Malicious access data determination method, device, medium and electronic device

By combining the generation of user portraits and malicious access databases, malicious access data is determined, the malicious access data is improved, the problem of missed judgment in the existing technology is solved, and the risk of attack on computing resources is reduced.

CN115085957BActive Publication Date: 2024-11-12CHINA TELECOM CORP LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110270921.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-03-12
Publication Date
2024-11-12
Estimated Expiration
2041-03-12

AI Technical Summary

Technical Problem

When determining malicious access to data, the prior art can easily lead to missed judgment problems, and it is difficult to effectively distinguish between legal and malicious access to data, resulting in attacks on computing resources.

Method used

By generating a user portrait, combining the matching results, traffic values ​​and confidence in the malicious access database, if at least one meets the preset judgment conditions, the target access data is determined to be malicious access data. The user portrait includes fields such as traffic components, access source IP, access operator, geographical ownership and access frequency. The confidence database is used to calculate the confidence and calculate the traffic threshold based on historical traffic for judgment.

Benefits of technology

It improves the judgment accuracy of malicious access to data, reduces the probability of missed judgment, avoids attacks on computing resources, and reduces the probability of misjudgment, and avoids the error cleaning of legal access to data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115085957B_ABST
    Figure CN115085957B_ABST
Patent Text Reader

Abstract

The present application provides a method, device, medium and electronic device for determining malicious access data, which relates to the field of computer technology, including: generating a user portrait based on the collected legitimate access data; when the target access data is detected, determining the matching result between the target access data and the malicious access database, and calculating the flow value corresponding to the target access data based on the user portrait; determining the confidence level corresponding to the target access data based on the user portrait and the malicious access database; if at least one of the matching result, flow value and confidence level meets the preset judgment condition, the target access data is judged to be malicious access data. It can be seen that the implementation of the above method can improve the judgment accuracy of malicious access data and reduce the probability of missed judgment, which is conducive to avoiding attacks on computing resources by malicious access data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method for determining malicious access data, a device for determining malicious access data, a computer-readable storage medium, and an electronic device. Background Art

[0002] Distributed Denial of Service (DDos) is one of the most important threats on the Internet. DDos attacks are attacks in which attackers consume the computing resources of the target through puppet hosts, preventing the target from providing services to legitimate users. Web servers and DNS servers are more common targets. The computing resources consumed by DDos attacks generally include CPU, memory, bandwidth, database servers, etc.

[0003] Generally speaking, DDos attacks are a type of malicious access data, and the way to deal with such malicious access data is generally to filter based on the characteristics of such access data (such as source address) or to determine malicious access data based on the access frequency of the source address. However, in reality, the determination conditions for malicious access data are more complex, and determining only by characteristics or access frequency is prone to missed determinations.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of this application is to provide a malicious access data determination method, a malicious access data determination device, a computer-readable storage medium and an electronic device, which can improve the determination accuracy of malicious access data and reduce the probability of missed determination, thereby helping to avoid malicious access data attacks on computing resources.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0007] According to one aspect of the present application, a method for determining malicious access data is provided, comprising:

[0008] Generate user profiles based on the collected legitimate access data;

[0009] When target access data is detected, the matching result between the target access data and the malicious access database is determined, and the traffic value corresponding to the target access data is calculated based on the user profile;

[0010] Determine the confidence level of the target access data based on the user profile and malicious access database;

[0011] If at least one of the matching result, traffic value and confidence meets the preset judgment condition, the target access data is judged to be malicious access data.

[0012] In an exemplary embodiment of the present application, before determining the matching result between the target access data and the malicious access database, the method further includes:

[0013] Building a malicious access database based on malicious access data in historical determination results;

[0014] The malicious access database is updated synchronously in real time according to the malicious access data update message in the cloud server.

[0015] In an exemplary embodiment of the present application, generating a user profile based on the collected legal access data includes:

[0016] Parse legal access data into structured data, and identify the structured data as user profiles;

[0017] Among them, the structured data includes multiple preset fields and field information corresponding to the multiple preset fields; the multiple preset fields include at least one of traffic composition, access source IP, access operator, regional affiliation and access frequency of access source IP.

[0018] In an exemplary embodiment of the present application, determining a matching result between target access data and a malicious access database includes:

[0019] Parse the target source address in the target access data;

[0020] Detect whether the target source address hits the malicious source address set in the malicious access database;

[0021] If so, it is determined that the target access data matches the malicious access database.

