A bus encryption method, device and equipment based on simulated annealing optimization

Abstract

The embodiment of the application discloses a bus encryption method and device based on simulated annealing optimization and equipment. The technical scheme provided by the embodiment of the application inputs bus network load information, bus attack score and bus encryption delay information into the trained encryption strategy model, analyzes and processes the bus network load information, the bus attack score and the bus encryption delay information through the encryption strategy model to obtain encryption parameter information, and encrypts the to-be-sent data according to the encryption parameter information, wherein the number of hidden layer nodes and the network weight of the encryption strategy model are optimized based on the simulated annealing algorithm in the training process. The simulated annealing algorithm can effectively reduce the condition that the encryption strategy model falls into local optimization, and the number of hidden layer nodes and the bus attack score are positively correlated, which can effectively adapt to the encryption intensity requirement in different network attack scenes, effectively guarantee the safety of the bus transmission data, and improve the bus data encryption effect.

Description

Technical Field

[0001] This application relates to data encryption technology, and more particularly to a bus encryption method, apparatus, and device based on simulated annealing optimization. Background Technology

[0002] With the increasing connectivity of vehicles to external devices (such as mobile devices and infrastructure) and the opening of vehicle system interfaces, intelligent connected vehicles face growing cybersecurity risks. These risks include not only data breaches and privacy violations, but more seriously, direct threats to personal safety. For example, attacks via the Controller Area Network (CAN) bus can control critical vehicle functions, such as the braking and steering systems, posing a serious threat to the safety of drivers and passengers.

[0003] To ensure vehicle safety, data transmitted via the bus is typically encrypted. Traditional encryption algorithms (such as the Advanced Encryption Standard (AES)) are vulnerable to eavesdropping and replay attacks due to their fixed key mechanism, making it difficult to effectively secure data transmitted via the bus, resulting in poor bus data encryption. Summary of the Invention

[0004] This application provides a bus encryption method, apparatus, and device based on simulated annealing optimization to solve the technical problems in related technologies where data transmitted via bus is difficult to effectively secure and bus data encryption is poor. By dynamically updating encryption parameters, the security of bus data transmission is improved, effectively ensuring the security of data transmitted via bus and improving the bus data encryption effect.

[0005] In a first aspect, embodiments of this application provide a bus encryption method based on simulated annealing optimization, comprising: Obtain bus network load information, bus attack score, and bus encryption latency information; The bus network load information, the bus attack score, and the bus encryption delay information are input into the trained encryption strategy model. The encryption strategy model analyzes and processes the bus network load information, the bus attack score, and the bus encryption delay information to obtain encryption parameter information. The number of hidden layer nodes and network weights of the encryption strategy model are optimized based on the simulated annealing algorithm during training, and the number of hidden layer nodes is positively correlated with the higher the bus attack score. The data to be sent is encrypted based on the encryption parameter information.

[0006] In a second aspect, embodiments of this application provide a bus encryption device based on simulated annealing optimization, including an information acquisition module, a parameter determination module, and a data encryption module, wherein: The information acquisition module is used to acquire bus network load information, bus attack score, and bus encryption delay information; The parameter determination module is used to input the bus network load information, the bus attack score, and the bus encryption delay information into the trained encryption strategy model. The encryption strategy model analyzes and processes the bus network load information, the bus attack score, and the bus encryption delay information to obtain encryption parameter information. The number of hidden layer nodes and network weights of the encryption strategy model are optimized based on the simulated annealing algorithm during training, and the number of hidden layer nodes is positively correlated with the higher the bus attack score. The data encryption module is used to encrypt the data to be sent according to the encryption parameter information.

[0007] In a third aspect, embodiments of this application provide a bus encryption device based on simulated annealing optimization, comprising: a memory and one or more processors; The memory is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the bus encryption method based on simulated annealing optimization as described in the first aspect.

[0008] In a fourth aspect, embodiments of this application provide a storage medium for storing computer-executable instructions, which, when executed by a computer processor, are used to perform the bus encryption method based on simulated annealing optimization as described in the first aspect.

