Chip system trust calculation method, security protection method and device

Abstract

The present invention discloses a method for calculating the trust of a core-grain system, a security protection method and a device, wherein the trust calculation method includes: collecting classification information and historical security events of all core-grain modules integrated on an intermediary layer through a security protection module; classifying the core-grain modules using a clustering algorithm according to the classification information; selecting the most reliable core-grain module in each category after classification according to historical security events; collecting the current performance indicators of other core-grain modules in the same category through the most reliable core-grain module; and calculating the trust according to the current performance indicators. The core-grain system security protection method is based on the core-grain system trust calculation method. The core-grain modules with a trust higher than a threshold value create a state snapshot, the core-grain modules with a trust lower than the threshold value are suspended, and are replaced with other core-grain modules of the same type that are higher than the threshold value. The deactivated core-grain modules are restored to their states according to the historical state snapshots, and a trust calculation is requested to be performed again. This method improves the security of the core-grain system.

Description

Technical Field

[0001] The present application relates to the field of semiconductor technology, and in particular to a chip system trust calculation method, a security protection method and a device. Background Art

[0002] With the continuous development of semiconductor technology, there are more advanced methods in the field of chip design and manufacturing. The chip module system based on 2.5D packaging combines modular chip modules with high-density 2.5D packaging technology. Such a system can not only improve the integration of physical space, but also realize the reuse and expansion of chip functions.

[0003] However, the modular and highly integrated characteristics of the chiplet module system also bring new security issues. First, since each chiplet module is an independent module, they may come from different supply chains. Once one of the chiplet modules is integrated with data eavesdropping and tampering functions, it may affect the security and stability of the entire chip system; secondly, the chiplet modules need to communicate with each other according to the UCIe protocol to exchange data and control signals, so communication security must also be guaranteed; in addition, due to the ultra-large-scale integration of the chiplet module system, it is necessary to reasonably allocate global security protection tasks. Traditional distributed security protection methods can no longer adapt to this complex and highly integrated chiplet module system. For this reason, a chiplet system trust calculation method, security protection method and device are proposed. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a core particle system trust calculation method, a security protection method and a device to solve the technical problems existing in the related art regarding the security of core particle modules and interconnections between modules and the allocation of system security protection tasks.

[0005] According to a first aspect of an embodiment of the present application, a method for calculating the trust of a core particle system is provided, wherein the core particle system includes a security protection module integrated on an interposer and core particle modules with different functions, and all the core particle modules are interconnected. The method includes:

[0006] The security protection module collects the classification information and historical security events of all core modules integrated on the interposer layer;

[0007] The security protection module classifies the core particle modules using a clustering algorithm according to the classification information;

[0008] The security protection module selects the most reliable core module in each category after classification according to the historical security events;

[0009] The most reliable core-grain module collects the current performance indicators of other core-grain modules in this category;

[0010] The most reliable core particle module calculates the trustworthiness according to the current performance indicator.

[0011] According to a second aspect of an embodiment of the present application, a device for calculating the trustworthiness of a core particle system is provided, wherein the core particle system includes a security protection module integrated on an interposer layer and core particle modules with different functions, and all the core particle modules are interconnected. The device includes:

[0012] A first collection module, used for the security protection module to collect classification information and historical security events of all core-grain modules integrated on the interposer layer;

[0013] A classification module, used for the security protection module to classify the core particle modules using a clustering algorithm according to the classification information;

[0014] A selection module, used for the security protection module to select the most reliable core module in each category after classification according to the historical security events;

[0015] The second collection module is used for the most reliable core-grain module to collect the current performance indicators of other core-grain modules in the same category;

[0016] A calculation module is used for the most reliable core particle module to calculate the trustworthiness according to the current performance indicator.

