A network security management system based on massive data computing

By adopting huge data calculation and comprehensive analysis models in the network security management system, the efficiency and accuracy of existing systems in data processing and attack intention identification are solved, and a fast response and continuous security network environment is achieved.

CN118713941BActive Publication Date: 2024-11-01FUJIAN BIG DATA PRIMARY DEV CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411208138.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-11-01
Estimated Expiration
2044-08-30

AI Technical Summary

Technical Problem

The existing network security management system is inefficient in processing and analyzing massive data, making it difficult to accurately identify the attacker's true intentions and attack paths, and has shortcomings in comprehensive assessment and emergency response, so it is impossible to quickly and accurately evaluate the network security status.

Method used

Using a network security management system based on huge amounts of data calculation, the data is divided into sub-data areas through the network security data area division module, combined with spoof signal data and real environment monitoring data for in-depth analysis, establish a comprehensive analysis model to calculate the comprehensive anomaly index, and realize Accurate identification and rapid response to spoofed signals.

Benefits of technology

It improves network security defense capabilities and emergency response speed, can quickly locate and analyze problem areas, provide scientific basis to evaluate the effectiveness of deception strategies, and promptly send out early warning signals to ensure the continuous security and stability of the network environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118713941B_ABST
    Figure CN118713941B_ABST
Patent Text Reader

Abstract

The present invention discloses a network security management system based on massive data calculation, which specifically relates to the field of network security, including a network security data area division module, a deception signal data acquisition module, a deception signal data analysis module, a real environment monitoring data acquisition module, a real environment monitoring data analysis module, a comprehensive analysis module, and a control module. The present invention can not only accurately identify potential network security threats and improve the pertinence and effectiveness of security protection, but also realize automatic judgment and instant warning of network security status through intelligent collaboration between the comprehensive analysis module and the control module, thereby greatly improving the emergency response speed and overall defense capability of network security. In general, the present invention provides a more scientific and efficient technical solution for the field of network security management while overcoming the shortcomings of the prior art.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of network security technology, and more specifically, to a network security management system based on massive data calculation. Background Art

[0002] As an important part of the field of information technology, network security has become increasingly complex and diverse with the popularization of the Internet and the rapid development of technology. The requirements for network security management systems are also becoming higher and higher. Among them, deception defense technology, as an active defense method, builds a false network environment and bait to induce attackers to expose their attack intentions and methods, thereby providing strong support for security protection.

[0003] Existing network security management systems, especially those involving deception defense technology, usually follow the following operating process: first, deploy false resources or information in the network, such as bait files, fake services, etc.; second, monitor the interaction of these false resources or information and collect the attacker's behavior data; then, analyze the collected data to identify potential attack behaviors or patterns; finally, take corresponding protective measures based on the analysis results, such as blocking the attack path, issuing early warning signals, etc.

[0004] However, there are still some shortcomings in its actual use. For example, although the existing deception defense technology has improved the network security protection capability to a certain extent, there are still many deficiencies. First, the existing system is often difficult to efficiently process and analyze massive data, which makes it difficult to detect potential security threats in a timely manner; secondly, in the analysis and identification of deception signals, the existing system lacks sufficient depth and precision, and it is difficult to accurately judge the attacker's true intentions and attack paths; in addition, the existing system also has deficiencies in comprehensive evaluation and emergency response, and is unable to quickly and accurately evaluate the network security status and take corresponding emergency measures. Therefore, the present invention is proposed to overcome these deficiencies, by comprehensively using technical means such as big data processing, intelligent analysis and comprehensive control, to achieve accurate identification, efficient analysis and immediate response to deception signals, thereby greatly improving the network security defense capability and emergency response speed. Summary of the invention

[0005] In order to overcome the above defects of the prior art, an embodiment of the present invention provides a network security management system based on massive data computing, which solves the problems raised in the above background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solution: a network security management system based on massive data computing, comprising:

[0007] Network security data area division module: used to determine the network security data of the target enterprise network as the target data area, divide the target data area into various sub-data areas by equal time division, and mark them as 1, 2...n in sequence;

[0008] Deception signal data collection module: used to collect deception bait interaction data, deception environment response data and deception strategy effect data of each sub-data area, and transmit the collected data to the deception signal data analysis module;

[0009] Deception signal data analysis module: including a deception bait interaction data analysis unit, a deception environment response data analysis unit and a deception strategy effect data analysis unit, used to analyze the data transmitted by the deception signal data acquisition module and transmit the analysis results to the comprehensive analysis module;

[0010] Real environment monitoring data collection module: used to collect system log abnormal data, network traffic abnormal data and host behavior monitoring data of each sub-data area, and transmit the collected data to the real environment monitoring data analysis module;

