Drive information security management system and method based on memristor neural network

Abstract

The invention discloses a driving information security management system and method based on a memristor neural network, and relates to the technical field of information security, and the method comprises the steps: S1, monitoring the synchronism of a response system and a driving system in real time, and collecting feedback signal data; s2, analyzing and designing a synchronous controller through a Lyapunov stability theory; s3, dynamically selecting an information encryption mode by using the memristor neural network according to the synchronization error, the feedback signal and the signal encryption level; s4, ensuring that the probability that the encrypted information is decrypted in the driving feedback interval is lower than a set threshold value; and S5, extracting and analyzing the historical encryption signal, and updating an information encryption mode and a network security level. Based on the Lyapunov stability theory, the synchronous controller is constructed, the signal encryption level is dynamically adjusted by using the memristor neural network, and high-level safety is ensured to be kept in the dynamic change process.

Description

Technical Field

[0001] The present invention relates to the field of information security technology, and in particular to a drive information security management system and method based on a memristor neural network. Background Art

[0002] With the development of information technology, industrial control systems and embedded systems are increasingly used in various industries. In these systems, information security and synchronization are key issues. Traditional information security management methods often focus on static encryption mechanisms or synchronization control strategies, which are difficult to cope with security challenges in dynamic environments. Especially in systems that require real-time feedback and high synchronization, the encryption and decryption process of information may be affected by changes in system status, leading to security and stability issues.

[0003] Although the current solutions provide basic information encryption and synchronization control strategies, they do not provide sufficient support for the dynamic adjustment of real-time synchronization errors, feedback signals, and encryption requirements. This makes it difficult to simultaneously meet information security and system stability in complex system environments. Summary of the invention

[0004] The purpose of the present invention is to provide a drive information security management system and method based on a memristor neural network to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a driving information security management method based on a memristor neural network, the method comprising the steps of:

[0006] S1. Real-time monitoring of the synchronization between the response system and the drive system, and collection of feedback signal data;

[0007] S2. Analyze and design synchronous controllers through Lyapunov stability theory;

[0008] S3, using a memristor neural network to dynamically select an information encryption method based on synchronization error, feedback signal and signal encryption level;

[0009] S4, ensuring that the probability of the encrypted information being decrypted within the drive feedback interval is lower than a set threshold;

[0010] S5. Extract and analyze historical encryption signals, and update information encryption methods and network security levels.

[0011] According to the above scheme, the synchronization is evaluated by monitoring the synchronization error between the response system and the drive system, and the formula is as follows:

[0012] e(t)=‖y response (t)-y drive (t) ‖;

[0013] Where e(t) represents the synchronization error at time t; y response (t) represents the output signal of the response system at time t; y drive (t) represents the output signal of the drive system at time t; t represents the time variable of continuous time;

[0014] The feedback signal includes feedback of state variables and control instructions of the response system and the drive system;

[0015] The collected feedback signal data is subjected to data preprocessing, which includes removing duplicate data, filling missing values, noise suppression and standardization processing; and an abnormal data detection and processing mechanism is performed on the feedback signal data to prevent excessive errors or abnormal feedback signals from affecting system decisions.

[0016] According to the above scheme, the Lyapunov stability theory analyzes the synchronization error stability of the system by defining a suitable Lyapunov function;

[0017] The Lyapunov function is used to analyze whether the system can recover to a stable state under the influence of disturbance or error, and ensure that the response system and the drive system remain stable during the synchronization process;

[0018] The system state is expressed as: x(t) = [x1(t), x2(t)] T ; Among them, x1(t) represents the state of the response system at time t; x2(t) represents the state of the drive system at time t; construct the Lyapunov function V(x) to describe the state of the system, the formula is as follows:

[0019]

[0020] Among them, P represents a positive definite matrix, which is the weight coefficient of the system; x1 represents the state of the response system; x2 represents the state of the driving system;

[0021] The Lyapunov function is used to measure the size of the difference in system states, and to determine whether the system will stabilize by analyzing the behavior of the system state changing over time;

[0022] Applying Lyapunov's second law, the stability of the system is analyzed by calculating the derivative of the Lyapunov function. The formula is as follows:

[0023]

[0024] Among them, when V(x) is a positive definite function and its derivative In the entire state space, all states x are negative definite functions, that is, V(x)>0, and When , it is concluded that the system is asymptotically stable, that is, the error between the response system and the drive system will gradually decrease and eventually reach a synchronous state;

[0025] When constructing the Lyapunov function, the inequality technique is used to define the upper bound of the error and ensure the reduction of the synchronization error. The inequality is as follows:

[0026]

[0027] The relationship between the system state and the control input is analyzed using the inequality.

