Network attacker analysis method, device, electronic device and storage medium

By performing abnormal analysis and extraction of attack behavior characteristics of network security data, combined with the coordinated work of the cloud and edge, the identity traceability of the network attacker is realized, solving the problem of insufficient analysis depth in the existing technology, and improving the identity of the attacker Identify accuracy and network security.

CN118473827BActive Publication Date: 2024-11-19NAT IND INFORMATION SECURITY DEV RES CENT
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202410917362.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-10
Publication Date
2024-11-19
Estimated Expiration
2044-07-10

AI Technical Summary

Technical Problem

The lack of effective correlation analysis in the analysis of cyber attacks by the existing technology leads to insufficient analysis depth and low accuracy of the attacker's identity identification, especially in complex cyber attack scenarios.

Method used

By performing abnormal analysis of network security data, extracting attack behavior characteristics, identifying attack events, linking attack events with the same identity information, tracing the source, and combining the coordinated work of the cloud and the edge, the analysis accuracy and efficiency are improved.

Benefits of technology

Through the combined analysis of information of multiple attack events, the attacker's identity identification accuracy is improved, network security is enhanced, the time from discovery to disposal is shortened, and the targetedness of network protection policies is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118473827B_ABST
    Figure CN118473827B_ABST
Patent Text Reader

Abstract

The present application is applicable to the field of network security technology, and provides an analysis method, device, electronic device and storage medium for network attackers. The analysis method includes: performing abnormal analysis on network security data to identify multiple attack events; extracting the attack behavior characteristics of each attack event; determining the identity information of the network attacker according to the attack behavior characteristics, and each attack event corresponds to an identity information; performing correlation analysis on each attack event corresponding to the same identity information to obtain the information of the correlation event; tracing the network attacker for the corresponding identity information based on the information of the correlation event to obtain the tracing result. The present application can improve the accuracy of the analysis of the attacker by correlating different attack events with the same identity information, thereby combining and analyzing the information of multiple attack events.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of network security technology, and in particular, relates to an analysis method, device, electronic device and storage medium for network attackers. Background Art

[0002] With the rapid development of network technology, network attacks are becoming more frequent and more complex, posing a serious threat to network security. At present, the analysis of network attackers often relies on a single data source or analysis method, and lacks effective correlation analysis, which is insufficient in the depth of analysis. With the expansion of network scale and the diversification of attack methods, attackers can carry out attacks more covertly, making the identity analysis of attackers more difficult. Existing analysis methods show low accuracy when dealing with complex network attacks. Summary of the invention

[0003] The embodiments of the present application provide a method, device, electronic device and storage medium for analyzing network attackers, which can solve the problem of low accuracy in analyzing network attackers.

[0004] In a first aspect, an embodiment of the present application provides a method for analyzing a network attacker, including:

[0005] Perform anomaly analysis on network security data and identify multiple attack incidents;

[0006] Extracting attack behavior features of each of the attack events;

[0007] Determine the identity information of the network attacker according to the attack behavior characteristics, each attack event corresponds to one piece of identity information;

[0008] Performing correlation analysis on the attack events corresponding to the same identity information to obtain information on the correlated events;

[0009] Based on the information of the associated event, the corresponding identity information is traced back to the network attacker to obtain a tracing result.

[0010] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0011] Multiple attack events are obtained from network security data, and the identity information of the attacker corresponding to each attack event is obtained based on the attack behavior characteristics. Different attack events with the same identity information are associated, and the attacker is traced based on the associated multiple attack events. Therefore, the accuracy of the analysis of the attacker can be improved by combining the information of multiple attack events.

[0012] In a possible implementation manner of the first aspect, the step of performing correlation analysis on the attack events corresponding to the same identity information to obtain information of correlated events includes:

[0013] Classifying all the attack events according to the attack behavior characteristics, and generating an attack type for each of the attack events;

[0014] The attack behavior characteristics and the attack types of different attack events corresponding to the same identity information are associated with the identity information to obtain information of the associated event.