[0009] This application embodiment inputs bus network load information, bus attack score, and bus encryption delay information into a trained encryption strategy model. The encryption strategy model analyzes and processes the bus network load information, bus attack score, and bus encryption delay information to obtain encryption parameter information. The data to be transmitted is then encrypted based on the encryption parameter information. The number of hidden layer nodes and network weights of the encryption strategy model are optimized during training using a simulated annealing algorithm. The simulated annealing algorithm can effectively reduce the possibility of the encryption strategy model getting stuck in local optima. Furthermore, the number of hidden layer nodes is positively correlated with the bus attack score, which can effectively adapt to the encryption strength requirements under different network attack scenarios. The encryption parameter information is dynamically updated to improve the security of bus data transmission, effectively protect the security of data transmitted on the bus, and improve the encryption effect of bus data. Attached Figure Description

[0010] Figure 1 This is a flowchart of a bus encryption method based on simulated annealing optimization provided in an embodiment of this application; Figure 2 This is a schematic diagram of an encryption strategy model training process provided in an embodiment of this application; Figure 3 This is a schematic diagram of a bus encryption device based on simulated annealing optimization provided in an embodiment of this application; Figure 4 This is a schematic diagram of a bus encryption device based on simulated annealing optimization provided in an embodiment of this application. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but additional steps not included in the drawings may also be present. The above processes can correspond to methods, functions, procedures, subroutines, subroutines, etc.

[0012] The bus encryption method based on simulated annealing optimization provided in this application can be applied to the field of automotive electronic communication security to encrypt data in the controller area network. It aims to dynamically update encryption parameter information to improve the security of bus data transmission, ensure the security of data transmitted on the bus, improve the encryption effect of bus data, enhance the security and real-time performance of the vehicle network, increase the security coefficient of the bus in the automotive network, reduce data leakage and privacy violations, and protect the safety of drivers and passengers.

[0013] Existing Controller Area Networks (Controller Area Networks) serve as the standard for communication between various Electronic Control Units (ECUs) in vehicles, enabling real-time data transmission. However, they lack built-in security mechanisms, making them vulnerable to threats such as eavesdropping and replay attacks, and hindering effective security of bus-transmitted data. Traditional encryption algorithms (such as AES) are computationally complex and rely on fixed keys, making them insufficient for the low latency and high real-time performance requirements of Controller Area Network buses. While neural networks can dynamically adjust encryption strategies, their parameter optimization efficiency is low, making them unsuitable for dynamic network environments. Therefore, this application provides a bus encryption method based on simulated annealing optimization to address the technical problem of poor security and ineffective bus data encryption in existing bus-transmitted data systems.

[0014] Figure 1 A flowchart of a bus encryption method based on simulated annealing optimization provided in this application embodiment is given. The bus encryption method based on simulated annealing optimization provided in this application embodiment can be executed by a bus encryption device based on simulated annealing optimization. The bus encryption device based on simulated annealing optimization can be implemented by hardware and / or software and integrated into a bus encryption device based on simulated annealing optimization. The bus encryption device can use an STM32F407 microcontroller to execute the bus encryption method and configure the encryption strategy model in an independent security chip (such as HSM, Hardware Security Module).

[0015] The following description uses a bus encryption device optimized by simulated annealing to illustrate the implementation of a bus encryption method optimized by simulated annealing. (Reference) Figure 1 The bus encryption method based on simulated annealing optimization includes: S110: Obtain bus network load information, bus attack score, and bus encryption delay information.

[0016] For example, the bus network load information, bus attack score, and bus encryption delay information of the data bus are acquired. The bus network load information can be understood as the current network load rate of the bus. The bus attack score indicates the intensity of the network attack currently affecting the bus (e.g., DoS attacks, replay attacks, injection attacks, etc.), serving as a dynamic indicator to quantify the threat level currently faced by the controller area network bus. It identifies potential attack types by analyzing network traffic and behavior patterns in real time and converts the threat level into a numerical score, which is used by the encryption strategy model to dynamically adjust encryption parameters. The higher the intensity of the network attack, the higher the corresponding bus attack score. Optionally, different weights can be assigned according to different attack types, and the weights can be normalized into a scoring function to obtain the bus attack score. The bus encryption delay information can be understood as the time elapsed from the original CAN data frame (e.g., data to be transmitted) to the generation of encrypted data output.

[0017] S120: Input the bus network load information, bus attack score, and bus encryption delay information into the trained encryption strategy model, and analyze and process the bus network load information, bus attack score, and bus encryption delay information through the encryption strategy model to obtain encryption parameter information.