[0011] Real environment monitoring data analysis module: including system log abnormal data analysis unit, network traffic abnormal data analysis unit and host behavior monitoring data analysis unit, used to analyze the data transmitted by the real environment monitoring data acquisition module and transmit the analysis results to the comprehensive analysis module;

[0012] Comprehensive analysis module: used to establish a comprehensive analysis model, import the data transmitted by the deception signal data analysis module and the real environment monitoring data analysis module into the comprehensive analysis model, calculate the comprehensive abnormality index of the target data area, and transmit it to the control module;

[0013] Control module: judge the comprehensive anomaly index of the target data area by establishing a preset value of the comprehensive anomaly index, analyze the network security status of the target enterprise network based on the judgment result, and send a control signal based on the network security status of the target enterprise network.

[0014] Preferably, the deception bait interaction data includes the number of bait file accesses, the number of connection attempts to the bait network service, the malicious behavior trigger rate after the bait information response, and the abnormal login attempt frequency on the bait system, which are specifically expressed as Bv, Bc, Bt, and Bf; the deception environment response data includes the simulated system response delay time, the rate of change of the number of attacks after the false information is returned, the number of malicious IPs captured in the deception environment, and the abnormal fluctuation range of the traffic in the deception environment, which are marked as Rd, Ra, Rs, and Rv respectively; the deception strategy effect data includes the attack detection rate after the strategy is implemented, the attack path change rate before and after the strategy adjustment, the attacker misjudgment rate under the deception strategy, and the percentage reduction of the potential attack surface covered by the strategy, which are marked as Td, Tr, Tm, and Te respectively.

[0015] Preferably, the deception bait interaction data analysis unit is used to establish a deception bait interaction data analysis model, import the deception bait interaction data transmitted by the deception signal data acquisition module into the deception bait interaction data analysis model, and calculate the deception bait effectiveness value of each sub-data area, which is specifically expressed as: , S.B. i represents the deception bait effectiveness value of the ith sub-data region, Bv i represents the number of times the decoy file is accessed in the ith sub-data area, Bc i represents the number of connection attempts of the decoy network service in the ith sub-data area, Bt i represents the malicious behavior triggering rate after the bait information response of the i-th sub-data area, Bf i represents the frequency of abnormal login attempts on the decoy system of the i-th sub-data area, and n represents the number of sub-data areas.

[0016] Preferably, the deception environment response data analysis unit is used to establish a deception environment response data analysis model, import the deception environment response data transmitted by the deception signal data acquisition module into the deception environment response data analysis model, and calculate the deception environment effectiveness value of each sub-data area, which is specifically expressed as: , SR i Rd represents the deception environment effectiveness value of the ith sub-data area. i represents the simulation system response delay time of the ith sub-data area, Ra i Rs represents the change rate of the number of attacks after the false information of the i-th sub-data area is returned. i Rv represents the number of malicious IPs trapped in the deception environment of the i-th sub-data area, i Rv represents the abnormal fluctuation amplitude of traffic in the deception environment of the i-th sub-data area, max It indicates the abnormal fluctuation amplitude of traffic in the maximum deception environment of the target data area, and n indicates the number of sub-data areas.

[0017] Preferably, the deception strategy effect data analysis unit is used to establish a deception strategy effect data analysis model, import the deception strategy effect data transmitted by the deception signal data acquisition module into the deception strategy effect data analysis model, and calculate the deception strategy effectiveness value of each sub-data area, which is specifically expressed as: ,ST i represents the effectiveness value of the deception strategy in the ith sub-data region, Td i represents the attack detection rate after the strategy is implemented in the i-th sub-data area, Tr i Tm represents the attack path change rate before and after the strategy adjustment of the i-th sub-data area. i represents the attacker's misjudgment rate under the deception strategy of the i-th sub-data area, Te i It represents the percentage reduction of potential attack surface covered by the deception strategy for the i-th sub-data area, and n represents the number of sub-data areas.

[0018] Preferably, the deception signal data analysis module calculates the deception signal comprehensive characteristic value of the i-th sub-data area through the deception bait effectiveness value of the i-th sub-data area, the deception environment effectiveness value of the i-th sub-data area, and the deception strategy effectiveness value of the i-th sub-data area, which is specifically expressed as: , κ i Represents the comprehensive characteristic value of the deception signal in the i-th sub-data area.