[0015] In the above scheme, attack events are classified by attack behavior characteristics, and attack types can more intuitively represent attack events, making it easier to associate different attack events.

[0016] In a possible implementation manner of the first aspect, the step of determining the identity information of the network attacker according to the attack behavior characteristics includes:

[0017] Matching the attack behavior characteristics of the network attacker with those of the historical attacker to obtain a matching value between the network attacker and the historical attacker;

[0018] When there is a match value greater than or equal to a preset threshold, the identity information of the historical attacker with the largest match value is determined as the identity information of the network attacker;

[0019] When the matching values ​​are all smaller than the preset threshold, the new identity information is determined to be the identity information of the network attacker.

[0020] In the above scheme, by using the information data of known historical attackers and comparing it with the characteristics of attack behavior, the identity information of the attacker can be quickly and accurately identified.

[0021] In a possible implementation manner of the first aspect, the step of extracting the attack behavior feature of each of the attack events includes:

[0022] Acquire attack information of each of the attack events; the attack information includes at least one of an attack tool, an attack technique, an attack time, a number of attacks, and an attack target;

[0023] The attack information is vectorized to obtain the attack behavior feature.

[0024] In the above scheme, the attack behavior characteristics directly represent the information such as the attacker's attack technology, attack tools, attack time, attack times and attack targets in the attack event, so that the extracted attack behavior characteristics are universal.

[0025] In a possible implementation manner of the first aspect, the step of performing anomaly analysis on network security data to identify multiple attack events includes:

[0026] Detecting abnormal information in the network security data;

[0027] An attack event is determined according to the abnormal information combination and an attack event library; the attack event library includes a plurality of the historical attack events, each of the historical attack events corresponds to one abnormal information combination, and each of the abnormal information combination includes at least one abnormal information.

[0028] In the above scheme, by utilizing one or more abnormal situations that may be caused by an attack event, the attack events that may correspond to various abnormal information combinations can be quickly and accurately identified based on the abnormal information in the network security data.

[0029] In a possible implementation manner of the first aspect, the tracing result includes at least one of an attack source, an attack path, an attack timeline, an attack tool, an attack technique, an attack motive, an attack target, and an attack impact of the attacker, and the network attacker analysis method further includes:

[0030] The attacker profile of the network attacker is updated according to the tracing result.

[0031] In the above scheme, the attacker portrait is updated according to the attacker information in the tracing results. The tracing results describe the attacker's corresponding attack source, attack path, attack timeline, attack motivation, attack impact, tools and techniques used in the attack, etc., so that the attacker portrait is as detailed as possible.

[0032] In a possible implementation manner of the first aspect, the network attacker analysis method is applied to a cloud, and before the step of performing anomaly analysis on network security data to identify multiple attack events, the step further includes:

[0033] Acquire the network security data; the network security data is collected based on the edge end, and the edge end is connected to the cloud;

[0034] After the step of tracing the source of the network attacker based on the corresponding identity information of the associated event to obtain the tracing result, the following step further includes:

[0035] The tracing result is fed back to each edge terminal to be used for adjusting the network protection strategy of each edge terminal.

[0036] In the above scheme, the edge has advantages such as low latency and high bandwidth, and has higher efficiency in data collection. The cloud has powerful computing power and storage resources, and can conduct in-depth analysis and mining of large amounts of data, with higher accuracy in data analysis. Through the collaborative work between the cloud and the edge, the accuracy and efficiency of the identity analysis of network attackers can be improved. In addition, the cloud will feed back the traceability results to each edge to formulate a network protection strategy. Since the edge is close to the user side, it can shorten the time from discovery to disposal of attack events, improving network security.

[0037] In a second aspect, an embodiment of the present application provides a network attacker analysis device, including:

[0038] The recognition module is used to perform anomaly analysis on network security data and identify multiple attack events;

[0039] An extraction module, used to extract attack behavior features of each of the attack events;

[0040] A determination module, used to determine the identity information of the network attacker according to the attack behavior characteristics, each attack event corresponds to one piece of identity information;

[0041] A correlation module, used for performing correlation analysis on the attack events corresponding to the same identity information to obtain information of the correlation events;

[0042] The tracing module is used to trace the network attacker to the corresponding identity information based on the information of the associated event to obtain a tracing result.

