted situation value of the quantum key cloud platform.

2. A quantum key cloud security situation awareness prediction system according to claim 1, characterized in that: The data collection layer uses probes to collect data from the quantum key cloud platform.

3. A quantum key cloud security situation awareness prediction system according to claim 2, characterized in that: The probes include flow probes, log probes, asset probes and vulnerability probes.

4. A quantum key cloud security situation awareness prediction system according to claim 1, characterized in that: The quantum computer includes an input layer, a hidden layer, and an output layer: The input layer is used to convert the input data into quantum state information and initialize the parameter weights on the quantum circuit; The hidden layer is used to measure the quantum state information through a variational quantum circuit to obtain an output vector; The output layer is used to map the output vector to obtain the prediction result of the input data.

5. A quantum key cloud security situation awareness prediction system according to claim 4, characterized in that: The specific steps of combining quantum computers, genetic algorithms and simulated annealing algorithms for optimization are: A1: Randomly generate M individuals as the initial population, where each individual includes n parameter weights, and each parameter weight corresponds to a different node on the quantum circuit of the quantum computer input layer; A2: Encode the location of parameter weights in each individual; A3: Calculate the fitness value of each individual based on the input data and output data of the quantum computer; A4: Determine whether the minimum fitness value is not greater than the preset minimum threshold; If yes, execute step A10; If not, proceed to step A5; A5: Determine whether the current number of iterations reaches the preset maximum number of iterations; If yes, execute step A10; If not, proceed to step A6; A6: Sort the fitness values ​​of each individual from small to large, retain the top-ranked individuals according to the preset ratio, and discard the bottom-ranked individuals; A7: Cross the retained individuals to generate new individual combinations; A8: Randomly mutate the codes of some individuals in the new individual combination; A9: The mutated individuals are grouped into an intermediate population, and simulated annealing is performed on the intermediate population to obtain a new generation of population, and then return to step A3 for the next round of iteration; A10: The individual with the smallest fitness value is taken as the optimal individual, and the optimization ends.

6. A quantum key cloud security situation awareness prediction system according to claim 5, characterized in that: In step A2, the positions of the parameter weights are binary-coded, the used parameter weight positions are coded as 1, and the unused parameter weight positions are coded as 0.

7. A quantum key cloud security situation awareness prediction system according to claim 5, characterized in that: In step A3, the fitness value is calculated by the following fitness function: Among them, X is the data input into the quantum computer, and Y is the predicted result of X.

8. A quantum key cloud security situation awareness prediction system according to claim 1, characterized in that: It also includes a data preprocessing layer for normalizing the classic data set input into the security situation assessment layer.

9. A quantum key cloud security situation awareness prediction system according to claim 1, characterized in that: The security situation assessment layer is preset with a platform security level, and the current security situation value of the quantum key cloud platform is assessed according to the platform security level corresponding to the optimization result.

10. A quantum key cloud security situation awareness prediction method according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1: Collect data from the quantum key cloud platform to obtain a classical data set; S2: Optimize the classic data set to obtain the prediction results of the classic data set; S3: Evaluate the current security situation value of the quantum key cloud platform based on the prediction results of the classical data set; S4: Optimize the current security situation value and the historical security situation value of the quantum key cloud platform to obtain the predicted situation value of the quantum key cloud platform; S5: Provide users with real-time warnings on the current security status of the quantum key cloud platform based on the current security status value and predicted status value of the quantum key cloud platform.

Images