[0019] Preferably, the system log abnormal data includes the number of abnormal login events in the log, the number of unknown process startups in the system log, the proportion of unauthorized file access recorded in the log, and the frequency of suspicious command execution detected in the log, which are marked as Le, Lu, Ld, and Lf respectively; the network traffic abnormal data includes the proportion of abnormal data packets in the network traffic, the number of network connection requests from unknown sources, the number of DDoS attack attempts in the network traffic, and the ratio of abnormal traffic peak to normal traffic, which are marked as Ep, Es, Ed, and Ex respectively; the host behavior monitoring data includes the number of unexpected external connections on the host, the number of abnormal host resource consumption events, the malware detection rate on the host, and the number of disguised process intrusions, which are marked as Hb, Hl, Hd, and Hu respectively.

[0020] Preferably, the system log abnormal data analysis unit is used to establish a system log abnormal data analysis model, import the system log abnormal data transmitted by the real environment monitoring data acquisition module into the system log abnormal data analysis model, and calculate the system log risk assessment value of each sub-data area, which is specifically expressed as: , M.T. i Le represents the system log risk assessment value of the ith sub-data area, irepresents the number of abnormal login events in the log of the ith sub-data area, Lu i Indicates the number of unknown process starts in the system log of the i-th sub-data area, Ld i represents the proportion of unauthorized file access in the log records of the ith sub-data area, Lf i Lf represents the execution frequency of suspicious commands detected in the log of the ith sub-data area. max Indicates the maximum suspicious command execution frequency detected in the log of the target data area, Lf min Indicates the minimum suspicious command execution frequency detected in the log of the target data area, and n indicates the number of sub-data areas.

[0021] Preferably, the network traffic anomaly data analysis unit is used to establish a network traffic anomaly data analysis model, import the network traffic anomaly data transmitted by the real environment monitoring data acquisition module into the network traffic anomaly data analysis model, and calculate the network traffic risk assessment value of each sub-data area, which is specifically expressed as: , M.E. i represents the network traffic risk assessment value of the ith sub-data area, Ep i Es represents the proportion of abnormal data packets in the network traffic of the ith sub-data area. i Indicates the number of network connection requests from unknown sources in the i-th sub-data area, Ed i represents the number of DDoS attack attempts in the network traffic of the ith sub-data area, Ex i It represents the ratio of the abnormal traffic peak value to the normal traffic of the ith sub-data area, and n represents the number of sub-data areas.

[0022] Preferably, the host behavior monitoring data analysis unit is used to establish a host behavior monitoring data analysis model, import the host behavior monitoring data transmitted by the real environment monitoring data acquisition module into the host behavior monitoring data analysis model, and calculate the host behavior risk assessment value of each sub-data area, which is specifically expressed as: , M.H. i Hb represents the host behavior risk assessment value of the ith sub-data area, i Indicates the number of unexpected external connections on the host of the ith sub-data area, Hl i Indicates the number of abnormal host resource consumption events in the i-th sub-data area, Hd i represents the malware detection rate on the host in the ith sub-data area, Hu i represents the number of times the masquerading process invades the i-th sub-data area, and n represents the number of sub-data areas.

[0023] Preferably, the real environment monitoring data analysis module calculates the real environment comprehensive risk assessment value of the i-th sub-data area through the system log risk assessment value of the i-th sub-data area, the network traffic risk assessment value of the i-th sub-data area, and the host behavior risk assessment value of the i-th sub-data area, which is specifically expressed as: , τ i Represents the real environmental comprehensive risk assessment value of the i-th sub-data area.

[0024] Preferably, the comprehensive analysis model is specifically expressed as: , η represents the comprehensive anomaly index of the target data area, κ i represents the comprehensive characteristic value of the deception signal of the ith sub-data region, τ i represents the comprehensive risk assessment value of the real environment of the i-th sub-data area, β1 represents the weight of the comprehensive characteristic value of the deception signal, β2 represents the weight of the comprehensive risk assessment value of the real environment, λ represents other influencing factors of the comprehensive anomaly index, and n represents the number of sub-data areas.

[0025] Preferably, the preset value of the comprehensive abnormality index is marked as η Def , when η Def >η, it means that the comprehensive anomaly index of the target data area is less than the preset value of the comprehensive anomaly index, indicating that the network security status of the target enterprise network is good, then the collection and analysis of the deception signal data and the real environment monitoring data shall be maintained. Def When <η, it means that the comprehensive anomaly index of the target data area is greater than the preset value of the comprehensive anomaly index, indicating that the network security status of the target enterprise network is poor, and an early warning signal is sent to the management terminal.