[0018] The trained encryption strategy model provided by this solution can be configured in a bus encryption device. As a data transmission device, it encrypts the data to be sent and then transmits the encrypted data to the receiving end via the bus. The number of hidden layer nodes and network weights in the encryption strategy model are optimized during training using a simulated annealing algorithm, and the number of hidden layer nodes is positively correlated with a higher bus attack score.

[0019] For example, the bus network load information, bus attack score, and bus encryption delay information obtained above are input into the trained encryption strategy model. The encryption strategy model analyzes and processes the bus network load information, bus attack score, and bus encryption delay information to obtain the corresponding encryption parameter information.

[0020] In one possible embodiment, such as Figure 2 The provided diagram illustrates a training process for an encryption strategy model. The training process for the encryption strategy model provided in this application includes: S101: Initialize the number of hidden layer nodes and network weights of the encryption strategy model.

[0021] S102: Based on the initial temperature, cooling rate, iteration number threshold, and preset energy function, simulated annealing optimization training is performed on the encryption strategy model to optimize the number of hidden layer nodes and network weights of the encryption strategy model.

[0022] For example, after building an initial encryption strategy model based on a preset neural network, the number of hidden layer nodes and network weights of the encryption strategy model are adjusted. The network weights, as internal weight parameters of the neural network, represent the connection strength between neurons and are used to calculate the mapping relationship from input data to output. For example, the encryption strategy model is initialized with 5 hidden layer nodes, and the network weights are randomly initialized within a preset weight range (e.g., [-0.5, 0.5]).

[0023] In one embodiment, after initializing the encryption strategy model, simulated annealing optimization training can be performed on the encryption strategy model using pre-collected training sample data based on the initial temperature (e.g., the initial temperature can be set to 1000), the cooling rate (e.g., the initial temperature can be set to 0.93), the iteration number threshold (e.g., the iteration number threshold can be set to 200), and a preset energy function.

[0024] During the training process of the encryption strategy model, the number of hidden layer nodes and network weights are dynamically optimized to enhance the model's ability to model complex attack characteristics, thereby improving the security strength of data encryption. Specifically, during training, the temperature decreases exponentially with the number of training iterations. The probability of accepting inferior solutions by the encryption strategy model can be calculated using the Metropolis criterion, effectively preventing the model from getting trapped in local optima. In the simulated annealing optimization training of the encryption strategy model, a preset energy function can be used as the objective function, which needs to be minimized. For example, if the currently determined preset energy function is greater than the previously determined preset energy function, the solution corresponding to the currently determined preset energy function can be accepted. The simulated annealing algorithm tends to explore the solution space extensively. When the currently determined preset energy function is less than or equal to the previously determined preset energy function, a worse solution is accepted with a certain acceptance probability. When the acceptance probability is greater than or equal to a preset probability threshold, the solution corresponding to the currently determined preset energy function can be accepted, and the simulated annealing algorithm tends to explore the solution space extensively. However, when the acceptance probability is less than the preset probability threshold, the solution corresponding to the currently determined preset energy function is rejected, and the simulated annealing algorithm tends to perform a local search in the vicinity of the current solution. This acceptance probability can be determined based on the difference between the currently determined preset energy function and the previously determined preset energy function, as well as the temperature corresponding to the current iteration process. For example, this probability can be expressed as: exp(-ΔE / T), where -ΔE is the difference between the current and previously determined preset energy functions, and T is the temperature.

[0025] This application uses simulated annealing to optimize the encryption strategy model by adjusting the initial temperature, cooling rate, iteration number threshold, and preset energy function. This optimizes the number of hidden layer nodes and network weights in the encryption strategy model, effectively preventing it from getting stuck in local optima. The encryption strategy model can effectively adapt to different network environments.

[0026] In one possible embodiment, cooling rates corresponding to different network scenarios can be pre-configured. Based on this, before performing simulated annealing optimization training on the encryption strategy model based on the initial temperature, cooling rate, iteration number threshold, and preset energy function, the network scenario can be determined, and the cooling rate can be determined according to the network scenario. Subsequently, simulated annealing optimization training can be performed on the encryption strategy model based on the determined cooling rate, initial temperature, iteration number threshold, and preset energy function.

[0027] The smaller the cooling rate, the faster the temperature decreases during simulated annealing optimization training of the encryption policy model, resulting in faster convergence. However, this may lead to getting trapped in local optima. Conversely, the larger the cooling rate, the slower the temperature decreases during simulated annealing optimization training, but the stronger the global search capability of the encryption policy model. This application effectively balances the training efficiency and global search capability of the encryption policy model under different network environments by determining the corresponding cooling rate based on different network scenarios.

