Enterprise cloud security situation assessment method and device, medium and equipment

By obtaining and computing the network security data of the enterprise cloud, and combining long and short-term memory neural network models to predict security situations, the problem that traditional passive defense methods cannot identify massive attacks is solved, and active evaluation and prediction of the enterprise cloud security situation is achieved. Improves the security of cloud environments.

CN119030756APending Publication Date: 2024-11-26SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

Patent Information

Application Number
CN202411056168.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

Traditional enterprise cloud security situation evaluation methods belong to the passive defense category, which cannot effectively identify and deal with massive attacks, it is difficult to provide reliable security defense strategies from a global perspective, and it is difficult to judge the security situation of the cloud environment due to a large number of irrelevant alarms.

Method used

By obtaining enterprise cloud network security data, computing device trend indicators and asset risk index, combining long and short-term memory neural network models to make security trend predictions, push risk messages to take protective measures in advance, and realize active evaluation of enterprise cloud security trends and predict.

Benefits of technology

It provides a reliable security defense strategy from a global perspective, reduces the occurrence of security threats such as information leakage, asset vulnerabilities and account hijacking, and improves the security of the cloud environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119030756A_ABST
    Figure CN119030756A_ABST
Patent Text Reader

Abstract

The invention provides an enterprise cloud security situation assessment method and device, a medium and equipment. The method comprises the following steps: acquiring network security data of enterprise cloud; the network security data comprises enterprise cloud asset value, vulnerability event information, alarm event information and threat event information; calculating a situation index of each device in the enterprise cloud according to the network security data; wherein the situation index comprises a score corresponding to the asset value, a vulnerability risk calculated according to the vulnerability event information, an alarm risk calculated according to the alarm event information and a threat attack risk calculated according to the threat event information; according to the situation index of each device, calculating an asset risk index of the device; and calculating a system risk index of the enterprise cloud according to each asset risk index corresponding to each device in the enterprise cloud. According to the method, a reliable security defense strategy can be provided for enterprise network security from a global perspective, and the security of an enterprise cloud environment can be guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of security risk technology, and in particular to an enterprise cloud security situation assessment method, device, medium, and equipment. Background Art

[0002] In recent years, with the rapid development of the Internet, more and more enterprises have introduced new technologies such as cloud computing, big data, and the Internet of Things. At this stage, the data generated by the application level and access points of enterprises have the characteristics of massive data. At the same time, cloud providers have turned their operating targets to small and medium-sized enterprises, hoping to gradually expand the application of cloud-related advanced technologies to small and medium-sized enterprises, thereby providing enterprises with efficient storage and data processing capabilities. From the perspective of cloud applications for small and medium-sized enterprises, this is not only a technical boost to small and medium-sized enterprises, but also a revolution in the development of cloud computing.

[0003] Enterprise cloud is a commercial cloud system specifically designed for the information operation and management business of enterprises in various fields. For example, there are enterprise internal cloud systems such as resource management cloud and data cloud with some special customized functions. However, as cloud computing business continues to expand, cloud security issues are also emerging. The current status of cloud security released by the Cloud Security Alliance points out that the main cloud security issues are threats such as data leakage, data vulnerabilities, account hijacking, and system vulnerabilities. Due to the large amount of multi-source heterogeneous data generated by access devices, applications, and virtual machines in the cloud platform, traditional security mechanisms will generate a large number of irrelevant alarms, and it is difficult for security managers to judge the situation of the cloud environment from the perspective of cloud security as a whole.

[0004] The traditional security situation assessment of enterprises has the following main problems: the traditional security management strategy belongs to the passive defense method, which has great limitations and lags, and cannot provide reliable security defense strategies for enterprise network security from a global perspective. In addition, the traditional passive defense mechanism of enterprises cannot accurately identify massive attacks. Summary of the invention

[0005] In response to at least one of the above technical problems, an embodiment of the present invention provides an enterprise cloud security situation assessment method and apparatus, medium, and equipment.