[0026] Technical effects and advantages of the present invention:

[0027] The present invention divides the network security data of the target enterprise network into multiple sub-data areas through a network security data area division module, so that data analysis and management are more refined and organized, which helps to quickly locate and analyze problem areas, thereby improving processing speed and efficiency; the deception signal data acquisition module collects deception bait interaction data, deception environment response data and deception strategy effect data of each sub-data area, providing a comprehensive and accurate data basis for subsequent deception signal analysis. These data can truly reflect the behavior and strategy of the attacker and help identify potential security threats; the deception signal data analysis module conducts in-depth analysis of the deception signal data, calculates the deception bait effectiveness value, deception environment effectiveness value and deception strategy effectiveness value of each sub-data area, and then obtains the deception signal comprehensive characteristic value, which provides a scientific basis for evaluating the effectiveness and optimization of the deception strategy, and helps to improve the pertinence and effectiveness of network security protection; the real environment monitoring data acquisition module collects system log abnormal data, network traffic abnormal data and host behavior monitoring data, ensuring comprehensive monitoring of the real network environment. These data can timely discover and report potential security incidents, which is a good basis for rapid response and disposal It provides strong support; through the analysis of the real environment monitoring data analysis module on the real environment monitoring data, the system log risk assessment value, network traffic risk assessment value and host behavior risk assessment value of each sub-data area are calculated, and then the real environment comprehensive risk assessment value is obtained, which provides an important basis for evaluating the security status of the entire network environment and helps enterprises to formulate more scientific and reasonable network security strategies; through the comprehensive analysis module, a comprehensive analysis model is established, and the deception signal data analysis results and the real environment monitoring data analysis results are combined to calculate the comprehensive anomaly index of the target data area, which can comprehensively reflect the overall status of network security and provide managers with intuitive security situation awareness. At the same time, according to the judgment results of the comprehensive anomaly index, the control module can send corresponding control signals to achieve rapid response and disposal of security incidents; through the control module, a comprehensive anomaly index preset value is established to judge the comprehensive anomaly index of the target data area, and the network security status of the target enterprise network is analyzed according to the judgment results. When the network security status is found to be poor, an early warning signal can be sent to the management terminal in time, thereby prompting the enterprise to take necessary security measures to ensure the continuous security and stability of the network environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] refer to Figure 1 A network security management system based on massive data computing is shown, including a network security data area division module, a deception signal data acquisition module, a deception signal data analysis module, a real environment monitoring data acquisition module, a real environment monitoring data analysis module, a comprehensive analysis module, and a control module.

[0031] The network security data area division module is used to determine the network security data of the target enterprise network as the target data area, divide the target data area into various sub-data areas by equal time division, and mark them as 1, 2...n in sequence.

[0032] The deception signal data collection module is used to collect deception bait interaction data, deception environment response data and deception strategy effect data of each sub-data area, and transmit the collected data to the deception signal data analysis module.

[0033] The deception bait interaction data includes the number of bait file accesses, the number of connection attempts to the bait network service, the malicious behavior triggering rate after the bait information response, and the abnormal login attempt frequency on the bait system, specifically represented as Bv, Bc, Bt, and Bf. The deception environment response data includes the simulated system response delay time, the rate of change of the number of attacks after the false information is returned, the number of malicious IPs captured in the deception environment, and the abnormal fluctuation range of traffic in the deception environment, respectively marked as Rd, Ra, Rs, and Rv. The deception strategy effect data includes the attack detection rate after the strategy is implemented, the attack path change rate before and after the strategy adjustment, the attacker misjudgment rate under the deception strategy, and the percentage reduction of the potential attack surface covered by the strategy, respectively marked as Td, Tr, Tm, and Te.

[0034] It should be specifically explained in this embodiment that the false information in the rate of change of the number of attacks after the false information is returned specifically refers to untrue data or information constructed and displayed to the attacker by the system in order to deceive or monitor the attacker. This information is designed to induce the attacker to expose his attack behavior, thereby providing support for the security protection of the system.

[0035] The deception signal data analysis module includes a deception bait interaction data analysis unit, a deception environment response data analysis unit and a deception strategy effect data analysis unit, which are used to analyze the data transmitted by the deception signal data acquisition module and transmit the analysis results to the comprehensive analysis module.

[0036] The deception bait interaction data analysis unit is used to establish a deception bait interaction data analysis model, import the deception bait interaction data transmitted by the deception signal data acquisition module into the deception bait interaction data analysis model, and calculate the deception bait effectiveness value of each sub-data area, which is specifically expressed as: , S.B. i represents the deception bait effectiveness value of the ith sub-data region, Bv i represents the number of times the decoy file is accessed in the ith sub-data area, Bc i represents the number of connection attempts of the decoy network service in the ith sub-data area, Bt i represents the malicious behavior triggering rate after the bait information response of the i-th sub-data area, Bf i represents the frequency of abnormal login attempts on the decoy system of the i-th sub-data area, and n represents the number of sub-data areas.