[0028] According to the above scheme, the synchronous controller, based on Lyapunov stability theory, ensures that the response system and the drive system stably converge to a synchronous state; the synchronous controller needs to minimize the synchronization error and ensure the robustness of the system;

[0029] The synchronous controller has the following formula:

[0030]

[0031] Where u(t) represents the synchronous controller; e(t) represents the synchronization error; t represents the time variable of continuous time; K p , K i and K d They are respectively expressed as proportional, integral and differential gains; the synchronous controller optimizes the performance of the synchronous controller by comprehensively adjusting the proportional, integral and differential gains.

[0032] According to the above scheme, the memristor neural network includes an input layer, a hidden layer and an output layer;

[0033] The input layer receives input variables; the input variables include synchronization error, feedback signal and signal encryption level;

[0034] The synchronization error is used to quantify the synchronization error between the response system and the drive system;

[0035] The feedback signal includes feedback of state variables and control instructions of the response system and the drive system;

[0036] the signal encryption level, an indication of a current encryption strength, the indication of the current encryption strength including low, medium and high signal encryption levels;

[0037] The hidden layer performs weighted processing and nonlinear transformation on the input signal through neurons, thereby extracting effective features;

[0038] The hidden layer includes M neurons, which receive input variables, perform calculations using weighted summation, and then perform nonlinear transformations through activation functions to generate output signals, and transmit the output signals to the next layer of neurons or finally to the output layer;

[0039] The weighted summation formula is as follows:

[0040]

[0041] Among them, z k (t) represents the activation value of the kth output neuron; w ki represents the connection weight between the kth output neuron and the ith input variable; n represents the total number of input variables; i represents the index of the input variable; x i (t) represents the input variable; t represents the time variable of continuous time; b k Represented as the bias term of the neuron;

[0042] The activation function formula is as follows:

[0043] a k (t) = σ(z k (t));

[0044] Among them, a k (t) represents the output signal of the neuron; σ represents the activation function;

[0045] The output layer outputs a suitable information encryption method according to the output signal of the hidden layer.

[0046] According to the above scheme, the memristor neural network adjusts the information encryption method according to real-time data, and dynamically adjusts the connection weight according to the synchronization error and feedback signal. The formula is as follows:

[0047]

[0048] Among them, w ki (t) represents the connection weight between the kth neuron and the ith input variable; η represents the learning rate, which controls the step size of weight update; It is represented as the gradient of synchronization error to weight; e(t) represents the synchronization error; h(t) represents the influence factor of feedback signal on weight; ΔL(t) represents the influence factor of change of signal encryption level on weight; α and β represent the influence weight factors of control feedback signal and change of signal encryption level on weight update respectively;

[0049] Real-time state adjustment uses reinforcement learning methods to adjust network weights through real-time feedback, allowing the network to quickly adapt to dynamic environments.

[0050] According to the above scheme, the dynamic selection of information encryption method uses a memristor neural network to dynamically select a suitable encryption method based on synchronization error, feedback signal and signal encryption level to ensure that the encryption strength matches the real-time requirements of the system;

[0051] By designing an encryption mechanism, the risk of information being decrypted within the drive feedback interval is reduced, ensuring information security.

[0052] According to the above scheme, the corresponding encryption strength is calculated according to the synchronization error, the feedback signal and the signal encryption level. The encryption strength affects the probability of information being decrypted. The formula is as follows:

[0053] C(t)=f(e(t),y(t),L);

[0054] Wherein, C(t) represents the encryption strength at time t; e(t) represents the synchronization error, which is the synchronization error between the response system and the drive system; y(t) represents the feedback signal; L represents the signal encryption level; f represents a function that combines the synchronization error, the feedback signal and the signal encryption level to determine the appropriate encryption strength;

[0055] The probability of being decrypted is as follows:

[0056] P decrypt (t) = g(C(t), Δt);

[0057] Among them, P decrypt (t) represents the probability of information being decrypted at time t; Δt represents the length of the drive feedback interval; g(C(t), Δt) is a function that represents the impact of encryption strength C(t) and drive feedback interval Δt on decryption risk;

[0058] The probability of ensuring that the encrypted information is decrypted within the drive feedback interval is lower than the set threshold, that is, P decrypt (t)<θ, where θ represents the set threshold.