[0028] Optionally, the network scenario can be a scenario with network attacks or a scenario without network attacks. Based on this, the method provided in this application for determining the cooling rate according to the network scenario can be: when the network scenario is a scenario without network attacks, the cooling rate is determined as a first cooling rate; when the network scenario is a scenario with network attacks, the cooling rate is determined as a second cooling rate, where the second cooling rate is less than the first cooling rate.

[0029] For example, when the network scenario is a non-network attack scenario, the cooling rate can be determined as a first cooling rate, while when the network scenario is a network attack scenario, the cooling rate can be determined as a second cooling rate, and the second cooling rate is less than the first cooling rate. For example, the value range of the first cooling rate can be [0.9, 0.95], for example, the first cooling rate can be set to 0.93, and the value range of the second cooling rate can be [0.8, 0.9], for example, the second cooling rate can be set to 0.85.

[0030] This application achieves a balance between training efficiency and global search capability of the encryption strategy model in scenarios without network attacks and scenarios with network attacks by setting the corresponding cooling rates as a first cooling rate and a second cooling rate, with the second cooling rate being less than the first cooling rate.

[0031] In one possible embodiment, before performing simulated annealing optimization training on the encryption strategy model based on the initial temperature, cooling rate, iteration number threshold, and preset energy function, the bus encryption method based on simulated annealing optimization provided in this application can also determine sample delay information and sample key entropy, perform weighted summation on the sample delay information and sample key entropy, and determine the weighted summation result as the preset energy function.

[0032] For example, an encryption strategy model is used to predict encryption parameters for training sample data, and the data is encrypted based on the predicted encryption parameters to determine sample delay information and sample key entropy. Sample delay information is understood as the time taken for sample data to travel from the original CAN data frame to the generated encrypted data output. Sample key entropy measures the uncertainty and randomness of the key stream output by the encryption strategy model; the higher the sample key entropy, the more difficult it is to guess the key, and the higher the data security. Assuming the encryption strategy model outputs a dynamic key stream (e.g., a 128-bit random number), ideally the key is completely random and uniformly distributed, and the entropy of the 128-bit key is 128 bits. However, in reality, the predicted key stream is not completely random and uniformly distributed, and the entropy of the 128-bit key will be less than 128 bits.

[0033] After determining the sample delay information and sample key entropy, a weighted summation can be performed on the sample delay information and sample key entropy based on preset weights, and the result of the weighted summation is determined as a preset energy function. Correspondingly, the encryption strategy model can be trained using simulated annealing with the aforementioned preset energy function, initial temperature, cooling rate, and iteration number threshold. This can effectively prevent the encryption strategy model from getting trapped in local optima and improve the encryption effect of bus data.

[0034] In one possible embodiment, the bus encryption method based on simulated annealing optimization provided in this application may normalize the sample delay information and sample key entropy before performing weighted summation. Accordingly, the weighted summation of the sample delay information and sample key entropy may be performed on the normalized sample delay information and sample key entropy.

[0035] For example, after determining the sample delay information and sample key entropy, the determined sample delay information and sample key entropy can be normalized, and then the normalized sample delay information and sample key entropy can be weighted and summed to obtain a preset energy function. For example, the sample key entropy can be normalized to a preset key entropy scoring standard. Assuming the preset key entropy scoring standard is a 5-point scale, the preset key entropy scoring standard is mapped to the entropy of a 128-bit key, with each point corresponding to an entropy value of 52.6. Assuming the entropy value corresponding to the sample key entropy is 107.52, then the normalized sample key entropy is (107.52 / 128) / 5 = 4.2 / *5.0. Optionally, the ratio of the sample delay information to a preset delay information benchmark can be used as the normalized sample delay information.

[0036] In one embodiment, the preset energy function provided in this application can be expressed as: Preset energy function = a * normalized sample delay information + b * normalized sample key entropy, where a and b are the sample delay weight and key entropy weight, respectively, for example, a = 0.6, b = 0.4. This application, by normalizing the sample delay information and sample key entropy, ensures the correct and stable calculation of the preset energy function, effectively avoiding the encryption strategy model from getting trapped in local optima and improving the bus data encryption effect.