[0037] The deception environment response data analysis unit is used to establish a deception environment response data analysis model, import the deception environment response data transmitted by the deception signal data acquisition module into the deception environment response data analysis model, and calculate the deception environment effectiveness value of each sub-data area, which is specifically expressed as: , SR i Rd represents the deception environment effectiveness value of the ith sub-data area. i represents the simulation system response delay time of the ith sub-data area, Ra i Rs represents the change rate of the number of attacks after the false information of the i-th sub-data area is returned. i Rv represents the number of malicious IPs trapped in the deception environment of the i-th sub-data area, i Rv represents the abnormal fluctuation amplitude of traffic in the deception environment of the i-th sub-data area, max It indicates the abnormal fluctuation amplitude of traffic in the maximum deception environment of the target data area, and n indicates the number of sub-data areas.

[0038] The deception strategy effect data analysis unit is used to establish a deception strategy effect data analysis model, import the deception strategy effect data transmitted by the deception signal data acquisition module into the deception strategy effect data analysis model, and calculate the deception strategy effectiveness value of each sub-data area, which is specifically expressed as: ,ST i represents the effectiveness value of the deception strategy in the ith sub-data region, Td irepresents the attack detection rate after the strategy is implemented in the i-th sub-data area, Tr i Tm represents the attack path change rate before and after the strategy adjustment of the i-th sub-data area. i represents the attacker's misjudgment rate under the deception strategy of the i-th sub-data area, Te i It represents the percentage reduction of potential attack surface covered by the deception strategy for the i-th sub-data area, and n represents the number of sub-data areas.

[0039] The deception signal data analysis module calculates the deception signal comprehensive characteristic value of the ith sub-data area through the deception bait effectiveness value of the ith sub-data area, the deception environment effectiveness value of the ith sub-data area, and the deception strategy effectiveness value of the ith sub-data area, which is specifically expressed as: , κ i Represents the comprehensive characteristic value of the deception signal in the i-th sub-data area.

[0040] The real environment monitoring data acquisition module is used to collect system log abnormal data, network traffic abnormal data and host behavior monitoring data of each sub-data area, and transmit the collected data to the real environment monitoring data analysis module.

[0041] The system log abnormal data includes the number of abnormal login events in the log, the number of unknown process startups in the system log, the proportion of unauthorized file access recorded in the log, and the frequency of suspicious command execution detected in the log, which are marked as Le, Lu, Ld, and Lf respectively. The network traffic abnormal data includes the proportion of abnormal data packets in the network traffic, the number of network connection requests from unknown sources, the number of DDoS attack attempts in the network traffic, and the ratio of abnormal traffic peak to normal traffic, which are marked as Ep, Es, Ed, and Ex respectively. The host behavior monitoring data includes the number of unexpected external connections on the host, the number of abnormal host resource consumption events, the malware detection rate on the host, and the number of disguised process intrusions, which are marked as Hb, Hl, Hd, and Hu respectively.

[0042] The real environment monitoring data analysis module includes a system log abnormal data analysis unit, a network traffic abnormal data analysis unit and a host behavior monitoring data analysis unit, which are used to analyze the data transmitted by the real environment monitoring data acquisition module and transmit the analysis results to the comprehensive analysis module.

[0043] The system log abnormal data analysis unit is used to establish a system log abnormal data analysis model, import the system log abnormal data transmitted by the real environment monitoring data acquisition module into the system log abnormal data analysis model, and calculate the system log risk assessment value of each sub-data area, which is specifically expressed as: , M.T. iLe represents the system log risk assessment value of the ith sub-data area, i represents the number of abnormal login events in the log of the ith sub-data area, Lu i Indicates the number of unknown process starts in the system log of the i-th sub-data area, Ld i represents the proportion of unauthorized file access in the log records of the ith sub-data area, Lf i Lf represents the execution frequency of suspicious commands detected in the log of the ith sub-data area. max Indicates the maximum suspicious command execution frequency detected in the log of the target data area, Lf min Indicates the minimum suspicious command execution frequency detected in the log of the target data area, and n indicates the number of sub-data areas.

[0044] The network traffic anomaly data analysis unit is used to establish a network traffic anomaly data analysis model, import the network traffic anomaly data transmitted by the real environment monitoring data acquisition module into the network traffic anomaly data analysis model, and calculate the network traffic risk assessment value of each sub-data area, which is specifically expressed as: , M.E. i represents the network traffic risk assessment value of the ith sub-data area, Ep i Es represents the proportion of abnormal data packets in the network traffic of the ith sub-data area. i Indicates the number of network connection requests from unknown sources in the i-th sub-data area, Ed i represents the number of DDoS attack attempts in the network traffic of the ith sub-data area, Ex i It represents the ratio of the abnormal traffic peak value to the normal traffic of the ith sub-data area, and n represents the number of sub-data areas.