[0059] According to the above scheme, the historical encrypted signal is analyzed based on the historical synchronization error, the probability of being decrypted and the encryption strength;

[0060] The synchronization error is analyzed to obtain the average synchronization error, and the formula is as follows:

[0061]

[0062] in, Expressed as the average value of synchronization error; e i (t) represents the synchronization error at the jth time point t; N represents the number of historical signals;

[0063] The probability of being decrypted is analyzed to obtain the average probability of being decrypted, and the formula is as follows:

[0064]

[0065] in, Expressed as the average value of the probability of being decrypted; C j (t) represents the probability of being decrypted at the jth time point t;

[0066] The encryption strength is analyzed to obtain an average encryption strength, and the formula is as follows:

[0067]

[0068] in, Expressed as the average encryption strength; Expressed as the encryption strength at the jth time point t;

[0069] Adjust the current information encryption method based on historical synchronization errors, probability of decryption and encryption strength analysis results;

[0070] Assess the security of the overall network and update the network security level based on historical analysis to ensure the security of the system.

[0071] A drive information security management system based on a memristor neural network, the system comprising: a data monitoring module, a synchronization control module, a memristor neural network module, a risk assessment module and a security optimization module;

[0072] The data monitoring module monitors the synchronization between the response system and the drive system in real time, collects feedback signals from the response system and the drive system, and evaluates the synchronization state;

[0073] The synchronization control module uses Lyapunov stability theory to design and adjust the synchronization control strategy to ensure that the response system and the drive system can stably converge to a synchronization state;

[0074] The memristor neural network module dynamically selects the information encryption method according to the synchronization error, feedback signal and signal encryption level to ensure that the encryption strength matches the real-time demand and ensures information security; the memristor neural network module has an adaptive mechanism and can dynamically adjust the encryption method, control strategy and network security level according to the attack type, network environment and technological progress;

[0075] The risk assessment module analyzes the probability of encrypted information being decrypted within the drive feedback interval, ensures that the probability of being decrypted within the drive feedback interval is lower than a set threshold, and reduces the risk of decryption of information during transmission;

[0076] The security optimization module performs data analysis on historical synchronization errors, probability of decryption and encryption strength, calculates average values, and analyzes the stability of encrypted signals and network security; updates the current encryption scheme based on the analysis results, and evaluates and adjusts the network security level; learns through historical data and real-time feedback, adjusts encryption strategies or optimization algorithms based on long-term operating data, and improves overall security and performance.

[0077] Compared with the prior art, the present invention has the following beneficial effects:

[0078] 1. Based on Lyapunov stability theory, the present invention constructs a synchronous controller to evaluate and adjust the synchronization of the response system and the drive system in real time to ensure that the synchronization error gradually decreases;

[0079] 2. The present invention utilizes a memristor neural network to dynamically adjust the signal encryption level, effectively reducing the probability of information being decrypted within the drive feedback interval, and ensuring a high level of security during dynamic changes;

[0080] 3. By analyzing historical synchronization errors, decryption probability and encryption strength, the present invention can optimize the current encryption method and network security level, making information security management more intelligent and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 This is a flow chart of the steps of a driving information security management method based on a memristor neural network of the present invention;

[0082] Figure 2 It is a structural schematic diagram of a drive information security management system based on a memristor neural network of the present invention. DETAILED DESCRIPTION

[0083] The following will be combined with the 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, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0084] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution, a driving information security management method based on a memristor neural network;

[0085] S1. Real-time monitoring of the synchronization between the response system and the drive system, and collection of feedback signal data;

[0086] The embodiments of the present application are described using an electric power monitoring center and a remote terminal device as examples, which are only used for illustration and not for limitation.

[0087] Specifically, the power monitoring center and the remote terminal device must maintain synchronization to ensure the effectiveness of instructions and feedback. The power monitoring center is the response system, and the remote terminal device is the drive system. There may be a certain delay or error between the power monitoring center and the remote terminal device. The synchronization of the response system and the drive system is evaluated by monitoring the synchronization error between the response system and the drive system. The formula is as follows:

[0088] e(t)=‖y response (t)-y drive (t) ‖;

[0089] Where e(t) represents the synchronization error at time t; y response (t) represents the output signal of the response system at time t; y drive (t) represents the output signal of the drive system at time t; t represents the time variable of continuous time;

[0090] For synchronization error, for example, the output signal of the power monitoring center is 50, while the output signal of the remote terminal device is 45. The device does not respond completely as expected. At this time, the synchronization error is: e(t) = |50-45| = 5;

[0091] Next, feedback signal data is collected, wherein the feedback signal includes feedback of the state variables and control instructions of the response system and the drive system; for example: the power monitoring center is the response system, and the remote terminal device is the drive system, then the state variable is the state of a substation device is "running" or "off", and the feedback of the control instruction is the substation circuit breaker switch switching from "off" to "on", which is only an example here and is not limited.