[0006] According to the first aspect, the enterprise cloud security situation assessment method provided by the embodiment of the present invention includes:

[0007] Acquire network security data of the enterprise cloud; wherein the network security data includes asset value, vulnerability event information, alarm event information, and threat event information of the enterprise cloud;

[0008] Calculate the situation index of each device in the enterprise cloud according to the network security data; wherein the situation index includes a score corresponding to the asset value, a vulnerability risk calculated according to the vulnerability event information, an alarm risk calculated according to the alarm event information, and a threat attack risk calculated according to the threat event information;

[0009] Calculate the asset risk index of each device based on its status indicators;

[0010] The system risk index of the enterprise cloud is calculated according to each asset risk index corresponding to each device in the enterprise cloud.

[0011] In one embodiment, calculating the asset risk index of each device according to the status indicator of the device includes:

[0012] The asset risk index of each device is calculated using a first calculation formula, wherein the first calculation formula includes:

[0013]

[0014] Among them, MIN() is the minimum function, A is the weight of vulnerability risk, B is the weight of warning risk, C is the weight of threat attack risk, A>B>C.

[0015] In one embodiment, the vulnerability event information includes the number of vulnerability events and scores corresponding to the severity of the vulnerability events; correspondingly, the vulnerability risk is the product of the number of vulnerability events and the scores corresponding to the severity of the vulnerability events.

[0016] In one embodiment, the alarm event information includes the number of alarm events and scores corresponding to the severity of the alarm events; correspondingly, the alarm risk is the product of the number of alarm events and the scores corresponding to the severity of the alarm events.

[0017] In one embodiment, the threat attack information includes the number of threat events and scores corresponding to the severity of the threat events; correspondingly, the threat attack risk is the product of the number of threat events and the scores corresponding to the severity of the threat events.

[0018] In one embodiment, calculating the system risk index of the enterprise cloud according to each asset risk index corresponding to each device in the enterprise cloud includes:

[0019] Determine the asset risk level of each device based on its asset risk index;

[0020] Calculate the average value of the asset risk index of each device corresponding to the same asset risk level to obtain the average asset risk index corresponding to the asset risk level;

[0021] The system risk index of the enterprise cloud is calculated according to each average asset risk index corresponding to each asset risk level.

[0022] In one embodiment, the calculating the system risk index of the enterprise cloud according to each average asset risk index corresponding to each asset risk level includes:

[0023] The system risk index of the enterprise cloud is calculated using a second calculation formula, where the second calculation formula is:

[0024] The system risk index of the enterprise cloud = (the average asset risk index corresponding to the critical asset risk level * a + the average asset risk index corresponding to the high-risk asset risk level * b + the average asset risk index corresponding to the medium-risk asset risk level * c + the average asset risk index corresponding to the low-risk asset risk level * d) / (a ​​+ b + c + d);

[0025] Among them, the asset risk levels of critical, high risk, medium risk and low are from high to low, a is the weight of the critical asset risk level, b is the weight of the high risk asset risk level, c is the weight of the medium risk asset risk level, d is the weight of the low risk asset risk level, and a>b>c>d.

[0026] In one embodiment, the method further comprises:

[0027] Determine a time series formed by the asset risk index corresponding to each device in the enterprise cloud at each time point in a recent time period;

[0028] Input the time series corresponding to each device into a pre-trained cloud security situation prediction model to obtain a risk prediction result of the device at a preset time point in the future; wherein the cloud security situation prediction model is a model trained based on a long short-term memory neural network;

[0029] According to the risk prediction results corresponding to each device, the devices with security risks are screened out, push messages are generated according to the devices with security risks, and the push messages are pushed to the operation and maintenance personnel, so that the operation and maintenance personnel can take security protection measures in advance for the devices with security risks.

[0030] According to the second aspect, the enterprise cloud security situation assessment device provided by the embodiment of the present invention includes:

[0031] A data acquisition module, used to acquire network security data of the enterprise cloud; wherein the network security data includes asset value, vulnerability event information, alarm event information and threat event information of the enterprise cloud;

[0032] A first calculation module is used to calculate the situation index of each device in the enterprise cloud according to the network security data; wherein the situation index includes a score corresponding to the asset value, a vulnerability risk calculated according to the vulnerability event information, an alarm risk calculated according to the alarm event information, and a threat attack risk calculated according to the threat event information;

[0033] The second calculation module is used to calculate the asset risk index of each device according to the situation index of the device;

[0034] The third calculation module is used to calculate the system risk index of the enterprise cloud according to each asset risk index corresponding to each device in the enterprise cloud.