[0043] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for analyzing a network attacker described in any one of the first aspects above is implemented.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for analyzing a network attacker described in any one of the first aspects above is implemented.

[0045] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the network attacker analysis method described in any one of the first aspects above.

[0046] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 It is a flowchart of a method for analyzing a network attacker provided by an embodiment of the present application;

[0049] Figure 2 It is a flowchart of step S11 in the method for analyzing a network attacker provided in one embodiment of the present application;

[0050] Figure 3 It is a flowchart of step S12 in the method for analyzing a network attacker provided in one embodiment of the present application;

[0051] Figure 4 It is a flowchart of step S13 in the method for analyzing a network attacker provided in one embodiment of the present application;

[0052] Figure 5 It is a flowchart of step S14 in the method for analyzing a network attacker provided in one embodiment of the present application;

[0053] Figure 6 This is a schematic diagram of the structure of the cloud-edge terminal provided by an embodiment of the present application;

[0054] Figure 7 It is a schematic diagram of the structure of the network attacker analysis device provided in an embodiment of the present application;

[0055] Figure 8 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0057] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0058] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0059] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0060] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0061] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0062] Figure 1 A schematic flow chart of a method for analyzing a network attacker provided by the present application is shown. As an example but not a limitation, the method may include the following steps:

[0063] S11. Perform anomaly analysis on network security data and identify multiple attack incidents.

[0064] Specifically, network security data refers to relevant data generated during network activities, which may include network traffic data and network log data. Among them, attack events refer to unauthorized access, tampering, destruction or theft of information by exploiting system security vulnerabilities or using malicious code to target computer networks or information systems, resulting in information security incidents such as system or service anomalies, data leakage, business interruption, etc., that is, the results or situations caused by attack behaviors.

[0065] S12. Extract attack behavior features of each attack event.

[0066] The attack behavior characteristics record the attack methods and tools used by the attacker. Various feature extraction algorithms, such as Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM), can be used to extract the characteristics of network attack behaviors from the data of attack events.

[0067] S13. Determine the identity information of the network attacker based on the characteristics of the attack behavior.

[0068] Among them, each attack event corresponds to an identity information. Specifically, one attack event corresponds to one attacker, and multiple attack events may correspond to the same attacker or different attackers. Each attacker has his own specific attack characteristics when launching a network attack, such as specific attack behavior, attack mode, attack tools or attack path sequence, etc. Therefore, by analyzing the attack characteristics, the identity of the corresponding attacker can be accurately identified.

[0069] S14: Perform correlation analysis on attack events corresponding to the same identity information to obtain information on correlated events.

[0070] Among them, the associated event refers to one or more attack events that are associated in identity information. Usually, an attacker often launches multiple attack events. Attack events with the same identity information can be classified into one category to form associated events, and then the associated events can be analyzed to obtain information about the associated events.

[0071] S15. Based on the information of the associated event, the corresponding identity information is traced back to the network attacker to obtain a tracing result.

[0072] Among them, the tracing results refer to a complete set of attack plans. The tracing results may include the attack source, attack path, attack timeline, attack motivation, attack impact, tools and techniques used in the attack, and chain of evidence.

[0073] The embodiment of the present application obtains multiple attack events from network security data, obtains the identity information of the attacker corresponding to each attack event based on the attack behavior characteristics analysis, associates different attack events with the same identity information, and traces the attacker based on the associated multiple attack events, thereby improving the accuracy of the analysis of the attacker by combining and analyzing the information of multiple attack events.

[0074] Let's take a specific scenario as an example, as an example but not a limitation. First, collect a large amount of network traffic data, which may include source IP addresses, destination IP addresses, transmitted data types and other information. If a large number of data packets are found to be sent from the same malicious IP address, then it is very likely an attack event. It can be preliminarily determined that this malicious IP address may be the source of the attacker. Through similar analysis, multiple attack events initiated by this malicious IP address can be obtained. By tracing the source of multiple attack events, the source of the attacker can be found. For example, if it is found that this malicious IP address is controlled by a specific botnet, then the source of this botnet can be traced back.