[0092] The collected feedback signal data is then preprocessed, including data cleaning, noise suppression and standardization. For example, a hash table or index structure is used to quickly identify and delete identical records, and deduplication is used to avoid receiving multiple identical data points due to network delays or other reasons. Linear or spline interpolation is performed based on the adjacent points before and after the time series to fill in missing values ​​and ensure data integrity. The use of filtering algorithms to suppress noise can improve data quality and thus improve the accuracy of the system. At the same time, the feedback signal data is subjected to abnormal data detection and processing mechanisms. For example, based on statistical methods or machine learning methods, outliers can be identified and eliminated. Error thresholds can be set for feedback signals and synchronization errors. Once the error exceeds the set range, an early warning or recovery mechanism is automatically activated to prevent excessive errors or abnormal feedback signals from affecting system decisions.

[0093] S2. Analyze and design synchronous controllers through Lyapunov stability theory;

[0094] Specifically, Lyapunov stability theory is used to define a suitable Lyapunov function to analyze the stability of the system's synchronization error; the Lyapunov function is used to analyze whether the system can recover to a stable state under the influence of disturbances or errors; the Lyapunov stability theory is used to analyze whether the synchronization error between the power monitoring center and the remote terminal equipment will gradually decrease. If the change of the synchronization error can be effectively controlled, it means that the system is stable.

[0095] The system state is expressed as: x(t) = [x1(t), x2(t)] T ; Among them, x1(t) represents the state of the response system at time t; x2(t) represents the state of the drive system at time t; construct the Lyapunov function V(x) to describe the state of the system, the formula is as follows:

[0096]

[0097] Among them, P represents a positive definite matrix, which is the weight coefficient of the system; x1 represents the state of the response system; x2 represents the state of the driving system;

[0098] The Lyapunov function is used to measure the size of the difference in the system state and to determine whether the system will stabilize by analyzing the behavior of the system state changing over time;

[0099] Applying Lyapunov's second law, the stability of the system is analyzed by calculating the derivative of the Lyapunov function. The formula is as follows:

[0100]

[0101] Among them, when V(x) is a positive definite function and its derivative In the entire state space, all states x are negative definite functions, that is, V(x)>0, and When , it is concluded that the system is asymptotically stable, that is, the error between the response system and the drive system will gradually decrease and eventually reach a synchronous state; for example, the derivative of the Lyapunov function is -2, which means that the system will gradually stabilize, that is, the synchronization error between the power monitoring center and the remote terminal device will decrease.

[0102] At the same time, the inequality technology is used to define the upper bound of the error and ensure the reduction of the synchronization error. The inequality is as follows:

[0103]

[0104] The relationship between the system state and the control input is analyzed using the inequality.

[0105] Next, based on Lyapunov stability theory, a synchronous controller is constructed to ensure that the response system and the drive system stably converge to a synchronous state. The formula is as follows:

[0106]

[0107] Where u(t) represents the synchronous controller; e(t) represents the synchronization error; t represents the time variable of continuous time; K p , K i and K d Respectively expressed as proportional, integral and differential gains; the synchronous controller optimizes the performance of the synchronous controller by comprehensively adjusting the proportional, integral and differential gains, thereby effectively reducing errors and maintaining the synchronization of the system, which helps to improve communication efficiency and ensure the accuracy and timeliness of information transmission. For example, problems such as sensor noise and network delay may be encountered, which will have a negative impact on synchronization. Using Lyapunov stability theory to construct a synchronous controller can enhance the robustness of the system so that it can still maintain good performance in the face of interference.

