Anti-attack method and system for improving security of intelligent terminal

By using a kernel-level behavior monitoring engine to analyze smart terminal processes and generate threat graphs, the solution effectively addresses zero-day vulnerabilities with real-time attack detection and mitigation, ensuring continuous service availability.

CN120316770AActive Publication Date: 2025-07-15SHENZHEN TOPWISE COMM CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202510811443.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-18
Publication Date
2025-07-15
Estimated Expiration
2045-06-18

AI Technical Summary

Technical Problem

Traditional smart terminal security solutions lack effective interception methods when dealing with zero-day exploitation, making it difficult to adapt to dynamic attack scenarios, resulting in a lack of timely repair of vulnerabilities when exploited, affecting service continuity.

Method used

Build a behavior monitoring engine in the kernel layer of the smart terminal, collect behavioral data flows of parallel task processes, extract parallel call characteristics and communication relationships, generate threat maps, and automatically generate hot patches for differential updates to fix vulnerabilities.

Benefits of technology

Real-time detection and prediction of smart terminal attack behaviors is realized, vulnerability response time is shortened, service continuous availability and accuracy of repair measures are ensured, and service continuity guarantee capabilities are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120316770A_ABST
    Figure CN120316770A_ABST
Patent Text Reader

Abstract

The invention provides an anti-attack method and system for improving the security of an intelligent terminal, and the method comprises the steps: extracting a parallel call feature of each task process in the intelligent terminal from a behavior data flow of a parallel task process in the intelligent terminal; determining a threat behavior sequence of the parallel task processes in the intelligent terminal according to each parallel calling feature and a communication relationship between the task processes in the intelligent terminal; performing reverse tracking dependence positioning on each threat behavior in the threat behavior sequence according to an intelligent terminal attack tracing module to obtain a plurality of attack dependence nodes of the threat behaviors in the intelligent terminal, and further generating a threat map of an attack link through all the attack dependence nodes; the threat graph is used for automatically generating the hotfix of the threat behavior in the intelligent terminal, and then the loophole is repaired in a mode of differently updating the hotfix without influencing the normal service of the intelligent terminal. On the basis of the scheme, hotfix repair of the attack behavior of the intelligent terminal can be realized, so that the guarantee service continuity of the intelligent terminal can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of computer security technology. More specifically, this application relates to an anti-attack method and system for improving the security of intelligent terminals. Background Art

[0002] With the popularization of intelligent terminals, the openness of intelligent terminal operating systems has increased, carrying a large amount of personal and business data, and security threats have been increasing continuously. The intelligent terminal security technology mainly focuses on three levels: hardware security, operating system security, and application security. Hardware security realizes resource isolation and protection through chip-level technology. Operating system security depends on vulnerability repair, self-controlled systems, and controlled updates. Application security is guaranteed through secure application stores and encryption technologies.

[0003] Traditional security solutions have significant runtime protection weaknesses when dealing with new threats, especially being ineffective against unknown attacks such as zero-day vulnerability exploitation. Detection mechanisms relying on signature library matching cannot identify attack signatures that have not been included, resulting in a lack of effective interception means when vulnerabilities are exploited. Static defense strategies are difficult to adapt to dynamic attack scenarios. Attackers can easily bypass detection through means such as code obfuscation and polymorphic deformation. Traditional solutions mostly adopt a post-fix mode, and there is a time difference from vulnerability exposure to patch deployment. Zero-day attacks often cause substantial damage during this window period. Therefore, how to achieve hot patch repair of intelligent terminal attack behaviors to improve the continuity of guarantee services for intelligent terminals has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides an anti-attack method and system for improving the security of intelligent terminals, which can realize hot patch repair of intelligent terminal attack behaviors, thereby improving the continuity of guarantee services for intelligent terminals.

[0005] In a first aspect, this application provides an anti-attack method for improving the security of intelligent terminals, including: Construct a behavior monitoring engine in the intelligent terminal kernel layer, and use the behavior monitoring engine to collect the behavior data streams of parallel task processes in the intelligent terminal; Extract the parallel call characteristics of each task process in the intelligent terminal from the behavior data streams, and then determine the threat behavior sequence of the parallel task processes in the intelligent terminal through the communication relationships between the parallel call characteristics and the task processes in the intelligent terminal; According to the intelligent terminal attack traceability module, perform reverse tracing and dependency localization on each threat behavior in the threat behavior sequence to obtain multiple attack dependency nodes of the threat behaviors in the intelligent terminal, and then generate a threat map of the attack link through all the attack dependency nodes; Automatically generate hot patches for threat behaviors in the intelligent terminal using the described threat map, and then repair vulnerabilities by differentially updating the hot patches without affecting the normal services of the intelligent terminal.