[0022] In an exemplary embodiment of the present application, calculating the traffic value corresponding to the target access data according to the user profile includes:

[0023] Determine a target user profile corresponding to the target source address from the user profiles;

[0024] The access frequency in the target user portrait is determined as the traffic value corresponding to the target access data.

[0025] In an exemplary embodiment of the present application, determining the confidence level corresponding to the target access data according to the user profile and the malicious access database includes:

[0026] Determine the prior information of the target access data according to the confidence database; wherein the confidence database includes the confidence corresponding to at least one of the legitimate access data and the malicious access data;

[0027] Determine the traffic distribution of the access frequency in the target user profile per unit time, and calculate the likelihood function of the target access data based on the traffic distribution;

[0028] The posterior information corresponding to the target access data is calculated as the confidence according to the prior information and the likelihood function.

[0029] In an exemplary embodiment of the present application, the method further includes:

[0030] The flow threshold corresponding to the current moment is calculated based on the flow at the historical moment. If the flow value of the target access data is greater than or equal to the flow threshold, it is determined that the flow value meets the preset determination condition;

[0031] If the matching result is used to indicate that the target access data matches the malicious access database, then it is determined that the matching result meets the preset determination condition;

[0032] If the confidence is a divergent result, it is determined that the confidence meets the preset determination conditions.

[0033] According to one aspect of the present application, a malicious access data determination device is provided, comprising: a user profile generation unit, a data calculation unit and a malicious access determination unit, wherein:

[0034] A user portrait generation unit, used to generate a user portrait based on the collected legal access data;

[0035] A data calculation unit, used to determine the matching result between the target access data and the malicious access database when the target access data is detected, and calculate the flow value corresponding to the target access data according to the user portrait;

[0036] The data calculation unit is further used to determine the confidence level corresponding to the target access data based on the user profile and the malicious access database;

[0037] The malicious access determination unit is used to determine that the target access data is malicious access data when at least one of the matching result, the flow value and the confidence meets the preset determination condition.

[0038] In an exemplary embodiment of the present application, the above-mentioned device further includes:

[0039] A database construction unit, used to construct a malicious access database according to the malicious access data in the historical determination result before the data calculation unit determines the matching result between the target access data and the malicious access database;

[0040] The database updating unit is used to synchronously update the malicious access database in real time according to the malicious access data update message in the cloud server.

[0041] In an exemplary embodiment of the present application, the user portrait generation unit generates a user portrait according to the collected legal access data, including:

[0042] Parse legal access data into structured data, and identify the structured data as user profiles;

[0043] Among them, the structured data includes multiple preset fields and field information corresponding to the multiple preset fields; the multiple preset fields include at least one of traffic composition, access source IP, access operator, regional affiliation and access frequency of access source IP.

[0044] In an exemplary embodiment of the present application, the data calculation unit determines the matching result between the target access data and the malicious access database, including:

[0045] Parse the target source address in the target access data;

[0046] Detect whether the target source address hits the malicious source address set in the malicious access database;

[0047] If so, it is determined that the target access data matches the malicious access database.

[0048] In an exemplary embodiment of the present application, the data calculation unit calculates the traffic value corresponding to the target access data according to the user profile, including:

[0049] Determine a target user profile corresponding to the target source address from the user profiles;

[0050] The access frequency in the target user portrait is determined as the traffic value corresponding to the target access data.

[0051] In an exemplary embodiment of the present application, the data calculation unit determines the confidence level corresponding to the target access data according to the user portrait and the malicious access database, including:

[0052] Determine the prior information of the target access data according to the confidence database; wherein the confidence database includes the confidence corresponding to at least one of the legitimate access data and the malicious access data;

[0053] Determine the traffic distribution of the access frequency in the target user profile per unit time, and calculate the likelihood function of the target access data based on the traffic distribution;

[0054] The posterior information corresponding to the target access data is calculated as the confidence according to the prior information and the likelihood function.

[0055] In an exemplary embodiment of the present application, the above-mentioned device further includes:

[0056] A condition determination unit, used to calculate a flow threshold corresponding to the current moment according to the flow at the historical moment, and if the flow value of the target access data is greater than or equal to the flow threshold, it is determined that the flow value meets the preset determination condition;

[0057] The condition determination unit is further used to determine that the matching result meets the preset determination condition when the matching result is used to indicate that the target access data matches the malicious access database;

[0058] The condition determination unit is further used to determine whether the confidence meets a preset determination condition if the confidence is a divergent result.