[0108] S3, using a memristor neural network to dynamically select an information encryption method based on synchronization error, feedback signal and signal encryption level;

[0109] In different working environments, system loads and communication states, synchronization errors, feedback signals and signal encryption levels will change. By adjusting the encryption method in real time, the best balance between resources and security can be maintained to meet actual needs, which can not only improve information security, but also avoid the waste of computing resources caused by excessive encryption. If only one of the conditions is considered separately, for example, the encryption method is selected based only on the synchronization error, the synchronization error only reflects the time difference between the systems and cannot fully reflect the security requirements of the data. In addition, adjusting the encryption method based on the synchronization error may lead to encryption that is too strong or too weak in some cases. For example, when the synchronization error is small but the system load is too high, if high-intensity encryption continues to be used, it will consume too many computing resources and affect system performance.

[0110] While ensuring that the synchronization error is gradually reduced, it is necessary to ensure the security of information transmitted between the power monitoring center and the remote terminal equipment. In order to prevent data from being maliciously stolen or tampered with, a memristor neural network is used to dynamically select encryption strategies;

[0111] Specifically, a memristor neural network is constructed through the collected feedback signal data, and the memristor neural network includes an input layer, a hidden layer and an output layer; wherein the input layer receives input variables, and the input variables include synchronization error, feedback signal and signal encryption level; synchronization error is used to quantify the synchronization error between the response system and the drive system; the feedback signal includes the feedback of the state variables and control instructions of the response system and the drive system; signal encryption level, an indication of the current encryption strength, and the indication of the current encryption strength includes low, medium and high signal encryption levels; after the input variable enters the hidden layer through the input layer, the hidden layer performs weighted processing and nonlinear transformation on the input signal through neurons, so as to extract effective features; wherein the hidden layer contains M neurons, the neurons receive the input variables, and calculate using weighted summation, and then perform nonlinear transformation through an activation function to generate an output signal, and the output signal is transmitted to the next layer of neurons or finally to the output layer;

[0112] Weighted summation, the formula is as follows:

[0113]

[0114] Among them, z k (t) represents the activation value of the kth output neuron; w ki represents the connection weight between the kth output neuron and the ith input variable; n represents the total number of input variables; i represents the index of the input variable; x i (t) represents the input variable; t represents the time variable of continuous time; b k Represented as the bias term of the neuron;

[0115] Activation function, the formula is as follows:

[0116] a k (t) = σ(z k (t));

[0117] Among them, a k (t) represents the output signal of the neuron; σ represents the activation function;

[0118] Next, the output layer receives the output signal of the hidden layer, and selects an information encryption method based on the output signal of the hidden layer to ensure that the encryption strength matches the real-time requirements of the system; information encryption methods include but are not limited to symmetric encryption, asymmetric encryption, quantum encryption and other encryption methods; when selecting an encryption method, the consumption of computing resources will be comprehensively considered, and according to the resource limitations of the system, an appropriate encryption algorithm will be dynamically selected to balance the encryption strength and the consumption of computing resources.

[0119] For example: the synchronization error e(t1) = 0.1, indicating that there is a slight asynchrony between the response system and the drive system; the feedback signal y(t1) shows a normal working state; the current signal encryption level L = medium; based on the synchronization error, feedback signal and signal encryption level, the memristor neural network obtains the encryption strength C(t1) and outputs a medium-strength AES-256-bit symmetric encryption algorithm for information encryption. The AES-256-bit symmetric encryption algorithm has a lower computational complexity, but its key distribution problem is more complicated; this is only used as an example and is not limited.

[0120] And by designing an encryption mechanism, the risk of information being decrypted within the drive feedback interval is reduced to ensure information security.

[0121] At the same time, the memristor neural network adjusts the information encryption method according to real-time data, and dynamically adjusts the connection weight according to the synchronization error and feedback signal. The formula is as follows:

[0122]

[0123] Among them, w ki (t) represents the connection weight between the kth neuron and the ith input variable; η represents the learning rate, which controls the step size of weight update; It is represented as the gradient of synchronization error to weight; e(t) represents the synchronization error; h(t) represents the impact factor of feedback signal on weight; ΔL(t) represents the impact factor of change of signal encryption level on weight; α and β represent the weight factors of control feedback signal and change of signal encryption level on weight update respectively.