[0006] In some embodiments, extracting the parallel call characteristics of each task process in the intelligent terminal from the behavior data stream specifically includes: For each task process in the intelligent terminal, obtain the call information and resource occupancy information of the task process from the behavior data stream; Extract the parallel characteristics in the call information and the occupancy characteristics in the resource occupancy information; Determine the parallel call characteristics of the task process through the parallel characteristics and the occupancy characteristics, and then obtain the parallel call characteristics of each task process in the intelligent terminal.

[0007] In some embodiments, determining the threat behavior sequence of parallel task processes in the intelligent terminal through each parallel call characteristic and the communication relationship between task processes in the intelligent terminal specifically includes: Determine the timing correlation score of parallel task processes in the intelligent terminal through the parallel characteristics in each parallel call characteristic; Determine the resource competition anomaly degree of parallel task processes in the intelligent terminal through the occupancy characteristics in each parallel call characteristic; Determine the communication relationship credibility of parallel task processes in the intelligent terminal through the communication relationship between task processes in the intelligent terminal; Perform weighted fusion on the timing correlation score, the resource competition anomaly degree, and the communication relationship credibility, and then obtain the threat behavior sequence of parallel task processes in the intelligent terminal.

[0008] In some embodiments, according to the intelligent terminal attack traceability module, perform reverse traceability dependency positioning on each threat behavior in the threat behavior sequence to obtain multiple attack dependency nodes of threat behaviors in the intelligent terminal, specifically including: For each threat behavior, starting from the trigger point of the threat behavior, construct a data dependency graph across task processes; Mark the likelihood values of each execution node of the threat behavior in the intelligent terminal through the data dependency graph; Use each likelihood value to screen out the attack dependency nodes of the threat behavior from the intelligent terminal, and then obtain the attack dependency nodes of each threat behavior.

[0009] In some embodiments, generating a threat map of the attack link through all the attack dependency nodes specifically includes: Obtain the tracking paths of each attack dependency node, and then determine the propagation delay of each tracking path; Determine the threat map of the attack link through all the tracking paths and each propagation delay.

[0010] In some embodiments, the behavior monitoring engine is a Linux-based hybrid monitoring framework.

[0011] In some embodiments, the intelligent terminal is a heterogeneous computing platform based on a security encryption engine and a multi-core processor.

[0012] In a second aspect, the present application provides an anti-attack system for improving the security of an intelligent terminal, including an anti-attack unit, and the anti-attack unit includes: An acquisition module, configured to build a behavior monitoring engine in the kernel layer of the intelligent terminal, and use the behavior monitoring engine to acquire the behavior data stream of parallel task processes in the intelligent terminal; A processing module, configured to extract the parallel call features of each task process in the intelligent terminal from the behavior data stream, and then determine the threat behavior sequence of the parallel task processes in the intelligent terminal through each parallel call feature and the communication relationship between the task processes in the intelligent terminal; The processing module is further configured to perform reverse traceability dependency positioning on each threat behavior in the threat behavior sequence according to the intelligent terminal attack traceability module, obtain multiple attack dependency nodes of the threat behavior in the intelligent terminal, and then generate a threat map of the attack link through all the attack dependency nodes; An execution module, configured to automatically generate a hot patch for the threat behavior in the intelligent terminal using the threat map, and then repair the vulnerability by differentially updating the hot patch without affecting the normal service of the intelligent terminal.

[0013] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above anti-attack method for improving the security of an intelligent terminal.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer is caused to execute the above anti-attack method for improving the security of an intelligent terminal.

[0015] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects: In an anti - attack method and system for improving the security of intelligent terminals provided by this application, a behavior monitoring engine is built in the kernel layer of the intelligent terminal, and the behavior monitoring engine is used to collect the behavior data stream of parallel task processes in the intelligent terminal; the parallel call characteristics of each task process in the intelligent terminal are extracted from the behavior data stream, and then the threat behavior sequence of the parallel task processes in the intelligent terminal is determined through the parallel call characteristics and the communication relationship between task processes in the intelligent terminal; according to the attack traceability module of the intelligent terminal, reverse - tracking dependency location is performed on each threat behavior in the threat behavior sequence to obtain multiple attack - dependent nodes of the threat behavior in the intelligent terminal, and then a threat map of the attack link is generated through all the attack - dependent nodes; the threat map is used to automatically generate hot patches for threat behaviors in the intelligent terminal, and then the vulnerability is repaired by means of differential updating of the hot patches without affecting the normal services of the intelligent terminal.