[0035] According to a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to execute the method provided in the first aspect.

[0036] According to a fourth aspect, an embodiment of the present invention provides a computing device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the method provided in the first aspect is implemented.

[0037] The enterprise cloud security situation assessment method, device, medium, and equipment provided by the embodiment of the present invention first obtain the network security data of the enterprise cloud, then calculate the situation index of each device in the enterprise cloud based on the network security data, and then calculate the asset risk index of each device based on the situation index of each device, and finally calculate the system risk index of the enterprise cloud based on each asset risk index corresponding to each device in the enterprise cloud. Compared with traditional passive defense methods, the embodiment of the present invention actively evaluates the security situation of the enterprise cloud, and the factors considered in the evaluation are more comprehensive and holistic, so that reliable security defense strategies can be provided for enterprise network security from a global perspective. Therefore, compared with traditional passive defense methods, the degree of lag is reduced. Moreover, the embodiment of the present invention implements the security situation assessment of the enterprise cloud environment, which helps to ensure the security of the enterprise cloud environment and reduce the occurrence of security threat events such as information leakage, asset vulnerabilities, and account hijacking. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic diagram of a process of an enterprise cloud security situation assessment method in one embodiment of the present invention;

[0039] Figure 2 This is an overall flow chart of device security situation prediction in one embodiment of the present invention;

[0040] Figure 3 This is an overall flow chart of device security situation prediction in one embodiment of the present invention;

[0041] Figure 4 It is a structural block diagram of an enterprise cloud security situation assessment device in one embodiment of the present invention. DETAILED DESCRIPTION

[0042] In a first aspect, an embodiment of the present invention provides a method for assessing the security situation of an enterprise cloud. Figure 1 The method comprises the following steps S110 to S140:

[0043] S110, obtaining network security data of the enterprise cloud; wherein the network security data includes asset value, vulnerability event information, warning event information, and threat event information of the enterprise cloud;

[0044] It is understandable that when conducting an enterprise cloud platform security situation assessment, it is necessary to base it on the security data of the enterprise cloud platform. The network security data involved includes the asset value of the enterprise cloud as well as event information such as vulnerabilities, threats, and alarms.

[0045] There are many ways to obtain network security data of enterprise clouds, such as vulnerability scanning, penetration testing, source code auditing, etc.:

[0046] (1) Vulnerability Scanning

[0047] A vulnerability is a defect in the specific implementation of hardware, software, or a protocol, or in a system security policy, which can allow an attacker to access or damage a system without authorization. It is an unprotected entry point left unintentionally by a restricted computer, component, application, or other online resource. Vulnerability scanning is a security detection behavior that detects the security vulnerabilities of a specified remote or local computer system based on a vulnerability database by scanning and other means to discover exploitable vulnerabilities.

[0048] (2) Penetration Testing

[0049] Penetration testing is initiated by highly skilled and qualified security service personnel, simulating the attack methods commonly used by hackers to simulate intrusion into the target system. The purpose of penetration testing is to fully explore and expose the weaknesses of the system, so that managers can understand the threats faced by their systems. Penetration testing is often an important part of risk assessment, providing important original reference data for risk assessment. Among them, the difference between penetration testing and vulnerability scanning: vulnerability scanning is to check the weaknesses of the system. Penetration testing is that the tester simulates a hacker, not only to find weaknesses in the system, but also to verify some high-risk weaknesses, and even to dig out some unknown weaknesses.

[0050] (3) Source code audit

[0051] Source code audit is a comprehensive security check of the security and reliability of the system's source code and software architecture by security service personnel who have rich coding experience and a deep understanding of secure coding principles and application security. The purpose of source code audit is to fully explore the security defects and regulatory defects in the cloud platform application code, so that developers can understand the threats that the application system they develop may face, and guide developers to correctly fix program defects.