[0017] According to a third aspect of an embodiment of the present application, a method for protecting the security of a core particle system is provided, wherein the core particle system includes a security protection module integrated on an interposer and core particle modules with different functions, and all the core particle modules are interconnected. The method includes:

[0018] The security protection module collects the classification information and historical security events of all core modules integrated on the interposer layer;

[0019] The security protection module classifies the core particle modules using a clustering algorithm according to the classification information;

[0020] The security protection module selects the most reliable core module in each category after classification according to the historical security events;

[0021] The most reliable core-grain module collects the current performance indicators of other core-grain modules in this category;

[0022] The most reliable core particle module calculates the trustworthiness according to the current performance indicator;

[0023] The core-grain modules with trust higher than the threshold create state snapshots, the core-grain modules with trust lower than the threshold are suspended, the most reliable core-grain module notifies other core-grain modules with trust higher than the threshold to replace the core-grain modules with trust lower than the threshold, and the core-grain modules with trust lower than the threshold restore the status of the deactivated core-grain modules according to the historical state snapshots and request to recalculate the trust.

[0024] According to a fourth aspect of an embodiment of the present application, a chiplet system security protection device is provided, wherein the chiplet system includes a security protection module integrated on an interposer and chiplet modules with different functions, and all the chiplet modules are interconnected. The device includes:

[0025] A first collection module, used for the security protection module to collect classification information and historical security events of all core-grain modules integrated on the interposer layer;

[0026] A classification module, used for the security protection module to classify the core particle modules using a clustering algorithm according to the classification information;

[0027] A selection module, used for the security protection module to select the most reliable core module in each category after classification according to the historical security events;

[0028] The second collection module is used for the most reliable core-grain module to collect the current performance indicators of other core-grain modules in the same category;

[0029] A calculation module, used for the most reliable core particle module to calculate the trustworthiness according to the current performance indicator;

[0030] The security protection module is used to create a state snapshot for the core-grain module with a trust level higher than the threshold, suspend the use of the core-grain module below the threshold, and the most reliable core-grain module notifies other core-grain modules with a trust level higher than the threshold to replace the core-grain module below the threshold. The core-grain module below the threshold restores the status according to the historical state snapshot and requests to recalculate the trust level.

[0031] According to a fifth aspect of an embodiment of the present application, there is provided an electronic device, including:

[0032] one or more processors;

[0033] A memory for storing one or more programs;

[0034] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in the first aspect or the third aspect.

[0035] According to a sixth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in the first aspect or the third aspect are implemented.

[0036] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0037] In the present invention, the security protection module serves as the security core of the system and is responsible for collecting classification information and historical security event data of all core-grain modules integrated on the intermediary layer. By applying a clustering algorithm, the security protection module can classify these core-grain modules and identify the most reliable core-grain module in each category. The most reliable core-grain module is further responsible for collecting the current performance indicators of other core-grain modules in the same category and calculating their trust values. This can not only ensure the global security control of the core-grain system, but also ensure the security of real-time communication. At the same time, assigning the real-time monitoring task to each class center for execution also reduces the amount of calculation of the Guard, which is conducive to the large-scale integration of the core-grain system.

[0038] In addition, the deactivation and replacement method of core module based on trust value enables the system to respond quickly and in real time to security issues that arise; the snapshot mechanism and the method of redeeming trust value can reduce the waste of hardware resources; and the periodic update of the model enables the system to update security policies in a timely manner and respond to new security threats.

[0039] In summary, the security protection method proposed in the present invention enhances the robustness and adaptability of the entire system.

[0040] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0042] Figure 1 is a schematic diagram of a core particle system according to an exemplary embodiment.

[0043] Figure 2 The figure is a flow chart of a method for calculating the trustworthiness of a core particle system according to an exemplary embodiment.

[0044] Figure 3 It is a schematic structural diagram of a core particle system trust calculation device according to an exemplary embodiment.

[0045] Figure 4 The figure is a flow chart of a core particle system security protection method according to an exemplary embodiment.

[0046] Figure 5 It is a schematic structural diagram of a core particle system safety protection device according to an exemplary embodiment.

[0047] Figure 6 The diagram is a schematic structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0048] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0049] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0050] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0051] refer to Figure 1 , is a schematic diagram of a chiplet system according to an exemplary embodiment. The chiplet system includes a security protection module Guard integrated on an intermediate layer and chiplet modules with different functions. All chiplet modules are interconnected according to the UCIe standard, and they can record their own historical security events.

[0052] The security protection module Guard here is also a core module, just like other core modules.