[0059] According to one aspect of the present application, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any one of the above methods by executing the executable instructions.

[0060] According to one aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, any one of the above methods is implemented.

[0061] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0062] The exemplary embodiments of the present application may have some or all of the following beneficial effects:

[0063] In the malicious access data determination method provided in an example implementation of the present application, a user portrait can be generated based on the collected legitimate access data; when target access data is detected, the matching result between the target access data and the malicious access database is determined, and the flow value corresponding to the target access data is calculated based on the user portrait; the confidence corresponding to the target access data is determined based on the user portrait and the malicious access database; if at least one of the matching result, flow value and confidence meets the preset determination condition, the target access data is determined to be malicious access data. According to the above scheme description, on the one hand, the present application can perform malicious access data determination based on user portraits and malicious access databases, improve the determination accuracy of malicious access data, and reduce the probability of missed determination, which is conducive to avoiding malicious access data attacks on computing resources. On the other hand, the present application can reduce the probability of false determination through malicious access data determination based on user portraits and malicious access databases, which is conducive to avoiding false cleaning of legitimate access data.

[0064] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0066] Figure 1 A schematic diagram showing an exemplary system architecture of a malicious access data determination method and a malicious access data determination device to which the embodiments of the present application can be applied;

[0067] Figure 2 A schematic diagram showing the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown;

[0068] Figure 3 A flowchart of a method for determining malicious access data according to an embodiment of the present application is schematically shown;

[0069] Figure 4 A schematic diagram of flow distribution according to an embodiment of the present application is shown schematically;

[0070] Figure 5 A schematic diagram of flow distribution according to another embodiment of the present application is shown schematically;

[0071] Figure 6A flowchart of a method for determining malicious access data according to an embodiment of the present application is schematically shown;

[0072] Figure 7 The structure block diagram of a malicious access data determination device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0073] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present application will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical solutions of the present application may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present application.

[0074] In addition, the accompanying drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0075] Figure 1 A schematic diagram of a system architecture of an exemplary application environment in which a method for determining malicious access data and a device for determining malicious access data according to an embodiment of the present application can be applied is shown.

[0076] like Figure 1 As shown, the system architecture 100 may include one or more of terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc. The terminal devices 101, 102, 103 may be various electronic devices with display screens, including but not limited to desktop computers, portable computers, smart phones, tablet computers, etc. It should be understood that Figure 1The number of terminal devices, networks and servers in the embodiment is only for illustration. According to the implementation requirements, there may be any number of terminal devices, networks and servers. For example, the server 105 may be a server cluster composed of multiple servers.

[0077] The malicious access data determination method provided in the embodiment of the present application is generally executed by the server 105, and accordingly, the malicious access data determination device is generally set in the server 105. However, it is easy for a person skilled in the art to understand that the malicious access data determination method provided in the embodiment of the present application can also be executed by the terminal device 101, 102 or 103, and accordingly, the malicious access data determination device can also be set in the terminal device 101, 102 or 103, and this is not particularly limited in this exemplary embodiment. For example, in an exemplary embodiment, the server 105 can generate a user portrait based on the collected legitimate access data; when the target access data is detected, the matching result of the target access data and the malicious access database is determined, and the flow value corresponding to the target access data is calculated according to the user portrait; the confidence corresponding to the target access data is determined according to the user portrait and the malicious access database; if at least one of the matching result, flow value and confidence meets the preset judgment condition, the target access data is determined to be malicious access data.

[0078] Figure 2 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0079] It should be noted that Figure 2 The computer system 200 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0080] like Figure 2 As shown, the computer system 200 includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 202 or a program loaded from a storage part 208 into a random access memory (RAM) 203. Various programs and data required for system operation are also stored in the RAM 203. The CPU 201, the ROM 202, and the RAM 203 are connected to each other via a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0081] The following components are connected to the I / O interface 205: an input section 206 including a keyboard, a mouse, etc.; an output section 207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 208 including a hard disk, etc.; and a communication section 209 including a network interface card such as a LAN card, a modem, etc. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I / O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 210 as needed, so that a computer program read therefrom is installed into the storage section 208 as needed.

[0082] In particular, according to an embodiment of the present application, the process described below with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 209, and / or installed from a removable medium 211. When the computer program is executed by the central processing unit (CPU) 201, various functions defined in the method and apparatus of the present application are executed.