[0016] Thus, in this application, hot patches for threat behaviors in the intelligent terminal are automatically generated using the threat map, and then the vulnerability is repaired by means of differential updating of the hot patches without affecting the normal services of the intelligent terminal. First, determining the threat behavior sequence can obtain an accurate set of attack behavior characteristics, thus providing a key target - location basis for hot - patch repair. Through in - depth analysis of parallel call characteristics and process communication relationships, the system can identify abnormal behavior patterns, which often correspond to specific attack methods. After serializing the characteristics of the attack methods, it can not only detect ongoing attacks in real - time but also predict the subsequent steps of the attack. Furthermore, the system can prepare a repair plan before the attack causes substantial damage, significantly shortening the vulnerability response time and winning a key time window for subsequent hot - patch generation, effectively ensuring the continuous availability of services. Then, determining the threat map can obtain a visual and complete attack link, thus providing a comprehensive path guidance for hot - patch repair. The threat map constructed by reverse - tracking attack - dependent nodes can clearly show the entry point, propagation path, and key operation nodes of the attack, helping the intelligent terminal distinguish between core vulnerabilities and secondary symptoms and ensuring that the repair measures act precisely on the most critical links. The time - delay weight analysis in the threat map can also reveal the operation rhythm of the attacker, helping to predict the possible next attack targets and making the repair plan more forward - looking. It not only avoids the time - delay defects of local patching but also blocks the subsequent operation space of the attacker, fundamentally improving the service continuity guarantee ability. In summary, based on the above - mentioned solution, hot - patch repair of intelligent terminal attack behaviors can be realized, thereby improving the service continuity guarantee of intelligent terminals. Brief Description of the Drawings

[0017] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 is an exemplary flowchart of an anti-attack method for improving the security of a smart terminal according to some embodiments of the present application; Figure 2 is a schematic flowchart of a process for determining a threat map according to some embodiments of the present application; Figure 3 is a schematic structural diagram of an anti-attack unit according to some embodiments of the present application; Figure 4 is a schematic structural diagram of a computer device for implementing an anti-attack method for improving the security of a smart terminal according to some embodiments of the present application. Detailed implementation manners

[0019] To better understand the technical solutions of the present application, the following will detail the technical solutions of the present application in conjunction with the drawings in the specification and specific implementation manners.

[0020] Refer to Figure 1 , which is an exemplary flowchart of an anti-attack method for improving the security of a smart terminal according to some embodiments of the present application. The anti-attack method for improving the security of a smart terminal mainly includes the following steps: In step 101, a behavior monitoring engine is built in the kernel layer of the smart terminal, and the behavior monitoring engine is used to collect the behavior data stream of parallel task processes in the smart terminal.

[0021] It should be noted that in the present application, the behavior data stream is a continuous monitoring data set composed of time-sequential task process activity records. The behavior data stream includes system call numbers, initiating threads, parameter hash values, CPU utilization rates, cache hit rates, and DMA transfer amounts in each task process; the behavior monitoring engine refers to a lightweight security proxy embedded in the smart terminal kernel, which is responsible for collecting multi-dimensional characteristics during the operation of task processes. The behavior monitoring engine is a hybrid monitoring framework based on Linux; the smart terminal is a heterogeneous computing platform based on a security encryption engine and a multi-core processor; parallel task processes refer to concurrent execution program entities that share computing resources and have communication or competition relationships.

[0022] In specific implementation, by modifying the task scheduling module of the operating system kernel, monitoring hooks are implanted during the context switching of task processes to capture basic operation metrics such as the scheduling latency and time slice occupancy rate of task processes in real time. Dynamic probes are deployed at the entry and exit of the kernel system calls of the intelligent terminal to record the types of system calls executed by each task process, parameter characteristics, and call timing relationships, forming call chain data with timestamps. Using the page table protection mechanism of the memory management unit, the access patterns of task processes to shared memory areas are monitored, including read / write frequencies, data flow directions, and out-of-bounds access attempts. The above three layers of monitoring data are aggregated through the kernel circular buffer and preprocessed to generate a standardized data stream containing the behavior fingerprints of task processes, and this standardized data stream is used as the behavior data stream of parallel task processes in the intelligent terminal.