[0053] The security protection module Guard may include:

[0054] Performance monitoring module, used to detect the current performance indicators of other core particle modules;

[0055] A data processing module is used to standardize the collected classified information data for comparison and analysis;

[0056] Historical data recording module, used to store historical security events and abnormal behaviors;

[0057] Data analysis module for analyzing historical security events, identifying trends and patterns, and generating alerts or reports.

[0058] The position of the safety protection module is recorded as coordinate (0, 0).

[0059] Figure 2 is a flow chart of a method for calculating the trustworthiness of a core particle system according to an exemplary embodiment. Figure 2 As shown, the method may include the following steps:

[0060] S1: The security protection module collects the classification information and historical security events of all core modules integrated on the interposer;

[0061] The classification information here may include: packaging location, function type, manufacturing process and performance characteristics. The details are as follows:

[0062] Package position: The position on the interposer, with the horizontal and vertical coordinates recorded as x and y respectively

[0063] Function type: records the function type of each chip (such as processor is recorded as 0, storage is 1, IO interface is 2).

[0064] Manufacturing process node: Query the process data and material specifications provided by the chip manufacturer, and record the manufacturing process node of each chip (such as 7nm, 5nm).

[0065] Performance characteristics: including standard performance indicators such as clock frequency and bandwidth.

[0066] The historical security events here may include:

[0067] 1) Access Violation, including:

[0068] Illegal login attempts: monitor and record every failed login attempt, and record detailed information of each login attempt, including user ID, attempt time, source IP address and reason for failure;

[0069] Privilege escalation: Record every privilege change event, including the operator, privilege changed, and time. Screen unauthorized privilege change records, including operations that add or delete user privileges;

[0070] Abnormal access patterns: Establish a normal access pattern baseline, monitor access to sensitive resources, and detect access frequency

[0071] Unusual or anomalous access patterns, such as frequent access to sensitive data by a specific user or IP address.

[0072] 2) Communication Error: Periodically send test packets or requests to confirm the health of the link. If no confirmation or packet is received, it may indicate a problem with the link.

[0073] 3) Malware Activity, including:

[0074] Malicious activity logging: Install and configure anti-virus software and malware detection tools to log every attempt to execute malicious code, including file, process, and network activity. Regularly update virus definition libraries to ensure that they can detect the latest malware;

[0075] Abnormal file operations: Monitor abnormal file operations in the file system, including abnormal creation, modification, or deletion operations. Record all file operation logs and analyze file access patterns to identify abnormal activities;

[0076] System resource anomalies, malware occupying abnormal resources or initiating abnormal network activities, monitor system resource usage, including CPU, memory, and network bandwidth. Detect and record abnormal resource usage, such as sudden resource consumption surges, and analyze network activities to identify malicious traffic.

[0077] 4) Data Anomaly, including:

[0078] Whether the data has been tampered with or damaged, use data integrity detection tools to generate and verify the checksum or hash value of the data. Check data integrity regularly to detect tampering or damage;

[0079] Abnormal read and write: monitor the read and write operations of the database, record the frequency and amount of read and write operations, and set thresholds to detect operations that exceed the normal range;

[0080] Data traffic anomalies, monitor data traffic patterns, and detect sudden traffic surges or decreases.

[0081] The security protection module collects the classification information and historical security events of all core modules integrated on the interposer layer. The classification information is used to classify cores, and the historical security events are used to select the most reliable cores. Collecting classification information helps to accurately allocate cores, thereby achieving classification management; collecting historical security event information is conducive to ensuring system security.

[0082] S2: the security protection module classifies the core particle modules using a clustering algorithm according to the classification information;

[0083] Specifically, the K-means model is used to classify the core particle modules into K categories. The specific process includes:

[0084] 1. Data processing:

[0085] Normalize each type of data, taking the horizontal axis value as an example:

[0086] ;

[0087] in is the normalized data, is the original data.

[0088] Initialize y, Functiontype, Processnode, Clockfrequency, and Bandwidth in the same way.