[0037] S130: Encrypt the data to be sent according to the encryption parameter information. For example, a keystream is generated based on the determined encryption parameter information described above. This keystream is then used to encrypt the data to be sent, resulting in encrypted data, which is then transmitted to the receiving end via a bus. Optionally, the encryption parameter information provided in this application can be one or more combinations of key update period, target encryption algorithm, and target obfuscation strength. Different combinations of encryption parameter information are used to generate random keystreams to encrypt the data, achieving low-latency, high-strength data obfuscation. The key update period can be understood as the update period of the key for the encrypted data. Assuming a key update period of 5ms corresponds to a keystream generation rate of 200Mbps, it can effectively cover attack traffic.

[0038] Optionally, the target encryption algorithm can be one or more combinations of XTEA (X-Tiny Encryption Algorithm), ChaCha20, AES, DES (Data Encryption Standard), Cast5, Cast6, and hash encryption algorithms. The target obfuscation strength can be understood as the strength of data obfuscation, and can be an increasing strength from L1 to L5. For example, according to the key update cycle, a key stream is generated using a preset key generation algorithm or neural network (e.g., an encryption strategy model). After XOR obfuscating the data to be sent according to the key stream, the obfuscation result is encrypted using the target encryption algorithm to obtain encrypted data.

[0039] Optionally, an encryption strategy model can be configured at the receiving end. The receiving end can provide the encryption strategy model with bus network load information, bus attack score, and bus encryption delay information to obtain decryption parameter information corresponding to the encryption parameter information (the decryption parameter information can be consistent with the encryption parameter information). Based on the decryption parameter information, a key stream is generated. The encrypted data can be decrypted using the key stream and the target encryption algorithm to obtain the corresponding data to be sent. This application dynamically enhances the key generation capability, ensuring that the key stream generation rate is greater than the peak attack traffic, guaranteeing encryption real-time performance, and ensuring that the encryption strategy model can still process all data frames in real time under high-intensity DoS attacks, avoiding encryption delays or communication interruptions due to insufficient key resources.

[0040] As described above, by inputting bus network load information, bus attack scores, and bus encryption latency information into the trained encryption strategy model, the encryption strategy model analyzes and processes these information to obtain encryption parameters. The data to be transmitted is then encrypted based on these parameters. The number of hidden layer nodes and network weights in the encryption strategy model are optimized during training using a simulated annealing algorithm. Simulated annealing effectively reduces the likelihood of the encryption strategy model getting trapped in local optima. Furthermore, the number of hidden layer nodes is positively correlated with a higher bus attack score, effectively adapting to encryption strength requirements under different network attack scenarios. Dynamically updating the encryption parameters improves the security of bus data transmission, effectively ensuring the security of transmitted data and enhancing the overall encryption effect of bus data.

[0041] Figure 3 A schematic diagram of a bus encryption device based on simulated annealing optimization provided in an embodiment of this application is given. (Reference) Figure 3 The bus encryption device based on simulated annealing optimization includes an information acquisition module 31, a parameter determination module 32, and a data encryption module 33.

[0042] The information acquisition module 31 is used to acquire bus network load information, bus attack score, and bus encryption delay information. The parameter determination module 32 is used to input the bus network load information, bus attack score, and bus encryption delay information into the trained encryption strategy model, and to analyze and process the bus network load information, bus attack score, and bus encryption delay information through the encryption strategy model to obtain encryption parameter information. The number of hidden layer nodes and network weights of the encryption strategy model are optimized based on the simulated annealing algorithm during training, and the number of hidden layer nodes is positively correlated with the higher the bus attack score. The data encryption module 33 is used to encrypt the data to be sent according to the encryption parameter information.

[0043] As described above, by inputting bus network load information, bus attack scores, and bus encryption latency information into the trained encryption strategy model, the encryption strategy model analyzes and processes these information to obtain encryption parameters. The data to be transmitted is then encrypted based on these parameters. The number of hidden layer nodes and network weights in the encryption strategy model are optimized during training using a simulated annealing algorithm. Simulated annealing effectively reduces the likelihood of the encryption strategy model getting trapped in local optima. Furthermore, the number of hidden layer nodes is positively correlated with a higher bus attack score, effectively adapting to encryption strength requirements under different network attack scenarios. Dynamically updating the encryption parameters improves the security of bus data transmission, effectively ensuring the security of transmitted data and enhancing the overall encryption effect of bus data.