[0075] Optionally, one implementation of step S15 may include tracing and analyzing the information of the associated events with the help of a Bayesian network. The Bayesian network is a probabilistic model that can represent the relationship between various variables in a probabilistic manner. Specifically, the Bayesian network is combined with the attack graph, and a Bayesian attack graph is constructed and analyzed based on the information of the associated events. The reachability probability of each network node and the probability of the attack path can be calculated and inferred through the attack relationship between network nodes, thereby realizing rapid tracing of the attack nodes and attack paths, and obtaining the characteristic information or background information of the attacker.

[0076] In a possible implementation, tracing and analyzing the information of related events includes: using multiple analysis methods to perform multi-dimensional analysis on the information of related events. The multiple analysis methods may include attack strategy analysis, attacker behavior pattern analysis, supply chain analysis, association analysis, and network infrastructure analysis, which can analyze the attacker's detailed identity, attacker's activity mode, attacker's background, attacker's system and application, etc. Specifically:

[0077] Behavioral pattern analysis is used to analyze the attackers’ behavioral patterns, such as the tools, techniques, timing, and target selection they use. These patterns may reveal information such as the attackers’ skill level, motivations, organizations they belong to, or their geographic location.

[0078] Attack strategy analysis is used to deeply study the strategies adopted by attackers, such as whether zero-day vulnerabilities, watering hole attacks, phishing attacks, etc. These strategies may indicate the professionalism and resource level of the attacker, thereby indirectly inferring the identity of the attacker.

[0079] Supply chain analysis is used to track the origin of malware, tools, or components used by attackers. This supply chain information may point to development tools, infrastructure, or partners used by attackers, thereby revealing the attackers' identities or organizational relationships.

[0080] Correlation analysis is used to correlate the current attack with known attacking organizations or individuals. For example, if the malware used in the attack is similar to the software used by a known hacker group, it can be inferred that the attack may be related to that group.

[0081] Network infrastructure analysis, which is used to analyze the network infrastructure used by the attacker, such as IP addresses, domain names, servers, etc. This information may reveal the attacker's geographic location, the hosting provider used, or connections to other known attackers.

[0082] In one possible implementation, multiple analysis methods are used to perform multi-dimensional analysis on the information of related events, including: integrating analysis methods such as attack strategy analysis, attacker behavior pattern analysis, supply chain analysis, correlation analysis, and network infrastructure analysis into the analysis model, and continuously optimizing this analysis model to perform multi-dimensional analysis on the information of related events through the analysis model.

[0083] Optional, see Figure 2 , one implementation of step S11 may include:

[0084] S111. Detect abnormal information in network security data.

[0085] S112. Determine an attack event based on the abnormal information combination and the attack event library.

[0086] The attack event library includes multiple historical attack events, each historical attack event corresponds to an abnormal information combination, and each abnormal information combination includes at least one abnormal information.

[0087] In one possible implementation, the abnormal information may include abnormal traffic and abnormal behavior. Step S111 includes: obtaining network traffic and user behavior by analyzing network traffic data and network log data, and analyzing the network traffic and user behavior to identify potential abnormal traffic and abnormal behavior.

[0088] In one possible implementation, analyzing network traffic and user behavior includes: analyzing network traffic and user behavior through deep learning algorithms, such as using a neural network model trained with historical attack data to analyze traffic characteristics and behavior characteristics in network traffic and user behavior, and detecting normal and abnormal traffic patterns and normal and abnormal behavior patterns.

[0089] In one possible implementation, step S112 includes: constructing an attack event library, and iteratively updating the historical attack events in the attack event library and the abnormal information combination corresponding to each historical attack event based on the historical attack data; matching the detected abnormal information with the abnormal information combination of the historical attack events, and when the match is successful, determining the attack event corresponding to one or more abnormal information.