[0089] For each core particle, the normalized classification information is recorded as:

[0090] C h iplet i =[ x i , y i , Functiontype i , Processnode i , Clockfrequency i , Bandwidt h i ] ;

[0091] The distances described below are calculated as follows (in and distance as an example):

[0092] ;

[0093] 2. Determine the k value:

[0094] There are n core particles in the system, which determines how many classes the data should be divided into, that is, the number of classes k;

[0095] Initialize the cluster center: randomly select k core particles as the initial cluster centers. These cluster centers will be used to define the initial position of the cluster.

[0096] 3. Initialize the class center:

[0097] 3.1) Randomly select the first class center:

[0098] Randomly select a core particle as the first class center .

[0099] 3.2) Select the remaining class centers:

[0100] For each unselected core particle, calculate its distance to the nearest selected cluster center ;

[0101] ;

[0102] Select a core particle as the next cluster center so that the square value of its distance to the nearest cluster center is maximized, that is, .

[0103] Repeat the step of selecting class centers until k class centers are selected, which will be used to define the initial positions of the classes.

[0104] 4. Assign data points:

[0105] Calculate the distance: For each , calculate it to all k cluster centers The Euclidean distance.

[0106] ;

[0107] Assign classes: Assign each core particle to the class center closest to it , thus forming a class, namely:

[0108] ;

[0109] in, express The class classification results.

[0110] 5. Update Center:

[0111] Calculate the new class center: For each class , recalculate the center of this class, that is, all the centers assigned to this class The core particle average:

[0112] ;

[0113] in, Is currently in the class The set of all core particles, Is a class The number of core particles.

[0114] 6. Iteration:

[0115] Check convergence conditions: Repeat the allocation phase and the update phase until the convergence conditions are met.

[0116] Convergence conditions include: the change in the class center is less than a preset threshold (i.e., the change in the class center is very small) or the class assignment of the core particles has not changed (i.e., the class assignment of each data point remains unchanged).

[0117] 7. Output results:

[0118] Final class center: When the algorithm converges, the final class center is output .

[0119] Class assignment results: Output the final class assignment for each core particle .

[0120] By grouping core modules with similar functions and performance into one category, it can be ensured that the system operates in the optimal configuration and these modules can be replaced in a timely manner when safety issues arise, thereby improving the overall performance and stability of the system.

[0121] S3: The security protection module selects the most reliable core module in each category after classification according to the historical security events;

[0122] The security protection module calculates the total number of historical security events for each core module using the following formula:

[0123] Total number of historical security events = number of access violations + number of communication anomalies + number of malware activities + number of data anomalies;

[0124] The module with the least number of historical safety tests among its peers is selected as the most reliable core module.

[0125] The most reliable chiplet modules can be effectively selected based on the number of historical security events. These selected chiplet modules will be used to monitor other chiplets in real time, ensuring the security of real-time communication and reducing the amount of Guard calculations, which is conducive to the large-scale integration of chiplet systems.

[0126] S4: The most reliable core-grain module collects the current performance indicators of other core-grain modules in this category;

[0127] The current performance indicators include: processor utilization, current remaining memory, maximum memory, network delay, packet loss rate, current temperature, maximum available temperature, data read and write rate, and maximum read and write rate.

[0128] Processor Utilization: Displays the current workload of the processor.

[0129] Current remaining memory: The amount of memory that is not being used by the system.

[0130] Maximum Memory: The total memory capacity available to the system.

[0131] Network latency: The time it takes for data to travel from source to destination.

[0132] Packet loss rate: the proportion of data packets lost during network transmission.

[0133] Current temperature: The current operating temperature of the device.

[0134] Maximum usable temperature: The maximum temperature that the device can withstand.

[0135] Data read and write rate: the speed of data transmission.

[0136] Maximum read and write speed: The highest read and write speed supported by the device.

[0137] By collecting the performance indicators of other core modules through the most reliable core module, comprehensive and accurate system performance data can be provided, which helps to monitor in real time, prevent failures, and improve system reliability.

[0138] S5: The most reliable core particle module calculates the trustworthiness according to the current performance indicator;

[0139] After processing the above data, the trust is calculated according to the formula:

[0140]

[0141] in, is the weight.

[0142] The design of calculating trust based on real-time performance indicators enables the system to evaluate the performance of each module in real time, allowing the system to respond quickly to dynamic changes and potential problems.