[0044] In one possible embodiment, the bus encryption device based on simulated annealing optimization further includes a model training module for training the encryption strategy model. The model training module trains the encryption strategy model by: Initialize the number of hidden layer nodes and network weights of the encryption strategy model; Simulated annealing optimization training is performed on the encryption strategy model based on the initial temperature, cooling rate, iteration number threshold, and preset energy function to optimize the number of hidden layer nodes and network weights of the encryption strategy model.

[0045] In one possible embodiment, before performing simulated annealing optimization training on the encryption strategy model based on the initial temperature, cooling rate, iteration number threshold, and preset energy function, the model training module further includes: Determine the network scenario and determine the cooling rate based on the network scenario.

[0046] In one possible embodiment, the model training module determines the cooling rate based on the network scenario, including: In a network scenario where there is no network attack, the cooling rate is determined as the first cooling rate. In the case of a network attack scenario, the cooling rate is determined to be the second cooling rate, which is less than the first cooling rate.

[0047] In one possible embodiment, before performing simulated annealing optimization training on the encryption strategy model based on the initial temperature, cooling rate, iteration number threshold, and preset energy function, the model training module further includes: Determine the sample delay information and sample key entropy, perform a weighted summation on the sample delay information and sample key entropy, and determine the weighted summation result as the preset energy function.

[0048] In one possible embodiment, the model training module further includes, before performing a weighted summation of the sample delay information and the sample key entropy: Normalize the sample delay information and sample key entropy; Accordingly, the model training module performs a weighted summation of the sample latency information and the sample key entropy, including: The normalized sample delay information and sample key entropy are weighted and summed.

[0049] In one possible embodiment, the encryption parameter information includes one or more combinations of key update cycle, target encryption algorithm, and target obfuscation strength.

[0050] It is worth noting that in the above embodiments of the bus encryption device based on simulated annealing optimization, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this application.

[0051] This application also provides a bus encryption device based on simulated annealing optimization, which can integrate the bus encryption device based on simulated annealing optimization provided in this application. Figure 4 This is a schematic diagram of a bus encryption device based on simulated annealing optimization provided in an embodiment of this application. (Reference) Figure 4 The bus encryption device based on simulated annealing optimization includes: an input device 43, an output device 44, a memory 42, and one or more processors 41; the memory 42 is used to store one or more programs; when one or more programs are executed by one or more processors 41, the one or more processors 41 implement the bus encryption method based on simulated annealing optimization as provided in the above embodiments. The input device 43, output device 44, memory 42, and processors 41 can be connected via a bus or other means. Figure 4 Taking the example of a connection between China and Israel via a bus.

[0052] The memory 42, as a computing device-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to the simulated annealing-optimized bus encryption method provided in any embodiment of this application (e.g., the information acquisition module 31, parameter determination module 32, and data encryption module 33 in the simulated annealing-optimized bus encryption device). The memory 42 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the device, etc. Furthermore, the memory 42 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 42 may further include memory remotely located relative to the processor 41, and these remote memories can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0053] Input device 43 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. Output device 44 may include display devices such as a display screen.

[0054] The processor 41 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 42, thereby implementing the bus encryption method based on simulated annealing optimization described above.

[0055] The bus encryption device, apparatus, and computer based on simulated annealing optimization provided above can be used to execute the bus encryption method based on simulated annealing optimization provided in any of the above embodiments, and have corresponding functions and beneficial effects.

[0056] This application embodiment also provides a storage medium for storing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to execute the bus encryption method based on simulated annealing optimization provided in the above embodiment. The bus encryption method based on simulated annealing optimization includes: acquiring bus network load information, bus attack score, and bus encryption delay information; inputting the bus network load information, bus attack score, and bus encryption delay information into a trained encryption strategy model; analyzing and processing the bus network load information, bus attack score, and bus encryption delay information through the encryption strategy model to obtain encryption parameter information, wherein the number of hidden layer nodes and network weights of the encryption strategy model are optimized based on the simulated annealing algorithm during training, and the number of hidden layer nodes is positively correlated with a higher bus attack score; and encrypting the data to be sent according to the encryption parameter information.

[0057] Storage medium – any type of memory device or storage device. The term “storage medium” is intended to include: mounting media, such as CD-ROMs, floppy disks, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disks or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. Furthermore, storage media may reside in a first computer system in which a program is executed, or may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media that may reside in different locations (e.g., in different computer systems connected via a network). Storage media may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.