[0090] The embodiment of the present application utilizes one or more abnormal information corresponding to an attack event, and can quickly and accurately identify attack events that may correspond to various abnormal information combinations based on the abnormal information in the network security data.

[0091] Optional, see Figure 3 , one implementation of step S12 may include:

[0092] S121. Obtain attack information of each attack event.

[0093] The attack information includes at least one of attack tools, attack techniques, attack time, attack times and attack targets.

[0094] S122: Perform vector processing on the attack information to obtain attack behavior features.

[0095] In the embodiment of the present application, the attack behavior characteristics directly characterize the attacker's attack technology, attack tools, attack time, attack times, attack targets and other information in the attack event, so that the extracted attack behavior characteristics are universal.

[0096] Optional, see Figure 4 , one implementation of step S13 may include:

[0097] S131. Match the attack behavior characteristics of the network attacker and the historical attacker to obtain a matching value between the network attacker and the historical attacker.

[0098] S132, determine whether the matching value is greater than or equal to a preset threshold, if so, execute step S133; if not, execute step S134.

[0099] S133: Determine the identity information of the historical attacker with the largest matching value as the identity information of the network attacker.

[0100] S134: When all matching values ​​are smaller than the preset threshold, determine that the new identity information is the identity information of the network attacker.

[0101] In a possible implementation, step S131 includes: establishing an intelligence information database of historical attackers, analyzing the characteristics of the techniques, tools, protocols, etc. used in the previous attacks to identify the attackers' technical level and preferences, and analyzing the attackers' behavior patterns, such as attack time, frequency, target selection, etc., to obtain more intelligence information about the attackers. Using the intelligence information database, the attack behavior characteristics are matched with the intelligence information of historical attackers to quickly identify the attackers that may correspond to the attack event.

[0102] In one possible implementation, step S132 includes: dividing the attack behavior features into key features and non-key features. For key features, matching is performed using a feature sameness matching method. The feature sameness matching method means that if the key features of the network attacker and the historical attacker are the same, the match is considered successful, otherwise the match fails; for non-key features, matching is performed using a feature similarity matching algorithm. The feature similarity matching algorithm means that if the similarity of the non-key features of the network attacker and the historical attacker is greater than or equal to a set similarity threshold, the match is considered successful, otherwise the match fails.

[0103] The embodiment of the present application utilizes the attack behavior characteristics of known historical attackers and compares them with the attack behavior characteristics of network attackers, so as to quickly and accurately identify the identity information of the attacker.

[0104] In a possible implementation, step S134 includes: finding clues to the attacker's identity information directly from the characteristics of the attack behavior, performing a reverse Domain Name System (DNS) query and a Whois query on the IP address of the attack source, obtaining the location and registration information of the IP address, and identifying the device type and operating system that the attacker may use by comparing the device fingerprint information in the attack traffic, thereby obtaining the attacker's identity information.

[0105] In a possible implementation, after determining the possible identity information of the attacker, the identity information is verified. Specifically, the identity information of the network attacker is comprehensively evaluated based on the intelligence information database and various identity information clues to confirm the authenticity of the identity information of the network attacker.

[0106] The embodiment of the present application identifies and cross-verifies the identity information of the attacker in a variety of ways to ensure that the identified attacker's identity has a high degree of credibility and accuracy.

[0107] Optional, see Figure 5, one implementation of step S14 may include:

[0108] S141. Classify all attack events according to attack behavior characteristics, and generate an attack type for each attack event.

[0109] S142: Associating attack behavior characteristics and attack types of different attack events corresponding to the same identity information with the identity information to obtain information of associated events.

[0110] In a possible implementation, step S141 includes: using a neural network to learn the features of the input data, and dividing the data into different categories based on these features. A classification algorithm such as a K-nearest neighbor algorithm may also be used to classify attack events by calculating the distance between each data point.