[0023] In step 102, the parallel call characteristics of each task process in the intelligent terminal are extracted from the behavior data stream, and then the threat behavior sequence of the parallel task processes in the intelligent terminal is determined through the parallel call characteristics and the communication relationships between the task processes in the intelligent terminal.

[0024] In some embodiments, the extraction of the parallel call characteristics of each task process in the intelligent terminal from the behavior data stream can be implemented by the following steps: For each task process in the intelligent terminal, the call information and resource occupancy information of the task process are obtained from the behavior data stream; The parallel characteristics in the call information and the occupancy characteristics in the resource occupancy information are extracted; The parallel call characteristics of the task process are determined through the parallel characteristics and the occupancy characteristics, and then the parallel call characteristics of each task process in the intelligent terminal are obtained.

[0025] In specific implementation, first, for each task process in the intelligent terminal, obtain the system call number, initiating thread, parameter hash value, CPU utilization rate, cache hit rate, and DMA transfer volume of the task process from the behavior data stream, so as to use the set of the system call number, initiating thread, and parameter hash value as the call information, and use the set of the CPU utilization rate, cache hit rate, and DMA transfer volume as the resource occupancy information; then, adopt the sliding window algorithm to perform temporal analysis on the call information, so as to obtain all system call synchronization rates and resource competition waiting durations across task processes obtained from the temporal analysis, and use the set of the mean value of all system call synchronization rates and the mean value of all resource competition waiting durations as the parallel features in the call information. At the same time, by statistically analyzing the periodic fluctuation law of the resource occupancy information, use the set of the memory bandwidth contention intensity and the computing unit load balance degree in the periodic fluctuation law as the occupancy features in the resource occupancy information; finally, initialize a feature fusion model based on a neural network, use the parallel features and the occupancy features as the input features in the feature fusion model, and use the feature fusion model to perform feature fusion on the parallel features and the occupancy features, so as to use the result of the feature fusion as the parallel call feature of the task process. In the above manner, the parallel call features of each task process in the intelligent terminal can be obtained.

[0026] It should be noted that in this application, the parallel call feature is a composite feature vector used to quantify the interaction intensity between task processes; the call information is a set of metadata recording the interaction details between the task process and the operating system; the resource occupancy information is a set of metrics quantifying the consumption degree of the task process on hardware resources; the parallel feature is an abstract pattern revealing the temporal correlation between multi-task processes, and this parallel feature represents the collaborative behavior law; the occupancy feature is a statistic describing the resource allocation abnormality degree, and this occupancy feature identifies non-competitive occupancy behaviors; the feature fusion model is a multi-source feature integration framework based on deep learning, which automatically learns the non-linear correlation between the parallel feature and the occupancy feature through a neural network. This feature fusion model adopts an attention mechanism to dynamically allocate feature weights and perform cross-modal interaction calculations in the feature embedding space, and finally outputs a compact feature vector integrating spatio-temporal dimensions. This vector can comprehensively represent the parallel collaboration mode and resource contention relationship between processes, and provide a highly discriminative feature representation for subsequent threat detection.

[0027] In some embodiments, determining the threat behavior sequence of parallel task processes in the intelligent terminal through the communication relationship between each parallel call feature and the task processes in the intelligent terminal can be implemented by the following steps: Determine the temporal correlation score of the parallel task processes in the intelligent terminal through the parallel features in each parallel call feature; Determine the resource competition abnormality degree of the parallel task processes in the intelligent terminal through the occupancy features in each parallel call feature; Determine the communication relationship credibility of parallel task processes in the intelligent terminal based on the communication relationships among task processes in the intelligent terminal; Perform weighted fusion on the temporal correlation score, the resource competition abnormality degree, and the communication relationship credibility, and then obtain the threat behavior sequence of parallel task processes in the intelligent terminal.

[0028] It should be noted that in this application, the threat behavior sequence; the temporal correlation score is a quantitative indicator for measuring the deviation of task process behavior from the normal mode in the time dimension, and this temporal correlation score reflects the time characteristics of potential attacks; the resource competition abnormality degree represents the abnormal occupation degree of task processes on hardware resources, and this resource competition abnormality degree can be used to detect stealth attacks; the communication relationship credibility is to evaluate the security level of communication behaviors between task processes, and this communication relationship credibility can be used to identify illegal data exchanges or privilege abuses.