[0058] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the bus encryption method based on simulated annealing optimization provided above, but can also perform related operations in the bus encryption method based on simulated annealing optimization provided in any embodiment of this application.

[0059] The bus encryption device, equipment, and storage medium based on simulated annealing optimization provided in the above embodiments can execute the bus encryption method based on simulated annealing optimization provided in any embodiment of this application. For technical details not described in detail in the above embodiments, please refer to the bus encryption method based on simulated annealing optimization provided in any embodiment of this application.

[0060] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments provided herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. A bus encryption method based on simulated annealing optimization, characterized in that, include: Obtain bus network load information, bus attack score, and bus encryption latency information; The bus network load information, the bus attack score, and the bus encryption delay information are input into the trained encryption strategy model. The encryption strategy model analyzes and processes the bus network load information, the bus attack score, and the bus encryption delay information to obtain encryption parameter information. The number of hidden layer nodes and network weights of the encryption strategy model are optimized based on the simulated annealing algorithm during training, and the number of hidden layer nodes is positively correlated with the bus attack score. The data to be sent is encrypted according to the encryption parameter information; The training process of the encryption strategy model includes: initializing the number of hidden layer nodes and network weights of the encryption strategy model; determining the network scenario and the cooling rate based on the network scenario; and performing simulated annealing optimization training on the encryption strategy model based on the initial temperature, cooling rate, iteration number threshold, and preset energy function to optimize the number of hidden layer nodes and network weights of the encryption strategy model.

2. The bus encryption method based on simulated annealing optimization according to claim 1, characterized in that, Determining the cooling rate based on the network scenario includes: In the case where the network scenario is a scenario without network attacks, the cooling rate is determined as the first cooling rate; In the case where the network scenario is a network attack scenario, the cooling rate is determined to be a second cooling rate, which is less than the first cooling rate.

3. The bus encryption method based on simulated annealing optimization according to claim 1, characterized in that, Before performing simulated annealing optimization training on the encryption strategy model based on the initial temperature, cooling rate, iteration number threshold, and preset energy function, the method further includes: Determine the sample delay information and the sample key entropy, perform a weighted summation on the sample delay information and the sample key entropy, and determine the weighted summation result as a preset energy function.

4. The bus encryption method based on simulated annealing optimization according to claim 3, characterized in that, Before performing the weighted summation process on the sample delay information and the sample key entropy, the method further includes: The sample delay information and the sample key entropy are normalized. Accordingly, the weighted summation of the sample delay information and the sample key entropy includes: The normalized sample delay information and the sample key entropy are then subjected to a weighted summation.

5. The bus encryption method based on simulated annealing optimization according to claim 1, characterized in that, The encryption parameter information includes one or more combinations of key update cycle, target encryption algorithm, and target obfuscation strength.

6. A bus encryption device based on simulated annealing optimization, characterized in that, It includes an information acquisition module, a parameter determination module, and a data encryption module, among which: The information acquisition module is used to acquire bus network load information, bus attack score, and bus encryption delay information; The parameter determination module is used to input the bus network load information, the bus attack score, and the bus encryption delay information into the trained encryption strategy model. The encryption strategy model analyzes and processes the bus network load information, the bus attack score, and the bus encryption delay information to obtain encryption parameter information. The number of hidden layer nodes and network weights of the encryption strategy model are optimized based on the simulated annealing algorithm during training, and the number of hidden layer nodes is positively correlated with the bus attack score. The data encryption module is used to encrypt the data to be sent according to the encryption parameter information; It also includes a model training module for training the encryption strategy model. The model training module trains the encryption strategy model by: initializing the number of hidden layer nodes and network weights of the encryption strategy model; determining the network scenario and determining the cooling rate based on the network scenario; and performing simulated annealing optimization training on the encryption strategy model based on the initial temperature, cooling rate, iteration number threshold and preset energy function to optimize the number of hidden layer nodes and network weights of the encryption strategy model.

7. A bus encryption device based on simulated annealing optimization, characterized in that, include: Memory and one or more processors; The memory is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the bus encryption method based on simulated annealing optimization as described in any one of claims 1-5.

8. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the bus encryption method based on simulated annealing optimization as described in any one of claims 1-5.

Images