[0111] As an example but not limitation, step S141 is specifically as follows: normalizing the attack behavior characteristics of each attack event, and calculating the characteristic distance between the attack behavior characteristics of each attack event; dividing the attack events into several attack types according to the characteristic distance, and calculating the characteristic center of each type of attack event; inputting the attack behavior characteristics of each attack event and each characteristic center into the neural network, calculating the similarity value between the attack behavior characteristics of each attack event and each characteristic center, dividing each attack event into a data set corresponding to the characteristic center corresponding to the highest similarity value, and re-updating the characteristic center of each attack type; determining the attack type corresponding to each attack event according to the attack behavior characteristics of the updated characteristic center.

[0112] As an example but not a limitation, step S141 is specifically as follows: Assuming that there are two attack events corresponding to the same identity information a, the attack behavior features extracted from the first attack event include features b and features c, and the attack behavior features extracted from the second attack event include features d and features e, and the attack types of the two attack events are types f and g, respectively. Types f and g can be directly associated with identity information a first, and then features b, c, d, and e can be indirectly associated with identity information a by associating attack behavior features with attack types. Assuming that the two attack events are associated events A, then identity information a, features b, c, d, e, type f, and type g are all represented as information of associated event A.

[0113] The embodiment of the present application uses identity information to perform correlation analysis on attack events, taking attack events with the same identity information as correlation events, and taking attack behavior feature information and attack type as information of correlation events. By classifying attack events by attack behavior features, attack types can more intuitively represent attack events, making it easier to correlate different attack events.

[0114] Optionally, after step S15, the method for analyzing the network attacker further includes updating the attacker portrait of the network attacker according to the tracing result, and continuously updating and improving the attacker portrait as new attack events occur.

[0115] The embodiment of the present application updates the attacker portrait according to the attacker information in the tracing results. The tracing results describe the attacker's corresponding attack source, attack path, attack timeline, attack motivation, attack impact, tools and techniques used in the attack, etc., so that the attacker portrait can reflect the attacker's detailed information.

[0116] In a possible implementation, the network attacker analysis method is applied in the cloud, that is, the network attacker analysis process is performed in the cloud.

[0117] In one possible implementation, the process of analyzing network attackers in the cloud includes: establishing an attacker identity analysis model in the cloud, performing a detailed analysis of network security data uploaded to the cloud, and obtaining a final tracing result.

[0118] Optionally, before step S11, the method for analyzing network attackers further includes obtaining network security data. The network security data is obtained based on edge data collection, and the edge data is connected to the cloud. As an example and not a limitation, see Figure 6 The cloud is located at the center of the network, and each edge terminal is located at the edge of the network. When there are multiple edge terminals, each edge terminal is bidirectionally connected to the cloud to achieve two-way communication.

[0119] In one possible implementation, multiple collection methods can be set at the edge to collect network traffic data and log data, etc. For example, honeypots, sensors, probes, firewalls, etc. can be deployed.

[0120] Optionally, after acquiring the network security data, the network attacker analysis method also includes pre-processing operations such as cleaning, deduplication, and format conversion on the network security data to improve the accuracy and availability of the data.

[0121] Optionally, after step S15, the method for analyzing network attackers further includes feeding back the tracing results to each edge end for adjusting the network protection strategy of each edge end.

[0122] Specifically, network protection strategies can be measures such as blocking attacker IP addresses and updating firewall rules to strengthen the defense and response mechanism against network attacks.

[0123] In the embodiment of the present application, the edge has advantages such as low latency and high bandwidth, and has higher efficiency in data collection. The cloud has powerful computing power and storage resources, and can conduct in-depth analysis and mining of large amounts of data, with higher accuracy in data analysis. Through the collaborative work between the cloud and the edge, the accuracy and efficiency of the identity analysis of network attackers can be improved. In addition, the cloud will feed back the traceability results to each edge to formulate a network protection strategy. The network protection strategy conforms to the actual situation of the edge, and because the edge is close to the user side, it can shorten the attack event from discovery to disposal, improving network security.