[0052] S120. Calculate the situation index of each device in the enterprise cloud according to the network security data; wherein the situation index includes a score corresponding to the asset value, a vulnerability risk calculated according to the vulnerability event information, an alarm risk calculated according to the alarm event information, and a threat attack risk calculated according to the threat event information;

[0053] For example, a very low asset value would have a score of 20, a low asset value would have a score of 40, a medium asset value would have a score of 60, a high asset value would have a score of 80, and a very high asset value would have a score of 100.

[0054] The vulnerability event information includes the number of vulnerability events and the scores corresponding to the severity of the vulnerability events; correspondingly, the vulnerability risk is the product of the number of vulnerability events and the scores corresponding to the severity of the vulnerability events.

[0055] For example, when the severity of a vulnerability event is crisis, the corresponding score is 80; when the severity of a vulnerability event is high risk, the corresponding score is 60; when the severity of a vulnerability event is medium risk, the corresponding score is 30; and when the severity of a vulnerability event is low risk, the corresponding score is 10.

[0056] The alarm event information includes the number of alarm events and the scores corresponding to the severity of the alarm events; correspondingly, the alarm risk is the product of the number of alarm events and the scores corresponding to the severity of the alarm events.

[0057] For example, when the severity of the alarm event is critical, the corresponding score is 80, when the severity of the alarm event is high, the corresponding score is 60, when the severity of the alarm event is medium, the corresponding score is 30, and when the severity of the alarm event is low, the corresponding score is 10.

[0058] The threat attack information includes the number of threat events and the scores corresponding to the severity of the threat events; correspondingly, the threat attack risk is the product of the number of threat events and the scores corresponding to the severity of the threat events.

[0059] For example, if the severity of the threat event is critical, the score corresponding to the severity of the threat event is 80. If the severity of the threat event is high, the score corresponding to the severity of the threat event is 60, if the severity of the threat event is medium, the score corresponding to the severity of the threat event is 30, and if the severity of the threat event is low, the score corresponding to the severity of the threat event is 10.

[0060] S130, calculating the asset risk index of each device according to the status indicator of the device;

[0061] In one embodiment, calculating the asset risk index of each device according to the status indicator of the device may include: using a first calculation formula to calculate the asset risk index of each device, the first calculation formula including:

[0062]

[0063] Among them, MIN() is the minimum function, A is the weight of vulnerability risk, B is the weight of warning risk, C is the weight of threat attack risk, A>B>C.

[0064] For example, A is 5, B is 3, and C is 2.

[0065] S140. Calculate the system risk index of the enterprise cloud according to each asset risk index corresponding to each device in the enterprise cloud.

[0066] In one embodiment, calculating the system risk index of the enterprise cloud according to each asset risk index corresponding to each device in the enterprise cloud in S140 may include:

[0067] S141. Determine the asset risk level of each device according to the asset risk index of the device;

[0068] It is understandable that after calculating the asset risk index of a device, the asset risk level of the device can be determined. The range of the asset risk index of the critical level is (75, 100], the range of the asset risk index of the high risk level is (50, 75], the range of the asset risk index of the medium risk level is (25, 50], and the range of the asset risk index of the low risk level is [0, 25]. Therefore, according to the asset risk index range corresponding to each level and the asset risk index of each device calculated in S130, the asset risk level of the device can be determined.

[0069] S142, calculating the average value of the asset risk index of each device corresponding to the same asset risk level, and obtaining the average asset risk index corresponding to the asset risk level;

[0070] Since there are multiple devices in an enterprise cloud, each device has its own asset risk index and asset risk level. The average asset risk index corresponding to the asset risk level can be obtained by averaging the asset risk indexes of each device with the same asset risk level. Thus, the average asset risk index corresponding to critical, high risk, medium risk, and low risk can be obtained.

[0071] S143. Calculate the system risk index of the enterprise cloud according to the average asset risk index corresponding to each asset risk level.