[0029] When specifically implemented, first, for each task process in the parallel task processes, use the dynamic time warping algorithm to compare the matching degree between the parallel characteristics in the parallel call characteristics of the task process and the known attack pattern library, calculate the deviation degree in its time dimension, and at the same time introduce the hidden Markov model to analyze the transition probability in the execution stage of the task process, evaluate whether the behavior of the task process conforms to the normal task scheduling rules, and finally output a standardized score in the range of 0-1, and use this standardized score as the temporal correlation of the task process. In the above way, the temporal correlation of each task process in the parallel task processes can be obtained, and thus the set of all temporal correlations is used as the temporal correlation score of the parallel task processes in the intelligent terminal. The higher the value of this temporal correlation score, the greater the possibility of temporal abnormality; second, use the isolation forest algorithm to identify the outliers of each task process from the resource occupancy characteristics, and combine the sliding window statistics to calculate the mutation rate of resource occupancy in each outlier, so as to screen out the task processes corresponding to the outliers with a mutation rate greater than the preset mutation threshold from all the outliers as abnormal task processes, and use the set of mutation rates of all abnormal task processes as the resource competition abnormality degree of the parallel task processes in the intelligent terminal.

[0030] Then, in specific implementation, for each task process, obtain the initial score of the credibility in the task process. By parsing the communication data packets between task processes, check the certificate chains, signatures, and permission tags of both communication parties. If it is found that an unauthorized task process attempts to access a highly sensitive interface or the communication content contains malicious payloads, then reduce the initial score of the credibility. Thus, use the reduced initial score as the credibility score of the task process. Through the above method, the credibility scores of all task processes can be obtained. Take the set of all credibility scores as the value range of the communication relationship credibility, and the communication relationship credibility of the parallel task processes in the intelligent terminal can be obtained. Finally, for each task process of the parallel task processes in the intelligent terminal, set the dynamic weights of the timing correlation, resource competition anomaly degree, and communication relationship credibility in the task process in combination with historical experience, and calculate the weighted sum of the timing correlation, resource competition anomaly degree, and communication relationship credibility as the comprehensive threat score of the task process. If the comprehensive threat score exceeds the adaptive threshold (initial value 1.2, adjusted according to the environment), then determine that the task process constitutes a threat behavior. Through the above method, all threat behaviors can be obtained, and thus arrange all threat behaviors in descending order according to the comprehensive threat score as the threat behavior sequence of the parallel task processes in the intelligent terminal.

[0031] In step 103, according to the intelligent terminal attack traceability module, perform reverse traceability dependency localization on each threat behavior in the threat behavior sequence to obtain multiple attack dependency nodes of the threat behaviors in the intelligent terminal, and then generate a threat graph of the attack link through all the attack dependency nodes.

[0032] In some embodiments, according to the intelligent terminal attack traceability module, performing reverse traceability dependency localization on each threat behavior in the threat behavior sequence to obtain multiple attack dependency nodes of the threat behaviors in the intelligent terminal can be implemented by the following steps: For each threat behavior, construct a cross-task process data dependency graph starting from the trigger point of the threat behavior; Mark the likelihood values of each execution node of the threat behavior in the intelligent terminal through the data dependency graph; Use each likelihood value to screen out the attack dependency nodes of the threat behavior from the intelligent terminal, and then obtain the attack dependency nodes of each threat behavior.

[0033] In specific implementation, first, for each threat behavior, the current execution node of the threat behavior is used as the trigger point of the threat behavior. Starting from the trigger point of the threat behavior, the data flow propagation path is traced backward, and the variable transfer, shared memory modification, and communication relationship between task processes are recorded. A weighted directed graph is constructed by combining static analysis (e.g., control flow graph parsing) and dynamic instrumentation (e.g., runtime taint tracking). The nodes of the weighted directed graph represent key data operations (e.g., file reading and writing, network requests), and the edges of the weighted directed graph represent data dependency relationships (e.g., parameter passing, return value impact). Thus, this weighted directed graph is used as the data dependency graph of cross-task processes. Then, a Bayesian inference model based on a neural network is initialized, and the context anomaly degree, data source credibility, and historical behavior baseline are used as influencing factors in this Bayesian inference model. This Bayesian inference model is used to quantify the attack possibility of each execution node of the threat behavior. Thus, the quantified result is used as the likelihood value of each execution node of the threat behavior in the intelligent terminal. Finally, the execution nodes with likelihood values greater than the preset vulnerability threshold are used as the attack dependency nodes of the threat behavior. Through the above method, the attack dependency nodes of each threat behavior can be obtained.