[0083] This exemplary embodiment provides a method for determining malicious access data. The method for determining malicious access data can be applied to the server 105, or to one or more of the terminal devices 101, 102, and 103, which is not particularly limited in this exemplary embodiment. Figure 3 As shown, the malicious access data determination method may include the following steps S310 to S340.

[0084] Step S310: Generate a user profile based on the collected legal access data.

[0085] Step S320: When target access data is detected, the matching result between the target access data and the malicious access database is determined, and the traffic value corresponding to the target access data is calculated according to the user portrait.

[0086] Step S330: Determine the confidence level corresponding to the target access data based on the user portrait and the malicious access database.

[0087] Step S340: If at least one of the matching result, the traffic value and the confidence meets the preset determination condition, the target access data is determined to be malicious access data.

[0088] Implementation Figure 3The method shown can determine malicious access data based on user portraits and malicious access databases, improve the accuracy of malicious access data determination, and reduce the probability of missed determination, thereby helping to avoid malicious access data attacks on computing resources. In addition, malicious access data determination can be performed through user portraits and malicious access databases to reduce the probability of false determination, thereby helping to avoid false cleaning of legitimate access data.

[0089] Next, the above steps of this exemplary embodiment are described in more detail.

[0090] In step S310, a user portrait is generated based on the collected legal access data.

[0091] Specifically, the user portrait can be represented by structured data or unstructured data, which is not limited in the embodiments of the present application. In addition, the user portrait is a multi-faceted description of an access source IP, where IP is a network address that can be used as a unique representation of the access party (e.g., user). In addition, legitimate access data is normal access data, which is different from malicious access data (e.g., DDoS attack).

[0092] As an optional embodiment, generating a user profile based on the collected legal access data includes: parsing the legal access data into structured data, and determining the structured data as a user profile; wherein the structured data includes multiple preset fields and field information corresponding to the multiple preset fields; the multiple preset fields include at least one of traffic composition, access source IP, access operator, regional affiliation and access frequency of the access source IP.

[0093] Specifically, before parsing the legal access data into structured data, the above method may further include the following steps: collecting legal access data based on NetFlow technology. NetFlow technology is a traffic collection technology developed based on traffic feature data statistics, which can present a network traffic session view from a streaming perspective, aggregate each end-to-end TCP / IP connection information into a flow, and record basic end-to-end connection attributes; a flow can be defined as a unidirectional flow between data packets with a given source and destination, both of which are composed of a network layer IP address and a transport layer source and destination port number.

[0094] It can be seen that the implementation of this optional embodiment can help improve the recording and acquisition of access frequency of target access data through the structured representation of legitimate access data, so as to determine malicious access data based on the access frequency of the target access data.

[0095] In step S320, when target access data is detected, the matching result between the target access data and the malicious access database is determined, and the traffic value corresponding to the target access data is calculated according to the user portrait.

[0096] Specifically, the traffic value corresponding to the target access data can be represented by the access frequency of the access source IP in the target access data within a preset time period. If the access frequency is higher than the traffic threshold, it means that the target access data may be malicious access data.

[0097] Based on this, before step S320, the above method may further include the following steps: constructing an access frequency analysis model based on the user portrait. Further, determining the matching result between the target access data and the malicious access database includes: when the target access data is detected, detecting whether the access source IP in the target access data is the IP recorded in the access frequency analysis model, if not, marking the access source IP of the target access data, and monitoring the access source IP of the target access data according to the marking result, so that when the access source IP is detected again, the access frequency corresponding to the access source IP can be updated in real time.

[0098] As an optional embodiment, before determining the matching result between the target access data and the malicious access database, the above method also includes: building a malicious access database based on the malicious access data in the historical judgment results; and synchronously updating the malicious access database in real time based on the malicious access data update message in the cloud server.

[0099] Specifically, a malicious access database is constructed based on malicious access data in historical judgment results, including: reading multiple historical judgment results within a preset time period (e.g., within a week); extracting attack judgment results used to represent judgments on malicious access data from multiple historical judgment results; and constructing a malicious access database based on the attack judgment results; wherein the malicious access database includes one or more malicious access data, and each malicious access data may include access source IP, destination IP, access operator, traffic component dimension, regional affiliation, access frequency, etc.