[0072] In one embodiment, calculating the system risk index of the enterprise cloud according to each average asset risk index corresponding to each asset risk level in S143 may include: calculating the system risk index of the enterprise cloud using a second calculation formula, where the second calculation formula is:

[0073] The system risk index of the enterprise cloud = (the average asset risk index corresponding to the critical asset risk level * a + the average asset risk index corresponding to the high-risk asset risk level * b + the average asset risk index corresponding to the medium-risk asset risk level * c + the average asset risk index corresponding to the low-risk asset risk level * d) / (a ​​+ b + c + d);

[0074] Among them, the asset risk levels of critical, high risk, medium risk and low are from high to low, a is the weight of the critical asset risk level, b is the weight of the high risk asset risk level, c is the weight of the medium risk asset risk level, d is the weight of the low risk asset risk level, and a>b>c>d.

[0075] For example, a is 4, b is 3, c is 2, and d is 1.

[0076] According to the relationship between the system risk index and the system risk level: critical: (75,100]; high risk: (50,75]; medium risk: (25,50]; low risk: [0,25], the system risk level corresponding to the system risk index can be determined.

[0077] It is understandable that cloud security status indicators can be divided into static indicators and dynamic indicators. Cloud platform assets, vulnerabilities, threats, and alarm events are relatively stable and can be regarded as static indicators, while threats and alarm events change frequently and belong to dynamic indicators.

[0078] It can be seen that based on S110 to S140, the current enterprise cloud security situation can be evaluated.

[0079] In one embodiment, see Figure 2 and Figure 3 The method provided in the embodiment of the present invention may further include S150 to S170:

[0080] S150, determining a time series formed by the asset risk index corresponding to each device in the enterprise cloud at each time point in a recent time period;

[0081] The calculation process of the asset risk index of each device at each time point within the time period refers to the calculation process of the asset risk index above. Specifically, firstly, the network security data of the device at that time point is obtained, then the indicators are extracted from the network security data, then the indicators are quantified, and the asset risk index of the device at that time point is calculated.

[0082] S160, inputting the time series corresponding to each device into a pre-trained cloud security situation prediction model to obtain a risk prediction result of the device at a preset time point in the future; wherein the cloud security situation prediction model is a model trained based on a long short-term memory neural network;

[0083] S170. Screen out devices with security risks based on the risk prediction results corresponding to each device, generate push messages based on the devices with security risks, and push the push messages to operation and maintenance personnel so that the operation and maintenance personnel can take security protection measures in advance for the devices with security risks.

[0084] It can be seen that based on S150 to S170, the future security situation of each device can be predicted.

[0085] For example, the time series formed by the asset risk index of each device at various time points in the past week, and then the time series is input into the cloud security situation prediction model, the risk prediction result of this device in the next day will be obtained, and the risk result includes risk and no risk. In this way, the risk prediction result corresponding to each device can be obtained. The risky devices are screened out to form a push message, and then the push message is sent to the operation and maintenance personnel, so that the operation and maintenance personnel can take security protection measures in advance for these devices with security risks.

[0086] Among them, the long short-term memory neural network is a time recursive neural network model that can process time series data and is used to predict network security situation. In the long short-term memory neural network, a processor is added to judge whether the information is "useful" or "useless". This processor corresponds to three gates, namely the input gate, the forget gate, and the output gate. Therefore, when a time series enters the long short-term memory neural network, the rules can be used to judge whether the information in the time series is "useful" or "useless". If it meets the model requirements, the "useful" information can be retained, and the "useless" information that does not meet the requirements is chosen to be forgotten through the forget gate. Therefore, when the enterprise cloud platform is attacked, the time series of the attack can be converted into the processing of the LSTM model. When the enterprise cloud platform is attacked, it may be an intermittent attack in a certain time series, or it may be a continuous attack in a certain time series. Therefore, the historical data set formed by the time series corresponding to the historical attack events of the enterprise cloud platform situation can be used as the data set for model training. In the cloud security situation prediction model based on long short-term memory neural network, historical data sets and risk-free labels are mainly used as input values ​​of the cloud security situation prediction model. Then, the information in the long and short memories is discarded through the forget gate cycle stage inside the model, and the newly input information is stored to update the unit state. Finally, the calculation result of the state function is output.