[0124] S4, ensuring that the probability of the encrypted information being decrypted within the drive feedback interval is lower than a set threshold;

[0125] Specifically, the corresponding encryption strength is calculated according to the synchronization error, feedback signal and signal encryption level. The encryption strength affects the probability of information being decrypted. The formula is as follows:

[0126] C(t)=f(e(t),y(t),L);

[0127] Wherein, C(t) represents the encryption strength at time t; e(t) represents the synchronization error, which is the synchronization error between the response system and the drive system; y(t) represents the feedback signal; L represents the signal encryption level; f represents a function that combines the synchronization error, the feedback signal and the signal encryption level to determine the appropriate encryption strength;

[0128] The probability of being decrypted is as follows:

[0129] P decrypt (t) = g(C(t), Δt);

[0130] Among them, P decrypt (t) represents the probability of information being decrypted at time t; Δt represents the length of the drive feedback interval; g(C(t), Δt) is a function that represents the impact of encryption strength C(t) and drive feedback interval Δt on decryption risk;

[0131] Ensure that the probability of encrypted information being decrypted within the drive feedback interval is lower than the set threshold, i.e., P decrypt (t)<θ, where θ represents the set threshold; for example, the set threshold is 0.05, since the probability of being decrypted is P decrypt (t)=0.01<θ=0.05, the current encryption strategy is safe and does not need to be adjusted.

[0132] S5. Extract and analyze historical encryption signals, and update information encryption methods and network security levels.

[0133] Specifically, all encrypted communication records within a period of time are extracted from the system log or database. These records should include but not be limited to encryption methods, key usage, synchronization errors, and feedback signals. Duplicate data is removed from these data, missing values ​​are filled, and data integrity and consistency are ensured. Features closely related to the analysis target are analyzed and screened out, including synchronization errors, probability of being decrypted, and encryption strength. Among them, the synchronization error is analyzed to obtain the average synchronization error, and the formula is as follows:

[0134]

[0135] in, Expressed as the average value of synchronization error; e i (t) represents the synchronization error at the jth time point t; N represents the number of historical signals;

[0136] While analyzing the synchronization error, the long-term trend and periodic changes in the time series of the synchronization error are identified through time series data analysis methods, such as the sliding average method, to evaluate the stability and response speed of the system;

[0137] The probability of being decrypted is analyzed to obtain the average probability of being decrypted. The formula is as follows:

[0138]

[0139] in, Expressed as the average value of the probability of being decrypted; C j (t) represents the probability of being decrypted at the jth time point t;

[0140] The encryption strength is analyzed to obtain the average encryption strength. The formula is as follows:

[0141]

[0142] in, Expressed as the average encryption strength; Expressed as the encryption strength at the jth time point t;

[0143] Adjust the current information encryption method based on historical synchronization errors, the probability of being decrypted, and the results of encryption strength analysis; for example, build a scoring model, assign weights to each dimension and calculate the total score, and decide whether the encryption method needs to be updated based on the results of the scoring model;

[0144] For example: when the synchronization error increases and the feedback signal is abnormal, the analysis shows that the current encryption strength is not sufficient to deal with potential security risks, and it may be necessary to increase the encryption strength, upgrade the encryption strategy, and adjust the current information encryption method; for example: upgrade from AES-256-bit symmetric encryption algorithm to combine RSA asymmetric encryption for key exchange, while maintaining AES-256-bit symmetric encryption algorithm for data encryption to enhance security; this is only an example for illustration and is not limited.

[0145] Assess the security of the overall network and update the network security level based on historical analysis to ensure the security of data transmitted in each communication and prevent sensitive information from being decrypted by unauthorized third parties.

[0146] The present invention provides another technical solution, a drive information security management system based on a memristor neural network;

[0147] The system includes: a data monitoring module, a synchronization control module, a memristor neural network module, a risk assessment module and a safety optimization module;

[0148] The data monitoring module monitors the synchronization between the response system and the drive system in real time, collects feedback signals from the response system and the drive system, and evaluates the synchronization state;

[0149] The synchronization control module uses Lyapunov stability theory to design and adjust the synchronization control strategy to ensure that the response system and the drive system can stably converge to a synchronization state;

[0150] The memristor neural network module dynamically selects the information encryption method according to the synchronization error, feedback signal and signal encryption level to ensure that the encryption strength matches the real-time demand and ensures information security; the memristor neural network module has an adaptive mechanism and can dynamically adjust the encryption method, control strategy and network security level according to the attack type, network environment and technological progress;

[0151] The risk assessment module analyzes the probability of encrypted information being decrypted within the drive feedback interval, ensures that the probability of being decrypted within the drive feedback interval is lower than a set threshold, and reduces the risk of decryption of information during transmission;

[0152] The security optimization module performs data analysis on historical synchronization errors, probability of decryption and encryption strength, calculates average values, and analyzes the stability of encrypted signals and network security; updates the current encryption scheme based on the analysis results, and evaluates and adjusts the network security level; learns through historical data and real-time feedback, adjusts encryption strategies or optimization algorithms based on long-term operating data, and improves overall security and performance.