[0045] The host behavior monitoring data analysis unit is used to establish a host behavior monitoring data analysis model, import the host behavior monitoring data transmitted by the real environment monitoring data acquisition module into the host behavior monitoring data analysis model, and calculate the host behavior risk assessment value of each sub-data area, which is specifically expressed as: , M.H. i Hb represents the host behavior risk assessment value of the ith sub-data area, i Indicates the number of unexpected external connections on the host of the ith sub-data area, Hl i Indicates the number of abnormal host resource consumption events in the i-th sub-data area, Hd i represents the malware detection rate on the host in the ith sub-data area, Hu i represents the number of times the masquerading process invades the i-th sub-data area, and n represents the number of sub-data areas.

[0046] The real environment monitoring data analysis module calculates the real environment comprehensive risk assessment value of the ith sub-data area through the system log risk assessment value of the ith sub-data area, the network traffic risk assessment value of the ith sub-data area, and the host behavior risk assessment value of the ith sub-data area, which is specifically expressed as: , τ i Represents the real environmental comprehensive risk assessment value of the i-th sub-data area.

[0047] The comprehensive analysis module is used to establish a comprehensive analysis model, import the data transmitted by the deception signal data analysis module and the real environment monitoring data analysis module into the comprehensive analysis model, calculate the comprehensive abnormality index of the target data area, and transmit it to the control module.

[0048] The comprehensive analysis model is specifically expressed as: , η represents the comprehensive anomaly index of the target data area, κ i represents the comprehensive characteristic value of the deception signal of the ith sub-data region, τ i represents the comprehensive risk assessment value of the real environment of the i-th sub-data area, β1 represents the weight of the comprehensive characteristic value of the deception signal, β2 represents the weight of the comprehensive risk assessment value of the real environment, λ represents other influencing factors of the comprehensive anomaly index, and n represents the number of sub-data areas.

[0049] The control module determines the comprehensive anomaly index of the target data area by establishing a preset value of the comprehensive anomaly index, analyzes the network security status of the target enterprise network according to the determination result, and sends a control signal according to the network security status of the target enterprise network.

[0050] The preset value of the comprehensive abnormality index is marked as η Def , when η Def >η, it means that the comprehensive anomaly index of the target data area is less than the preset value of the comprehensive anomaly index, indicating that the network security status of the target enterprise network is good, then the collection and analysis of the deception signal data and the real environment monitoring data shall be maintained. Def When <η, it means that the comprehensive anomaly index of the target data area is greater than the preset value of the comprehensive anomaly index, indicating that the network security status of the target enterprise network is poor, and an early warning signal is sent to the management terminal.

[0051] The present invention divides the network security data of the target enterprise network into multiple sub-data areas through a network security data area division module, so that data analysis and management are more refined and organized, which helps to quickly locate and analyze problem areas, thereby improving processing speed and efficiency; the deception signal data acquisition module collects deception bait interaction data, deception environment response data and deception strategy effect data of each sub-data area, providing a comprehensive and accurate data basis for subsequent deception signal analysis. These data can truly reflect the behavior and strategy of the attacker and help identify potential security threats; the deception signal data analysis module conducts in-depth analysis of the deception signal data, calculates the deception bait effectiveness value, deception environment effectiveness value and deception strategy effectiveness value of each sub-data area, and then obtains the deception signal comprehensive characteristic value, which provides a scientific basis for evaluating the effectiveness and optimization of the deception strategy, and helps to improve the pertinence and effectiveness of network security protection; the real environment monitoring data acquisition module collects system log abnormal data, network traffic abnormal data and host behavior monitoring data, ensuring comprehensive monitoring of the real network environment. These data can timely discover and report potential security incidents, which is a good basis for rapid response and disposal It provides strong support; through the analysis of the real environment monitoring data analysis module on the real environment monitoring data, the system log risk assessment value, network traffic risk assessment value and host behavior risk assessment value of each sub-data area are calculated, and then the real environment comprehensive risk assessment value is obtained, which provides an important basis for evaluating the security status of the entire network environment and helps enterprises to formulate more scientific and reasonable network security strategies; through the comprehensive analysis module, a comprehensive analysis model is established, and the deception signal data analysis results and the real environment monitoring data analysis results are combined to calculate the comprehensive anomaly index of the target data area, which can comprehensively reflect the overall status of network security and provide managers with intuitive security situation awareness. At the same time, according to the judgment results of the comprehensive anomaly index, the control module can send corresponding control signals to achieve rapid response and disposal of security incidents; through the control module, a comprehensive anomaly index preset value is established to judge the comprehensive anomaly index of the target data area, and the network security status of the target enterprise network is analyzed according to the judgment results. When the network security status is found to be poor, an early warning signal can be sent to the management terminal in time, thereby prompting the enterprise to take necessary security measures to ensure the continuous security and stability of the network environment.