[0034] It should be noted that in this application, the attack dependency node is an indispensable key operation point in the attack chain. After removing or repairing this attack dependency node, the attack execution can be blocked. The data dependency graph is a directed graph used to describe the cross-process data flow relationship in the threat behavior, and it can be used to visualize the attack path. The likelihood value is a probability index that quantifies the degree of association between a specific operation node and an attack. The Bayesian inference model is an intelligent analysis framework based on probability statistics. By dynamically learning the joint probability distribution of features such as context anomaly degree, data source credibility, and historical behavior baseline through a neural network, this Bayesian inference model is based on prior knowledge and real-time observation data, and uses Bayes' theorem to recursively update the posterior probability of each execution node, fusing multi-dimensional security indicators into a standardized likelihood value in the 0-1 interval, quantitatively reflecting the risk degree of the node being exploited by an attack. The higher the value, the stronger the criticality of the node in the attack chain.

[0035] In some embodiments, a threat map of the attack link is generated through all the attack dependency nodes. Refer to Figure 2 As shown, this figure is a schematic flow diagram for determining the threat map in some embodiments of this application. In this embodiment, the threat map can be determined by the following steps: In step 1031, the tracking paths of each attack dependency node are obtained, and then the propagation delay of each tracking path is determined. In step 1032, the threat map of the attack link is determined through all the tracking paths and each propagation delay.

[0036] In specific implementation, first, for each attack-dependent node, starting from the attack-dependent node, forward and backward tracing is performed along the edges of the data dependency graph, and the complete data flow path is recorded as the tracing path of the attack-dependent node. Through the above method, the tracing paths of all attack-dependent nodes can be obtained. For each tracing path, the time delay difference between adjacent nodes in the tracing path is obtained from the record file of the intelligent terminal, so that the sum of the absolute values of all time delay differences is used as the propagation delay of the tracing path. Through the above method, the propagation delays of all tracing paths can be obtained; then, an atlas adjustment model based on time delay weighting is initialized, the initial atlas of the attack link is obtained from the console of the intelligent terminal as the adjustment target in the atlas adjustment model, and each propagation delay is used as the adjustment weight in the atlas adjustment model. The atlas adjustment model is used to mark the conversion efficiency of the attack phase in the initial atlas, so that the initial atlas marked by the atlas adjustment model is used as the threat atlas of the attack link.

[0037] It should be noted that in this application, the threat atlas is the topological structure of the visualized attack link, and this threat atlas contains node relationships and time delay characteristics; the tracing path refers to the data control flow propagation trajectory between attack-dependent nodes, and this tracing path can be used to restore the attack steps; the propagation delay represents the execution time difference of the attack behavior between adjacent nodes in the path; the atlas adjustment model is a computational framework for dynamically optimizing the visualization of the attack link. By quantifying the influence weight of the propagation delay on the attack phase conversion, the topological structure of the threat atlas is automatically adjusted. This atlas adjustment model takes the initial attack atlas as the input, converts the time delay data into edge weight coefficients, uses the graph neural network to denoise and strengthen the high-time-delay paths, and at the same time compresses the low-time-delay redundant nodes, and finally outputs an optimized atlas that can intuitively reflect the key path of the attack efficiency, where the node spacing is proportional to the time consumed in the attack phase, and the edge thickness represents the cross-phase dependence intensity.

[0038] In step 104, the threat atlas is used to automatically generate hot patches for threat behaviors in the intelligent terminal, and then the vulnerabilities are repaired by differentially updating the hot patches without affecting the normal services of the intelligent terminal.

[0039] It should be noted that in this application, a hot patch refers to a runtime vulnerability repair code unit that can take effect without restarting, and this hot patch is used to maintain service continuity. Specifically, when implemented, the graph analysis engine of the smart terminal can be used to parse the attack dependency nodes in the threat graph to locate the specific location of the vulnerability (for example, the memory address with an out-of-bounds write vulnerability, the function entry without parameter verification). Combining the vulnerability type to match the predefined repair policy library (for example, memory protection policy, permission verification policy), and using binary rewriting technology, jump instructions are inserted at the target function entry to redirect the execution flow to a secure memory area. The secure memory area contains newly generated patch code, while maintaining the integrity of the original function. Thus, the patch code in the secure memory area is used as a hot patch. The byte-level difference between the patch and the original code is calculated by the differential update engine to generate a lightweight incremental patch package. The dynamic link library hot loading mechanism provided by the operating system is used to replace the target code page in memory during the process runtime, and atomic operations are used to ensure the thread safety of the update process.