[0153] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A drive information security management method based on a memristor neural network, characterized in that: The method comprises the steps of: S1. Real-time monitoring of the synchronization between the response system and the drive system, and collection of feedback signal data; S2. Analyze and design synchronous controllers through Lyapunov stability theory; S3, using a memristor neural network to dynamically select an information encryption method based on synchronization error, feedback signal and signal encryption level; S4, ensuring that the probability of the encrypted information being decrypted within the drive feedback interval is lower than a set threshold; S5. Extract and analyze historical encryption signals, and update information encryption methods and network security levels.

2. The driving information security management method based on memristor neural network according to claim 1 is characterized in that: The synchronization is evaluated by monitoring the synchronization error between the response system and the drive system, and the formula is as follows: e(t)=‖y response (t)-y drive (t)‖; Where e(t) represents the synchronization error at time t; y response (t) represents the output signal of the response system at time t; y drive (t) represents the output signal of the drive system at time t; t represents the time variable of continuous time; The feedback signal includes feedback of state variables and control instructions of the response system and the drive system.

3. The driving information security management method based on memristor neural network according to claim 1 is characterized in that: The Lyapunov stability theory analyzes the synchronization error stability of the system by defining a suitable Lyapunov function; The Lyapunov function is used to analyze whether the system can recover to a stable state under the influence of disturbance or error, and ensure that the response system and the drive system remain stable during the synchronization process; The system state is expressed as: x(t) = [x1(t), x2(t)] T ; Among them, x1(t) represents the state of the response system at time t; x2(t) represents the state of the drive system at time t; construct the Lyapunov function V(x) to describe the state of the system, the formula is as follows: Among them, P represents a positive definite matrix, which is the weight coefficient of the system; x1 represents the state of the response system; x2 represents the state of the driving system; The Lyapunov function is used to measure the size of the difference in system states, and to determine whether the system will stabilize by analyzing the behavior of the system state changing over time; Applying Lyapunov's second law, the stability of the system is analyzed by calculating the derivative of the Lyapunov function. The formula is as follows: Among them, when V(x) is a positive definite function and its derivative In the entire state space, all states x are negative definite functions, that is, V(x)>0, and When , it is concluded that the system is asymptotically stable, that is, the error between the response system and the drive system will gradually decrease and eventually reach a synchronous state; When constructing the Lyapunov function, the inequality technique is used to define the upper bound of the error and ensure the reduction of the synchronization error. The inequality is as follows: The relationship between the system state and the control input is analyzed using the inequality.

4. The driving information security management method based on memristor neural network according to claim 3 is characterized by: The synchronous controller, based on Lyapunov stability theory, ensures that the response system and the drive system stably converge to a synchronous state; the synchronous controller needs to minimize the synchronization error and ensure the robustness of the system; The synchronous controller has the following formula: Where u(t) represents the synchronous controller; e(t) represents the synchronization error; t represents the time variable of continuous time; K p , K i and K d They are respectively expressed as proportional, integral and differential gains; the synchronous controller optimizes the performance of the synchronous controller by comprehensively adjusting the proportional, integral and differential gains.

5. The driving information security management method based on memristor neural network according to claim 1 is characterized in that: The memristor neural network includes an input layer, a hidden layer and an output layer; The input layer receives input variables; the input variables include synchronization error, feedback signal and signal encryption level; The synchronization error is used to quantify the synchronization error between the response system and the drive system; The feedback signal includes feedback of state variables and control instructions of the response system and the drive system; the signal encryption level, an indication of a current encryption strength, the indication of the current encryption strength including low, medium and high signal encryption levels; The hidden layer performs weighted processing and nonlinear transformation on the input signal through neurons, thereby extracting effective features; The hidden layer includes M neurons, which receive input variables, perform calculations using weighted summation, and then perform nonlinear transformations through activation functions to generate output signals, and transmit the output signals to the next layer of neurons or finally to the output layer; The weighted summation formula is as follows: Among them, z k (t) represents the activation value of the kth output neuron; w ki represents the connection weight between the kth output neuron and the ith input variable; n represents the total number of input variables; i represents the index of the input variable; x i (t) represents the input variable; t represents the time variable of continuous time; b k Represented as the bias term of the neuron; The activation function formula is as follows: a k (t)=σ(z k (t)); Among them, a k (t) represents the output signal of the neuron; σ represents the activation function; The output layer outputs a suitable information encryption method according to the output signal of the hidden layer.