[0052] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0053] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A network security management system based on massive data computing, characterized in that: include: Network security data area division module: used to determine the network security data of the target enterprise network as the target data area, divide the target data area into various sub-data areas by equal time division, and mark them as 1, 2...n in sequence; Deception signal data collection module: used to collect deception bait interaction data, deception environment response data and deception strategy effect data of each sub-data area, and transmit the collected data to the deception signal data analysis module; Deception signal data analysis module: including a deception bait interaction data analysis unit, a deception environment response data analysis unit and a deception strategy effect data analysis unit, used to analyze the data transmitted by the deception signal data acquisition module and transmit the analysis results to the comprehensive analysis module; The deception bait interaction data analysis unit is used to establish a deception bait interaction data analysis model, import the deception bait interaction data transmitted by the deception signal data acquisition module into the deception bait interaction data analysis model, and calculate the deception bait effectiveness value of each sub-data area, which is specifically expressed as: , S.B. i represents the deception bait effectiveness value of the ith sub-data region, Bv i represents the number of times the decoy file is accessed in the ith sub-data area, Bc i represents the number of connection attempts of the decoy network service in the ith sub-data area, Bt i represents the malicious behavior triggering rate after the bait information response of the i-th sub-data area, Bf i represents the frequency of abnormal login attempts on the decoy system of the i-th sub-data area, and n represents the number of sub-data areas; The deception environment response data analysis unit is used to establish a deception environment response data analysis model, import the deception environment response data transmitted by the deception signal data acquisition module into the deception environment response data analysis model, and calculate the deception environment effectiveness value of each sub-data area, which is specifically expressed as: , SR i Rd represents the deception environment effectiveness value of the ith sub-data area. i represents the simulation system response delay time of the ith sub-data area, Ra i Rs represents the change rate of the number of attacks after the false information of the i-th sub-data area is returned. i Rv represents the number of malicious IPs trapped in the deception environment of the i-th sub-data area, i Rv represents the abnormal fluctuation amplitude of traffic in the deception environment of the i-th sub-data area, max It indicates the abnormal fluctuation amplitude of traffic in the maximum deception environment of the target data area, and n indicates the number of sub-data areas; The deception strategy effect data analysis unit is used to establish a deception strategy effect data analysis model, import the deception strategy effect data transmitted by the deception signal data acquisition module into the deception strategy effect data analysis model, and calculate the deception strategy effectiveness value of each sub-data area, which is specifically expressed as: ,ST i represents the effectiveness value of the deception strategy in the ith sub-data region, Td i represents the attack detection rate after the strategy is implemented in the i-th sub-data area, Tr i Tm represents the attack path change rate before and after the strategy adjustment of the i-th sub-data area. i represents the attacker's misjudgment rate under the deception strategy of the i-th sub-data area, Te i represents the percentage reduction of the potential attack surface covered by the deception strategy for the i-th sub-data area, and n represents the number of sub-data areas; The deception signal data analysis module calculates the deception signal comprehensive characteristic value of the ith sub-data area through the deception bait effectiveness value of the ith sub-data area, the deception environment effectiveness value of the ith sub-data area, and the deception strategy effectiveness value of the ith sub-data area, which is specifically expressed as: , κ i represents the comprehensive characteristic value of the deception signal of the i-th sub-data area; Real environment monitoring data collection module: used to collect system log abnormal data, network traffic abnormal data and host behavior monitoring data of each sub-data area, and transmit the collected data to the real environment monitoring data analysis module; Real environment monitoring data analysis module: including system log abnormal data analysis unit, network traffic abnormal data analysis unit and host behavior monitoring data analysis unit, used to analyze the data transmitted by the real environment monitoring data acquisition module and transmit the analysis results to the comprehensive analysis module; The system log abnormal data analysis unit is used to establish a system log abnormal data analysis model, import the system log abnormal data transmitted by the real environment monitoring data acquisition module into the system log abnormal data analysis model, and calculate the system log risk assessment value of each sub-data area, which is specifically expressed as: , M.T. i Le represents the system log risk assessment value of the ith sub-data area, i represents the number of abnormal login events in the log of the ith sub-data area, Lu i Indicates the number of unknown process starts in the system log of the i-th sub-data area, Ld i represents the proportion of unauthorized file access in the log records of the ith sub-data area, Lf i Lf represents the execution frequency of suspicious commands detected in the log of the ith sub-data area. max Indicates the maximum suspicious command execution frequency detected in the log of the target data area, Lf min Indicates the minimum suspicious command execution frequency detected in the log of the target data area, and n indicates the number of sub-data areas; The network traffic anomaly data analysis unit is used to establish a network traffic anomaly data analysis model, import the network traffic anomaly data transmitted by the real environment monitoring data acquisition module into the network traffic anomaly data analysis model, and calculate the network traffic risk assessment value of each sub-data area, which is specifically expressed as: , M.E. i represents the network traffic risk assessment value of the ith sub-data area, Ep i Es represents the proportion of abnormal data packets in the network traffic of the ith sub-data area. i Indicates the number of network connection requests from unknown sources in the i-th sub-data area, Ed i represents the number of DDoS attack attempts in the network traffic of the ith sub-data area, Ex i represents the ratio of the abnormal traffic peak value to the normal traffic of the ith sub-data area, and n represents the number of sub-data areas; The host behavior monitoring data analysis unit is used to establish a host behavior monitoring data analysis model, import the host behavior monitoring data transmitted by the real environment monitoring data acquisition module into the host behavior monitoring data analysis model, and calculate the host behavior risk assessment value of each sub-data area, which is specifically expressed as: , M.H. i Hb represents the host behavior risk assessment value of the ith sub-data area, i Indicates the number of unexpected external connections on the host of the ith sub-data area, Hl i Indicates the number of abnormal host resource consumption events in the i-th sub-data area, Hd i represents the malware detection rate on the host in the ith sub-data area, Hu i represents the number of times the masquerading process invades the i-th sub-data area, and n represents the number of sub-data areas; The real environment monitoring data analysis module calculates the real environment comprehensive risk assessment value of the i-th sub-data area through the system log risk assessment value of the i-th sub-data area, the network traffic risk assessment value of the i-th sub-data area, and the host behavior risk assessment value of the i-th sub-data area, which is specifically expressed as: , τ i represents the real environmental comprehensive risk assessment value of the ith sub-data area; Comprehensive analysis module: used to establish a comprehensive analysis model, import the data transmitted by the deception signal data analysis module and the real environment monitoring data analysis module into the comprehensive analysis model, calculate the comprehensive abnormality index of the target data area, and transmit it to the control module; The comprehensive analysis model is specifically expressed as: , η represents the comprehensive anomaly index of the target data area, κ i represents the comprehensive characteristic value of the deception signal of the ith sub-data region, τ i represents the comprehensive risk assessment value of the real environment of the ith sub-data area, β1 represents the weight of the comprehensive characteristic value of the deception signal, β2 represents the weight of the comprehensive risk assessment value of the real environment, λ represents other influencing factors of the comprehensive anomaly index, and n represents the number of sub-data areas; Control module: judge the comprehensive anomaly index of the target data area by establishing a preset value of the comprehensive anomaly index, analyze the network security status of the target enterprise network based on the judgment result, and send a control signal based on the network security status of the target enterprise network.