[0087] Moreover, after the cloud security situation prediction model based on the long short-term memory neural network is constructed, it is necessary to continuously adjust the iteration parameters for iterative training. When the accuracy of the model no longer increases or the loss no longer decreases continuously, the iteration is stopped, and the model state is optimal at this time. At this time, the cloud security situation assessment model based on the long short-term memory neural network can predict the situation of enterprise cloud security. During the training process, it is necessary to judge the results of each iteration. If it reaches the optimal result, the model is stored; if it does not meet expectations, the parameters need to be updated through back propagation and iterative training continues. After the training is completed, the cloud security situation assessment model is verified, that is, the model is run based on the test set to verify the situation assessment effect of the model.

[0088] It is understandable that situational awareness is a dynamic, comprehensive and holistic ability to assess the security risk of a target object based on internal and external environments. This situational assessment is mainly based on security big data, and is a capability or method to identify security threats before or during the event, understand and analyze threats, and respond to and handle them from the overall perspective of a target object, and ultimately provide security decision-making plans or action plans for threats to ensure the safe implementation of software systems. The situational awareness of enterprise cloud platforms is to perceive or prevent increasingly intelligent, professional and hidden network security threats or attacks.

[0089] It is understandable that the security situation assessment of the enterprise cloud platform is a process of analyzing the asset value, potential threats, weak links, and protective measures taken by the information system with reference to risk assessment standards and management specifications, judging the probability of security incidents and possible losses, and proposing risk management measures. That is, after the cloud platform is connected to the Internet, an information security risk assessment is conducted to determine the network security vulnerabilities and whether they meet the assessment standards for the cloud platform network access security assessment and the standards for the network security level protection assessment.

[0090] The current status of cloud security released by the Cloud Security Alliance points out that the main cloud security issues are threats such as data leakage, data vulnerabilities, account hijacking, and system vulnerabilities. Due to the large amount of multi-source heterogeneous data generated by access devices, applications, and virtual machines in the cloud platform, traditional security mechanisms will generate a large number of irrelevant alarms, and it is difficult for security managers to judge the situation of the cloud environment from the overall perspective of cloud security. In order to solve the bottleneck problem of the identification and defense of massive attacks by the traditional passive defense mechanism of the enterprise, an embodiment of the present invention proposes a method for assessing the security situation of the enterprise cloud based on situation awareness, which can realize the security situation assessment and prediction of the enterprise cloud environment, and provide a reference plan for early security assessment to ensure the security of the enterprise cloud environment and reduce the occurrence of security threat events such as information leakage, asset vulnerabilities, and account hijacking, so as to propose more effective attack defense strategies or defense methods.

[0091] In a second aspect, an embodiment of the present invention provides an enterprise cloud security situation assessment device, see Figure 4 , the device 100 comprises:

[0092] The data acquisition module 110 is used to acquire the network security data of the enterprise cloud; wherein the network security data includes the asset value, vulnerability event information, warning event information and threat event information of the enterprise cloud;

[0093] A first calculation module 120 is used to calculate the situation index of each device in the enterprise cloud according to the network security data; wherein the situation index includes a score corresponding to the asset value, a vulnerability risk calculated according to the vulnerability event information, an alarm risk calculated according to the alarm event information, and a threat attack risk calculated according to the threat event information;

[0094] The second calculation module 140 is used to calculate the asset risk index of each device according to the status indicator of the device;

[0095] The third calculation module 150 is used to calculate the system risk index of the enterprise cloud according to each asset risk index corresponding to each device in the enterprise cloud.

[0096] In one embodiment, the second calculation module is specifically used to calculate the asset risk index of each device using a first calculation formula, wherein the first calculation formula includes:

[0097]

[0098] Among them, MIN() is the minimum function, A is the weight of vulnerability risk, B is the weight of warning risk, C is the weight of threat attack risk, A>B>C.

[0099] In one embodiment, the vulnerability event information includes the number of vulnerability events and scores corresponding to the severity of the vulnerability events; correspondingly, the vulnerability risk is the product of the number of vulnerability events and the scores corresponding to the severity of the vulnerability events.