6. The driving information security management method based on memristor neural network according to claim 5 is characterized by: The memristor neural network adjusts the information encryption method according to real-time data, and dynamically adjusts the connection weight according to the synchronization error and feedback signal. The formula is as follows: Among them, w ki (t) represents the connection weight between the kth neuron and the ith input variable; η represents the learning rate, which controls the step size of weight update; It is represented as the gradient of synchronization error to weight; e(t) represents the synchronization error; h(t) represents the impact factor of feedback signal on weight; ΔL(t) represents the impact factor of change of signal encryption level on weight; α and β represent the weight factors of control feedback signal and change of signal encryption level on weight update respectively.

7. The driving information security management method based on memristor neural network according to claim 1 is characterized by: The dynamic selection of information encryption method uses a memristor neural network to dynamically select an appropriate encryption method based on synchronization error, feedback signal and signal encryption level to ensure that the encryption strength matches the real-time requirements of the system; By designing an encryption mechanism, the risk of information being decrypted within the drive feedback interval is reduced, ensuring information security.

8. The driving information security management method based on memristor neural network according to claim 1 is characterized by: The corresponding encryption strength is calculated according to the synchronization error, the feedback signal and the signal encryption level. The encryption strength affects the probability of information being decrypted. The formula is as follows: C(t)=f(e(t),y(t),L); Wherein, C(t) represents the encryption strength at time t; e(t) represents the synchronization error, which is the synchronization error between the response system and the drive system; y(t) represents the feedback signal; L represents the signal encryption level; f represents a function that combines the synchronization error, the feedback signal and the signal encryption level to determine the appropriate encryption strength; The probability of being decrypted is as follows: P decrypt (t)=g(C(t),Δt); Among them, P decrypt (t) represents the probability of information being decrypted at time t; Δt represents the length of the drive feedback interval; g(C(t), Δt) is a function that represents the impact of encryption strength C(t) and drive feedback interval Δt on decryption risk; The probability of ensuring that the encrypted information is decrypted within the drive feedback interval is lower than the set threshold, that is, P decrypt (t)<θ, where θ represents the set threshold.

9. The driving information security management method based on memristor neural network according to claim 1 is characterized by: Analyze historical encryption signals based on historical synchronization errors, probability of being decrypted, and encryption strength; The synchronization error is analyzed to obtain the average synchronization error, and the formula is as follows: in, Expressed as the average value of synchronization error; e i (t) represents the synchronization error at the jth time point t; N represents the number of historical signals; The probability of being decrypted is analyzed to obtain the average probability of being decrypted, and the formula is as follows: in, Expressed as the average value of the probability of being decrypted; C j (t) represents the probability of being decrypted at the jth time point t; The encryption strength is analyzed to obtain an average encryption strength, and the formula is as follows: in, Expressed as the average encryption strength; Expressed as the encryption strength at the jth time point t; Adjust the current information encryption method based on historical synchronization errors, probability of decryption and encryption strength analysis results; Assess the security of the overall network and update the network security level based on historical analysis to ensure the security of the system.

10. A drive information security management system based on a memristor neural network, applied to a drive information security management method based on a memristor neural network as claimed in any one of claims 1 to 9, characterized in that: The system includes: a data monitoring module, a synchronization control module, a memristor neural network module, a risk assessment module and a safety optimization module; The data monitoring module monitors the synchronization between the response system and the drive system in real time, collects feedback signals from the response system and the drive system, and evaluates the synchronization state; The synchronization control module uses Lyapunov stability theory to design and adjust the synchronization control strategy to ensure that the response system and the drive system can stably converge to a synchronization state; The memristor neural network module dynamically selects the information encryption method according to the synchronization error, feedback signal and signal encryption level to ensure that the encryption strength matches the real-time demand and ensure information security; The risk assessment module analyzes the probability of encrypted information being decrypted within the drive feedback interval, ensures that the probability of being decrypted within the drive feedback interval is lower than a set threshold, and reduces the risk of decryption of information during transmission; The security optimization module performs data analysis on historical synchronization errors, decryption probabilities, and encryption strengths, calculates average values, and analyzes the stability of encrypted signals and network security; updates the current encryption scheme based on the analysis results, and evaluates and adjusts the network security level.

Images