[0143] It can be seen from the above embodiments that the core grain trust calculation method of the present application classifies the core grain modules through a clustering algorithm and identifies the most reliable module in each category, which can effectively optimize the trust calculation and system security. The most reliable module is responsible for collecting the performance indicators of other modules of the same type and calculating the trust value, which not only improves the accuracy of data collection, but also ensures the system's global security control of the core grain module. In addition, assigning real-time monitoring tasks to each class center can reduce the computing burden of the security module Guard, help achieve large-scale integration of the system, and improve the security of real-time communications.

[0144] Corresponding to the aforementioned embodiment of the method for calculating the trustworthiness of a core-grain system, the present application also provides an embodiment of a device for calculating the trustworthiness of a core-grain system.

[0145] Figure 3 is a block diagram of a device for calculating the trustworthiness of a core particle system according to an exemplary embodiment. Figure 3 The chiplet system includes a security protection module integrated on the interposer and chiplet modules with different functions. All the chiplet modules are interconnected according to the UCIe standard. The device includes:

[0146] The first collection module 1 is used for the security protection module to collect the classification information and historical security events of all the core modules integrated on the interposer layer;

[0147] Classification module 2, used for the security protection module to classify the core particle modules using a clustering algorithm according to the classification information;

[0148] Selection module 3, used for the security protection module to select the most reliable core module in each category after classification according to the historical security events;

[0149] The second collection module 4 is used for the most reliable core-grain module to collect the current performance indicators of other core-grain modules in the same category;

[0150] The calculation module 5 is used for the most reliable core particle module to calculate the trustworthiness according to the current performance index.

[0151] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0152] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0153] Embodiment 2:

[0154] Figure 4 is a flow chart of a core particle system security protection method according to an exemplary embodiment. Figure 4 As shown, the core particle system includes a security protection module integrated on the interposer and core particle modules with different functions, and all the core particle modules are interconnected according to the UCIe standard. The method may include the following steps:

[0155] S1: The security protection module collects the classification information and historical security events of all core modules integrated on the interposer;

[0156] S2: the security protection module classifies the core particle modules using a clustering algorithm according to the classification information;

[0157] S3: The security protection module selects the most reliable core module in each category after classification according to the historical security events;

[0158] S4: The most reliable core-grain module collects the current performance indicators of other core-grain modules in this category;

[0159] S5: The most reliable core particle module calculates the trustworthiness according to the current performance indicator;

[0160] S6: The core-grain modules with trust higher than the threshold create state snapshots, the core-grain modules with trust lower than the threshold are suspended, the most reliable core-grain module notifies other core-grain modules with trust higher than the threshold to replace the core-grain modules with trust lower than the threshold, the core-grain modules with trust lower than the threshold restore the status according to the historical state snapshots and request to recalculate the trust.

[0161] The above S1-S5 refer to Example 1 and are not elaborated here.

[0162] For S6, the state snapshot includes: configuration data, performance indicators, security logs, operating conditions, software status, error logs, and trust indicators, so as to trace back to the normal state when a failure occurs next time, where:

[0163] Configuration data: The configuration settings and parameters of the chipset at the time of the snapshot.

[0164] Performance Metrics: Historical performance data for the chipset, such as processor utilization, memory usage, and data transfer rates.

[0165] Security logs: Records of security events such as access violations, communication anomalies, and malware activity.

[0166] Operating Conditions: Chipset operating condition information, including temperature and power consumption.

[0167] Software Status: The status of the software and firmware running on the chipset, including applied updates or patches.

[0168] Error log: records any errors or exceptions.

[0169] Trust indicators: historical trust assessment results and related assessment or certification information.

[0170] In one embodiment, a protection strategy is formed based on trust:

[0171] The most reliable core module broadcasts the calculated trust to other core modules in the same class.

[0172] If a core module disagrees with the trust test results, it can apply for arbitration.

[0173] After applying for arbitration, the reliable chip module will re-evaluate its trustworthiness.

[0174] If a core module is evaluated more than three times, it enters the public evaluation stage.

[0175] In the crowd evaluation, all coregear modules in the class evaluate the problematic coregear module, and the average trust is taken as the final decision.

[0176] In addition, the security protection module retrains the K-means model in each cycle to adapt to the changes in the system.