[0040] In addition, on the other hand of this application, in some embodiments, this application provides an anti-attack system for improving the security of a smart terminal. The anti-attack system for improving the security of a smart terminal includes an anti-attack unit. Refer to Figure 3 , which is a schematic structural diagram of the anti-attack unit shown according to some embodiments of this application. The anti-attack unit includes: a collection module 201, a processing module 202, and an execution module 203, which are described as follows: Collection module 201. In this application, the collection module 201 is mainly used to build a behavior monitoring engine in the kernel layer of the smart terminal and use the behavior monitoring engine to collect the behavior data stream of parallel task processes in the smart terminal. Processing module 202. In this application, the processing module 202 is used to extract the parallel call characteristics of each task process in the smart terminal from the behavior data stream, and then determine the threat behavior sequence of the parallel task processes in the smart terminal through the communication relationship between each parallel call characteristic and the task processes in the smart terminal. It should be noted that the processing module 202 is also used to perform reverse traceability dependency positioning on each threat behavior in the threat behavior sequence according to the smart terminal attack traceability module to obtain multiple attack dependency nodes of the threat behavior in the smart terminal, and then generate a threat graph of the attack link through all the attack dependency nodes. Execution module 203. In this application, the execution module 203 is mainly used to automatically generate hot patches for the threat behavior in the smart terminal using the threat graph, and then repair the vulnerability by differentially updating the hot patch without affecting the normal service of the smart terminal.

[0041] The above text has introduced in detail the examples of the anti - attack method and system for improving the security of intelligent terminals provided by the embodiments of the present application. It can be understood that, in order to implement the above functions, the corresponding device includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0042] In some embodiments, the present application further provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above - mentioned anti - attack method for improving the security of intelligent terminals.

[0043] In some embodiments, referring to Figure 4 , the dotted line in this figure indicates that the unit or the module is optional. This figure is a schematic structural diagram of a computer device for implementing the anti - attack method for improving the security of intelligent terminals provided by the embodiments of the present application. The above - mentioned anti - attack method for improving the security of intelligent terminals can be implemented by Figure 4 the computer device shown. The computer device includes at least one processor 301, a memory 302, and at least one communication unit 305. The computer device can be a terminal device, a server, or a chip.

[0044] The processor 301 can be a general - purpose processor or a special - purpose processor. For example, the processor 301 can be a central processing unit (CPU). The CPU can be used to control the computer device, execute software programs, and process the data of software programs. The computer device can also include a communication unit 305 for realizing the input (receiving) and output (sending) of signals.

[0045] For example, the computer device can be a chip, and the communication unit 305 can be the input and / or output circuit of the chip, or the communication unit 305 can be the communication interface of the chip. The chip can be a component of a terminal device, a network device, or other devices.

[0046] Again, for example, the computer device can be a terminal device or a server, and the communication unit 305 can be the transceiver of the terminal device or the server, or the communication unit 305 can be the transceiver circuit of the terminal device or the server.

[0047] The computer device may include one or more memories 302, on which there is a program 304. The program 304 can be run by the processor 301 to generate instructions 303, enabling the processor 301 to execute the methods described in the above method embodiments according to the instructions 303. Optionally, data (such as a target audit model) may also be stored in the memory 302. Optionally, the processor 301 may also read the data stored in the memory 302. This data may be stored at the same storage address as the program 304, or it may be stored at a different storage address from the program 304.

[0048] The processor 301 and the memory 302 can be set separately or integrated together. For example, they can be integrated on a system on chip (SOC) of a terminal device.

[0049] It should be understood that each step of the above method embodiments can be completed by a logical circuit in the form of hardware or instructions in the form of software in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices. For example, discrete gate, transistor logic devices, or discrete hardware components.

[0050] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0051] For example, in some embodiments, the present application also provides a computer-readable storage medium. Instructions or code are stored in the computer-readable storage medium. When the instructions or code run on a computer, the computer is enabled to execute the anti-attack method for improving the security of intelligent terminals described above.

[0052] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0053] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to cover these changes and modifications.