[0100] In one embodiment, the alarm event information includes the number of alarm events and scores corresponding to the severity of the alarm events; correspondingly, the alarm risk is the product of the number of alarm events and the scores corresponding to the severity of the alarm events.

[0101] In one embodiment, the threat attack information includes the number of threat events and the scores corresponding to the severity of the threat events; correspondingly, the threat attack risk is the product of the number of threat events and the scores corresponding to the severity of the threat events.

[0102] In one embodiment, the third calculation module includes:

[0103] A first determining unit is used to determine the asset risk level of each device according to the asset risk index of the device;

[0104] The first calculation unit is used to calculate the average value of the asset risk index of each device corresponding to the same asset risk level to obtain the average asset risk index corresponding to the asset risk level;

[0105] The second calculation unit is used to calculate the system risk index of the enterprise cloud according to each average asset risk index corresponding to each asset risk level.

[0106] In one embodiment, the second calculation unit is specifically used to: calculate the system risk index of the enterprise cloud using a second calculation formula, and the second calculation formula is: the system risk index of the enterprise cloud = (the average asset risk index corresponding to the critical asset risk level * a + the average asset risk index corresponding to the high-risk asset risk level * b + the average asset risk index corresponding to the medium-risk asset risk level * c + the average asset risk index corresponding to the low-risk asset risk level * d) / (a ​​+ b + c + d);

[0107] Among them, the asset risk levels of critical, high risk, medium risk and low are from high to low, a is the weight of the critical asset risk level, b is the weight of the high risk asset risk level, c is the weight of the medium risk asset risk level, d is the weight of the low risk asset risk level, and a>b>c>d.

[0108] In one embodiment, the device may further include:

[0109] A first determination module is used to determine a time series formed by the asset risk index corresponding to each device in the enterprise cloud at each time point in a recent time period;

[0110] A risk presetting module is used to input the time series corresponding to each device into a pre-trained cloud security situation prediction model to obtain a risk prediction result of the device at a preset time point in the future; wherein the cloud security situation prediction model is a model trained based on a long short-term memory neural network;

[0111] The risk push module is used to screen out devices with security risks according to the risk prediction results corresponding to each device, generate push messages based on each device with security risks, and push the push messages to operation and maintenance personnel so that the operation and maintenance personnel can take security protection measures in advance for each device with security risks.

[0112] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents in the device provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0113] In a third aspect, an embodiment of the present invention provides a computer-readable medium, on which computer instructions are stored. When the computer instructions are executed by a processor, the processor executes the method provided in the first aspect.

[0114] Specifically, a system or device equipped with a storage medium can be provided, on which software program code that implements the functions of any of the above-mentioned embodiments is stored, and a computer (or CPU or MPU) of the system or device can be enabled to read and execute the program code stored in the storage medium.

[0115] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0116] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0117] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0118] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0119] It is understandable that the explanation, specific implementation methods, beneficial effects, examples, etc. of the relevant contents in the computer-readable medium provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0120] In a fourth aspect, an embodiment of the present specification provides a computing device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the method in any embodiment of the specification.

[0121] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents in the computing device provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0122] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0123] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the present invention can be implemented by hardware, software, widgets, or any combination thereof. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0124] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for assessing enterprise cloud security situation. It is characterized in that include: Acquire network security data of the enterprise cloud; wherein the network security data includes asset value, vulnerability event information, alarm event information, and threat event information of the enterprise cloud; Calculate the situation index of each device in the enterprise cloud according to the network security data; wherein the situation index includes a score corresponding to the asset value, a vulnerability risk calculated according to the vulnerability event information, an alarm risk calculated according to the alarm event information, and a threat attack risk calculated according to the threat event information; Calculate the asset risk index of each device based on its status indicators; The system risk index of the enterprise cloud is calculated according to each asset risk index corresponding to each device in the enterprise cloud.

2. The method according to claim 1, It is characterized in that The asset risk index of each device is calculated based on the status indicator of the device, including: The asset risk index of each device is calculated using a first calculation formula, wherein the first calculation formula includes: Among them, MIN() is the minimum function, A is the weight of vulnerability risk, B is the weight of warning risk, C is the weight of threat attack risk, A>B>C.