[0177] The trust-based core module deactivation and replacement method can timely identify and deactivate modules with security issues or performance degradation to prevent the spread of problems; through the snapshot mechanism, the system can save the performance and trust value status of the module, allowing it to be restored to a safe state when needed, and the trust value redemption method can re-evaluate and restore the trust status of the module. The periodic update of the model enables the system to update security policies in a timely manner to respond to new security threats.

[0178] It can be seen from the above embodiments that the module management and dynamic adjustment method based on trust value in the present application not only improves the system's response speed to security issues, but also optimizes resource utilization efficiency, providing effective guarantee for large-scale integration and long-term stable operation of the system.

[0179] Corresponding to the aforementioned embodiment of the chip system security protection method, the present application also provides an embodiment of a chip system security protection device.

[0180] Figure 5 FIG. 1 is a block diagram of a chip system security protection device according to an exemplary embodiment. Figure 5 The chiplet system includes a security protection module integrated on the interposer and chiplet modules with different functions. All the chiplet modules are interconnected according to the UCIe standard. The device includes:

[0181] The first collection module 1 is used for the security protection module to collect the classification information and historical security events of all the core modules integrated on the interposer layer;

[0182] Classification module 2, used for the security protection module to classify the core particle modules using a clustering algorithm according to the classification information;

[0183] Selection module 3, used for the security protection module to select the most reliable core module in each category after classification according to the historical security events;

[0184] The second collection module 4 is used for the most reliable core-grain module to collect the current performance indicators of other core-grain modules in the same category;

[0185] The calculation module 5 is used for the most reliable core particle module to calculate the trustworthiness according to the current performance index.

[0186] Security protection module 6 is used to create a state snapshot for the core-grain module whose trust is higher than the threshold, suspend the use of the core-grain module whose trust is lower than the threshold, and the most reliable core-grain module notifies other core-grain modules whose trust is higher than the threshold to replace the core-grain modules whose trust is lower than the threshold. The core-grain modules whose trust is lower than the threshold restore the status according to the historical state snapshot and request to recalculate the trust.

[0187] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0188] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0189] Embodiment 3:

[0190] Accordingly, the present application also provides an electronic device, comprising: one or more processors; a memory for storing 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 above-mentioned core particle system trust calculation method or core particle system security protection method. Figure 6 As shown, it is a hardware structure diagram of a chiplet system trust calculation device or a chiplet system security protection device provided by an embodiment of the present invention, in which any device with data processing capability is located, except Figure 6 In addition to the processor, memory and network interface shown, any device with data processing capabilities in which the apparatus in the embodiments is located may also include other hardware, generally based on the actual functions of the device with data processing capabilities, which will not be described in detail.

[0191] Accordingly, the present application also provides a computer-readable storage medium on which computer instructions are stored, and when the instructions are executed by the processor, the core grain system trust calculation method or the core grain system security protection method as described above is implemented. The computer-readable storage medium can be an internal storage unit of any device with data processing capabilities described in any of the aforementioned embodiments, such as a hard disk or a memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), an SD card, a flash card (Flash Card), etc. equipped on the device. Furthermore, the computer-readable storage medium can also include both an internal storage unit and an external storage device of any device with data processing capabilities. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capabilities, and can also be used to temporarily store data that has been output or is to be output.

[0192] Those skilled in the art will readily appreciate other embodiments of the present application after considering the description and practicing the contents disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The description and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0193] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for calculating the trustworthiness of a core particle system, characterized in that: The core particle system includes a security protection module integrated on an interposer layer and core particle modules with different functions, and all the core particle modules are interconnected. The method includes: The security protection module collects the classification information and historical security events of all core modules integrated on the interposer layer; The security protection module classifies the core particle modules using a clustering algorithm according to the classification information; The security protection module selects the most reliable core module in each category after classification according to the historical security events; The most reliable core-grain module collects the current performance indicators of other core-grain modules in this category; The most reliable core particle module calculates the trustworthiness according to the current performance indicator; The step of calculating the trust level according to the current performance indicator includes: The trust is calculated by the following formula; ； in, is the weight.