[0124] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0125] Corresponding to the analysis method of the network attacker described in the above embodiment, Figure 7 A structural block diagram of a network attacker analysis device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0126] Reference Figure 7 , the device comprises:

[0127] The identification module 21 is used to perform anomaly analysis on network security data and identify multiple attack events.

[0128] The extraction module 22 is used to extract the attack behavior features of each attack event.

[0129] The determination module 23 is used to determine the identity information of the network attacker according to the attack behavior characteristics, and each attack event corresponds to an identity information.

[0130] The correlation module 24 is used to perform correlation analysis on various attack events corresponding to the same identity information to obtain information of the correlated events.

[0131] The tracing module 25 is used to trace the network attacker to the corresponding identity information based on the information of the associated event to obtain a tracing result.

[0132] In one possible implementation, the identification module 21 includes: a detection unit, used to detect abnormal information in network security data; a first determination unit, used to determine an attack event based on the abnormal information combination and an attack event library; wherein the attack event library includes multiple attack events, each attack event corresponds to an abnormal information combination, and each abnormal information combination corresponds to at least one abnormal information.

[0133] In one possible implementation, the extraction module 22 includes: an acquisition unit, used to obtain attack information of each attack event; wherein the attack information includes at least one of an attack tool, an attack technique, an attack time, a number of attacks, and an attack target; and a processing unit, used to vectorize the attack information to obtain the attack behavior characteristics.

[0134] In one possible implementation, the determination module 23 includes: a matching unit, which is used to match the attack behavior characteristics of the network attacker and the historical attacker to obtain a matching value between the network attacker and the historical attacker; a second determination unit, which is used to determine the identity information of the historical attacker with the largest matching value as the identity information of the network attacker when there is a matching value greater than or equal to a preset threshold; and a third determination unit, which is used to determine that the new identity information is the identity information of the network attacker when all matching values ​​are less than the preset threshold.

[0135] In one possible implementation, the association module 24 includes: a classification unit, which is used to classify all attack events according to attack behavior characteristics and generate an attack type for each attack event; an association unit, which is used to associate the attack behavior characteristics and attack types of different attack events corresponding to the same identity information with the identity information to obtain information about associated events.

[0136] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0137] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0138] An embodiment of the present application also provides an electronic device, which network device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the above-mentioned method embodiments when executing the computer program.

[0139] like Figure 8 The electronic device 30 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0140] The electronic device 30 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different device components (including the memory 32 and the processor 31).

[0141] The bus 33 includes a data bus, an address bus, and a control bus.

[0142] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and a cache memory 322 , and may further include a read only memory (ROM) 323 .

[0143] The memory 32 may also include a program tool 325 having a set (at least one) of program modules 324, such program modules 324 including but not limited to: operating means, one or more applications, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0144] The processor 31 executes various functional applications and data processing, such as the data association method of the above embodiment, by running the computer program stored in the memory 32 .

[0145] The electronic device 30 may also communicate with one or more external devices 34. Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the model generating device 30 may also communicate with one or more networks via a network adapter 36. Figure 8 As shown, the network adapter 36 communicates with other modules of the model generation device 30 via the bus 33. It should be understood that although Figure 8 Not shown, other hardware and / or software modules may be used in conjunction with the model-generated device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) devices, tape drives, and data backup storage devices.