2. A network security management system based on massive data computing according to claim 1, characterized in that: The deception bait interaction data includes the number of bait file accesses, the number of connection attempts to the bait network service, the malicious behavior triggering rate after the bait information response, and the abnormal login attempt frequency on the bait system, specifically represented as Bv, Bc, Bt, and Bf. The deception environment response data includes the simulated system response delay time, the rate of change of the number of attacks after the false information is returned, the number of malicious IPs captured in the deception environment, and the abnormal fluctuation range of traffic in the deception environment, respectively marked as Rd, Ra, Rs, and Rv. The deception strategy effect data includes the attack detection rate after the strategy is implemented, the attack path change rate before and after the strategy adjustment, the attacker misjudgment rate under the deception strategy, and the percentage reduction of the potential attack surface covered by the strategy, respectively marked as Td, Tr, Tm, and Te.

3. A network security management system based on massive data computing according to claim 1, characterized in that: The system log abnormal data includes the number of abnormal login events in the log, the number of unknown process startups in the system log, the proportion of unauthorized file access recorded in the log, and the frequency of suspicious command execution detected in the log, which are marked as Le, Lu, Ld, and Lf respectively. The network traffic abnormal data includes the proportion of abnormal data packets in the network traffic, the number of network connection requests from unknown sources, the number of DDoS attack attempts in the network traffic, and the ratio of abnormal traffic peak to normal traffic, which are marked as Ep, Es, Ed, and Ex respectively. The host behavior monitoring data includes the number of unexpected external connections on the host, the number of abnormal host resource consumption events, the malware detection rate on the host, and the number of disguised process intrusions, which are marked as Hb, Hl, Hd, and Hu respectively.