Claims

1. An anti-attack method for improving the security of intelligent terminals, characterized in that, It includes the following steps: Build a behavior monitoring engine in the kernel layer of the smart terminal, and use the behavior monitoring engine to collect the behavior data stream of parallel task processes in the smart terminal; Extract the parallel call characteristics of each task process in the smart terminal from the behavior data stream, and then determine the threat behavior sequence of the parallel task processes in the smart terminal through the communication relationship between each parallel call characteristic and the task processes in the smart terminal; According to the attack traceability module of the smart terminal, perform reverse traceability dependency location on each threat behavior in the threat behavior sequence to obtain multiple attack dependency nodes of the threat behavior in the smart terminal, and then generate a threat map of the attack link through all the attack dependency nodes; Automatically generate a hot patch for the threat behavior in the smart terminal using the threat map, and then repair the vulnerability by differentially updating the hot patch without affecting the normal service of the smart terminal.

2. The method according to claim 1, characterized in that, Extracting the parallel call characteristics of each task process in the smart terminal from the behavior data stream specifically includes: For each task process in the smart terminal, obtain the call information and resource occupancy information of the task process from the behavior data stream; Extract the parallel characteristics in the call information and the occupancy characteristics in the resource occupancy information; Determine the parallel call characteristics of the task process through the parallel characteristics and the occupancy characteristics, and then obtain the parallel call characteristics of each task process in the smart terminal.

3. The method according to claim 1, wherein Determining the threat behavior sequence of the parallel task processes in the smart terminal through the communication relationship between each parallel call characteristic and the task processes in the smart terminal specifically includes: Determine the timing correlation score of the parallel task processes in the smart terminal through the parallel characteristics in each parallel call characteristic; Determine the resource competition abnormality degree of the parallel task processes in the smart terminal through the occupancy characteristics in each parallel call characteristic; Determine the communication relationship credibility of the parallel task processes in the smart terminal through the communication relationship between the task processes in the smart terminal; Perform weighted fusion on the timing correlation score, the resource competition abnormality degree, and the communication relationship credibility to obtain the threat behavior sequence of the parallel task processes in the smart terminal.

4. The method according to claim 1, wherein According to the attack traceability module of the smart terminal, performing reverse traceability dependency location on each threat behavior in the threat behavior sequence to obtain multiple attack dependency nodes of the threat behavior in the smart terminal specifically includes: For each threat behavior, start from the trigger point of the threat behavior and build a data dependency graph across task processes; Mark the likelihood values of each execution node of the threat behavior in the smart terminal through the data dependency graph; Use each likelihood value to screen out the attack dependency nodes of the threat behavior from the smart terminal to obtain the attack dependency nodes of each threat behavior.

5. The method according to claim 1, wherein Generating a threat map of the attack link through all the attack dependency nodes specifically includes: Obtain the tracking paths of each attack dependency node, and then determine the propagation delay of each tracking path; Determine the threat map of the attack link through all the tracking paths and each propagation delay.

6. The method according to claim 1, wherein The behavior monitoring engine is a hybrid monitoring framework based on Linux.

7. The method according to claim 1, wherein The smart terminal is a heterogeneous computing platform based on a security encryption engine and a multi-core processor.

8. An anti-attack system for improving the security of intelligent terminals, the anti-attack system for improving the security of intelligent terminals includes an anti-attack unit, characterized in that, The anti-attack unit includes: A collection module, configured to build a behavior monitoring engine in the kernel layer of the smart terminal, and use the behavior monitoring engine to collect the behavior data stream of parallel task processes in the smart terminal; A processing module, configured to extract the parallel call characteristics of each task process in the smart terminal from the behavior data stream, and then determine the threat behavior sequence of the parallel task processes in the smart terminal based on the communication relationship between the parallel call characteristics and the task processes in the smart terminal; The processing module is further configured to perform reverse tracing dependency location on each threat behavior in the threat behavior sequence according to the smart terminal attack traceability module, obtain multiple attack dependency nodes of the threat behavior in the smart terminal, and then generate a threat graph of the attack link through all the attack dependency nodes; An execution module, configured to automatically generate a hot patch for the threat behavior in the smart terminal using the threat graph, and then repair the vulnerability by differentially updating the hot patch without affecting the normal services of the smart terminal.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory is configured to store a computer program, and the processor is configured to call and run the computer program from the memory, so that the computer device executes the anti-attack method for improving the security of the smart terminal according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Instructions or codes are stored in the computer-readable storage medium, and when the instructions or codes are run on a computer, the computer is caused to execute the anti-attack method for improving the security of the smart terminal according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Hot patching method and related device

    CN117668846A

  • Network attack link tracking and threat situation reasoning method based on knowledge graph

    CN119544327A

  • Diagnostic test method based on computer platform Vspy

    CN119718963A

  • Interference channel contention modelling using machine learning

    US20230137788A1