[0146] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0147] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0148] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0150] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0151] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0152] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for analyzing network attackers, It is characterized in that include: Perform anomaly analysis on network security data and identify multiple attack incidents; Extracting attack behavior features of each of the attack events; Determine the identity information of the network attacker according to the attack behavior characteristics, each attack event corresponds to one piece of identity information; Performing correlation analysis on the attack events corresponding to the same identity information to obtain information on the correlated events; Tracing the network attacker to the corresponding identity information based on the information of the associated event to obtain a tracing result, wherein the tracing result includes at least one of the attacker's attack source, attack path, attack timeline, attack tool, attack technique, attack motive, attack target, and attack impact; The step of performing correlation analysis on the attack events corresponding to the same identity information to obtain information about the correlated events includes: classifying all the attack events according to the attack behavior characteristics to generate an attack type for each attack event; correlating the attack behavior characteristics and the attack types of different attack events corresponding to the same identity information with the identity information to obtain information about the correlated events; The step of determining the identity information of the network attacker according to the attack behavior characteristics includes: matching the attack behavior characteristics of the network attacker with those of historical attackers to obtain a matching value between the network attacker and the historical attackers; when there is a matching value greater than or equal to a preset threshold, determining the identity information of the historical attacker with the largest matching value as the identity information of the network attacker; when the matching values ​​are all less than the preset threshold, determining the new identity information as the identity information of the network attacker; The step of extracting the attack behavior feature of each of the attack events comprises: obtaining attack information of each of the attack events; the attack information comprises at least one of an attack tool, an attack technique, an attack time, an attack number, and an attack target; performing vector processing on the attack information to obtain the attack behavior feature; The network attacker analysis method further includes: updating an attacker portrait of the network attacker according to the tracing result.

2. The method for analyzing a network attacker according to claim 1, It is characterized in that The step of performing anomaly analysis on network security data and identifying multiple attack events includes: Detecting abnormal information in the network security data; An attack event is determined according to an abnormal information combination and an attack event library; the attack event library includes a plurality of historical attack events, each of the historical attack events corresponds to one abnormal information combination, and each of the abnormal information combination includes at least one abnormal information.

3. The method for analyzing a network attacker according to claim 1, It is characterized in that The network attacker analysis method is applied to the cloud, and before the step of performing abnormal analysis on network security data and identifying multiple attack events, the step further includes: Acquire the network security data; the network security data is collected based on the edge end, and the edge end is connected to the cloud; After the step of tracing the source of the network attacker based on the corresponding identity information of the associated event to obtain the tracing result, the following step further includes: The tracing result is fed back to each edge terminal to be used for adjusting the network protection strategy of each edge terminal.

4. An analysis device for a network attacker, It is characterized in that include: The recognition module is used to perform anomaly analysis on network security data and identify multiple attack events; An extraction module, used to extract attack behavior features of each of the attack events; A determination module, used to determine the identity information of the network attacker according to the attack behavior characteristics, each attack event corresponds to one piece of identity information; A correlation module, used for performing correlation analysis on the attack events corresponding to the same identity information to obtain information of the correlation events; A tracing module, configured to trace the source of the network attacker to the corresponding identity information based on the information of the associated event, and obtain a tracing result, wherein the tracing result includes at least one of the attacker's attack source, attack path, attack timeline, attack tool, attack technique, attack motive, attack target, and attack impact; The association module is specifically used to: classify all the attack events according to the attack behavior characteristics, and generate an attack type for each of the attack events; associate the attack behavior characteristics and the attack type of different attack events corresponding to the same identity information with the identity information to obtain information of the associated event; The determination module is specifically used to: match the attack behavior characteristics of the network attacker with the historical attacker to obtain a matching value between the network attacker and the historical attacker; when there is a matching value greater than or equal to a preset threshold, determine the identity information of the historical attacker with the largest matching value as the identity information of the network attacker; when the matching values ​​are all less than the preset threshold, determine the new identity information as the identity information of the network attacker; The extraction module is specifically used to: obtain attack information of each of the attack events; the attack information includes at least one of attack tools, attack techniques, attack time, attack times and attack targets; perform vector processing on the attack information to obtain the attack behavior characteristics; The network attacker analysis device is also used to update the attacker portrait of the network attacker according to the tracing result.

5. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method for analyzing a network attacker according to any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium storing a computer program, It is characterized in that When the computer program is executed by a processor, the method for analyzing a network attacker according to any one of claims 1 to 3 is implemented.

Citation Information

Patent Citations

  • Network attack event traceability processing method and device, equipment and storage medium

    CN111935192A

  • Tracking and tracing method and device based on WEB dynamic defense

    CN115208643A

  • Network attack tracing method and device and storage medium

    CN117375988A

  • Method and apparatus for obtaining attacker information, device, and storage medium

    WO2020107446A1