2. A method for calculating the trustworthiness of a core particle system according to claim 1, characterized in that: The classification information includes: packaging location, functional type, manufacturing process and performance characteristics.

3. A method for calculating the trustworthiness of a core particle system according to claim 1, characterized in that: The most reliable core module in each category after classification is selected based on the historical security events, including: The core module with the least number of historical security events among its peers is selected as the most reliable core module.

4. A method for calculating the trustworthiness of a core particle system according to claim 1, characterized in that: The historical security events include: access violations, communication anomalies, malware activities and data anomalies.

5. A method for calculating the trustworthiness of a core particle system according to claim 1, characterized in that: The current performance indicators include: processor utilization, current remaining memory, maximum memory, network delay, packet loss rate, current temperature, maximum available temperature, data read and write rate, and maximum read and write rate.

6. A chiplet system trust calculation device, characterized in that: The chiplet system includes a security protection module integrated on the interposer and chiplet modules with different functions, and all the chiplet modules are interconnected. The device includes: A first collection module, used for the security protection module to collect classification information and historical security events of all core-grain modules integrated on the interposer layer; A classification module, used for the security protection module to classify the core particle modules using a clustering algorithm according to the classification information; A selection module, used for the security protection module to select the most reliable core module in each category after classification according to the historical security events; The second collection module is used for the most reliable core-grain module to collect the current performance indicators of other core-grain modules in the same category; A calculation module, used for the most reliable core particle module to calculate the trustworthiness according to the current performance indicator; The step of calculating the trust level according to the current performance indicator includes: The trust is calculated by the following formula; ； in, is the weight.

7. A chip system security protection method, characterized in that: The core particle system includes a security protection module integrated on an interposer layer and core particle modules with different functions, and all the core particle modules are interconnected. The method includes: The security protection module collects the classification information and historical security events of all core modules integrated on the interposer layer; The security protection module classifies the core particle modules using a clustering algorithm according to the classification information; The security protection module selects the most reliable core module in each category after classification according to the historical security events; The most reliable core-grain module collects the current performance indicators of other core-grain modules in this category; The most reliable core particle module calculates the trustworthiness according to the current performance indicator; The core-grain modules with a trust level higher than the threshold create a state snapshot, and the core-grain modules with a trust level lower than the threshold are suspended. The most reliable core-grain module notifies other core-grain modules with a trust level higher than the threshold to replace the core-grain modules with a trust level lower than the threshold. The core-grain modules with a trust level lower than the threshold restore their status based on the historical state snapshot and request a recalculation of the trust level. The step of calculating the trust level according to the current performance indicator includes: The trust is calculated by the following formula; ； in, is the weight.

8. A chip system security protection method according to claim 7, characterized in that: The status snapshot includes: configuration data, performance indicators, security logs, operating conditions, software status, error logs, and trust indicators.

9. A core particle system safety protection device, characterized in that: The chiplet system includes a security protection module integrated on the interposer and chiplet modules with different functions, and all the chiplet modules are interconnected. The device includes: A first collection module, used for the security protection module to collect classification information and historical security events of all core-grain modules integrated on the interposer layer; A classification module, used for the security protection module to classify the core particle modules using a clustering algorithm according to the classification information; A selection module, used for the security protection module to select the most reliable core module in each category after classification according to the historical security events; The second collection module is used for the most reliable core-grain module to collect the current performance indicators of other core-grain modules in the same category; A calculation module, used for the most reliable core particle module to calculate the trustworthiness according to the current performance indicator; The security protection module is used to create a state snapshot for the core-grain modules with a trust level higher than the threshold, suspend the use of the core-grain modules with a trust level lower than the threshold, and notify other core-grain modules with a trust level higher than the threshold to replace the core-grain modules with a trust level lower than the threshold. The core-grain modules with a trust level lower than the threshold restore their status according to the historical state snapshot and request a recalculation of the trust level. The step of calculating the trust level according to the current performance indicator includes: The trust is calculated by the following formula; ； in, is the weight.

10. An electronic device, characterized in that: include: one or more processors; A memory for storing 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 method according to any one of claims 1-5, 7, and 8.

11. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by the processor, the steps of the method as described in any one of claims 1-5, 7, and 8 are implemented.

Images