3. The method according to claim 1, It is characterized in that The vulnerability event information includes the number of vulnerability events and the scores corresponding to the severity of the vulnerability events; correspondingly, the vulnerability risk is the product of the number of vulnerability events and the scores corresponding to the severity of the vulnerability events.

4. The method according to claim 1, It is characterized in that The alarm event information includes the number of alarm events and the scores corresponding to the severity of the alarm events; correspondingly, the alarm risk is the product of the number of alarm events and the scores corresponding to the severity of the alarm events; And / or, the threat attack information includes the number of threat events and the scores corresponding to the severity of the threat events; correspondingly, the threat attack risk is the product of the number of threat events and the scores corresponding to the severity of the threat events.

5. The method according to claim 1, It is characterized in that The calculating the system risk index of the enterprise cloud according to each asset risk index corresponding to each device in the enterprise cloud includes: Determine the asset risk level of each device based on its asset risk index; Calculate the average value of the asset risk index of each device corresponding to the same asset risk level to obtain the average asset risk index corresponding to the asset risk level; The system risk index of the enterprise cloud is calculated according to each average asset risk index corresponding to each asset risk level.

6. The method according to claim 5, It is characterized in that The calculating the system risk index of the enterprise cloud according to each average asset risk index corresponding to each asset risk level includes: The system risk index of the enterprise cloud is calculated using a second calculation formula, where the second calculation formula is: The system risk index of the enterprise cloud = (the average asset risk index corresponding to the critical asset risk level * a + the average asset risk index corresponding to the high-risk asset risk level * b + the average asset risk index corresponding to the medium-risk asset risk level * c + the average asset risk index corresponding to the low-risk asset risk level * d) / (a ​​+ b + c + d); Among them, the asset risk levels of critical, high risk, medium risk and low are from high to low, a is the weight of the critical asset risk level, b is the weight of the high risk asset risk level, c is the weight of the medium risk asset risk level, d is the weight of the low risk asset risk level, and a>b>c>d.

7. The method according to claim 1, It is characterized in that The method further comprises: Determine a time series formed by the asset risk index corresponding to each device in the enterprise cloud at each time point in a recent time period; Input the time series corresponding to each device into a pre-trained cloud security situation prediction model to obtain a risk prediction result of the device at a preset time point in the future; wherein the cloud security situation prediction model is a model trained based on a long short-term memory neural network; According to the risk prediction results corresponding to each device, the devices with security risks are screened out, push messages are generated according to the devices with security risks, and the push messages are pushed to the operation and maintenance personnel, so that the operation and maintenance personnel can take security protection measures in advance for the devices with security risks.

8. An enterprise cloud security situation assessment device, It is characterized in that include: A data acquisition module, used to acquire network security data of the enterprise cloud; wherein the network security data includes asset value, vulnerability event information, alarm event information and threat event information of the enterprise cloud; A first calculation module is used to calculate the situation index of each device in the enterprise cloud according to the network security data; wherein the situation index includes a score corresponding to the asset value, a vulnerability risk calculated according to the vulnerability event information, an alarm risk calculated according to the alarm event information, and a threat attack risk calculated according to the threat event information; The second calculation module is used to calculate the asset risk index of each device according to the situation index of the device; The third calculation module is used to calculate the system risk index of the enterprise cloud according to each asset risk index corresponding to each device in the enterprise cloud.

9. A computer-readable storage medium, It is characterized in that A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

10. A computing device, It is characterized in that The method comprises a memory and a processor, wherein the memory stores executable codes, and when the processor executes the executable codes, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Method and a device for calculating a regional production risk index

    CN109583732A

  • Risk assessment method and assessment system for power business system

    CN110033202A

  • Financial risk index prediction model construction method and device and risk situation prediction method and device

    CN111429006A

  • Enterprise security analysis system and method based on big data, and medium

    CN118333405A

Cited By

  • Information security level protection evaluation system and method

    CN120012107A

  • Multi-technology fusion network security health assessment method and system

    CN120151026A

  • A multi-technology fusion network security health assessment method and system

    CN120151026B