[0100] Based on this, the malicious access database is updated in real time according to the malicious access data update message in the cloud server, including: regularly requesting malicious access data update messages from the cloud server, the malicious access data update message is used to indicate the newly added malicious access data in the cloud server within a period of time; when receiving the malicious access data update message responded by the cloud server, the malicious access database is updated in real time according to the malicious access data update message to improve the richness of the malicious access data types in the database. Based on this, after the malicious access database is updated in real time according to the malicious access data update message, it can also include: generating corresponding analysis and protection suggestions according to the malicious access data in the malicious access data update message and outputting them to the user interface.

[0101] In addition, after constructing a malicious access database based on malicious access data in the historical judgment results, the above method may also include the following steps: coupling the malicious access database with the user portrait, and constructing a malicious access data detection and defense cleaning model based on the coupling result. Based on this, the flow value corresponding to the target access data is calculated according to the user portrait, including: calculating the flow value corresponding to the target access data according to the malicious access data detection and defense cleaning model. Based on this, the confidence corresponding to the target access data is determined according to the user portrait and the malicious access database, including: determining the confidence corresponding to the target access data according to the malicious access data detection and defense cleaning model.

[0102] It can be seen that the implementation of this optional embodiment can improve the subsequent calculation accuracy of matching results, traffic values ​​and confidence levels by building and updating the malicious access database, thereby improving the accuracy of determining malicious access data.

[0103] As an optional embodiment, determining the matching result between the target access data and the malicious access database includes: parsing the target source address (i.e., access source IP) in the target access data; detecting whether the target source address hits the malicious source address set in the malicious access database; if so, determining that the target access data matches the malicious access database.

[0104] Specifically, detecting whether the target source address hits the malicious source address set in the malicious access database includes: detecting whether there is a malicious source address that is the same as the target source address in the malicious source address set in the malicious access database; if so, it means that the target source address hits the malicious source address set and the process ends; if not, it means that the target source address does not hit the malicious source address set, and then the traffic value corresponding to the target access data can be calculated according to the user portrait.

[0105] It can be seen that the implementation of this optional embodiment can improve the efficiency of determining malicious access data by associating the target source address with the malicious source address set, thereby facilitating the cleaning of malicious access data as soon as possible and avoiding the impact on the response efficiency of normal access.

[0106] As an optional embodiment, calculating the traffic value corresponding to the target access data based on the user portrait includes: determining the target user portrait corresponding to the target source address from the user portrait; determining the access frequency in the target user portrait as the traffic value corresponding to the target access data.

[0107] Specifically, determining the target user profile corresponding to the target source address from the user profile can be understood as determining the target user profile corresponding to the target source address from multiple user profiles.

[0108] It can be seen that implementing this optional embodiment can determine the flow value corresponding to the current target access data, and judging the target access data as malicious access data based on the flow value can help reduce the normal business cleaning damage rate and the attack traffic leakage cleaning rate.

[0109] In step S330, the confidence level corresponding to the target access data is determined based on the user portrait and the malicious access database.

[0110] Specifically, the malicious access database is used to store a variety of malicious access data, different malicious access data can correspond to different access source IPs, and the confidence is used to represent the reputation value of the access source IP of the target access data. In addition, before being determined as malicious access data, malicious access data can be determined as legitimate access data based on normal access frequency and confidence. When the access frequency and confidence of the access source IP of the access data change abnormally, the original legitimate access data can be determined as malicious access data.

[0111] As an optional embodiment, the confidence corresponding to the target access data is determined based on the user profile and the malicious access database, including: determining the prior information of the target access data based on the confidence database; wherein the confidence database includes the confidence corresponding to at least one of the legitimate access data and the malicious access data; determining the traffic distribution of the access frequency in the target user profile per unit time, and calculating the likelihood function of the target access data based on the traffic distribution; and calculating the posterior information corresponding to the target access data as the confidence based on the prior information and the likelihood function.

[0112] Specifically, the prior information of the target access data is determined according to the confidence database, including: extracting the target access source IP in the target access data; detecting whether there is prior information P(R) corresponding to the target access source IP in the confidence database; if there is no prior information P(R), the target access source IP is randomly assigned as the prior information P(R) of the target access source IP; if there is prior information, the prior information P(R) is read.

[0113] Based on this, the traffic distribution of the access frequency in the target user portrait within a unit time (eg, 5s) is determined, including: graphing the access frequency in the target user portrait to obtain a graph for representing the traffic distribution of the access frequency within a unit time.

[0114] See also Figure 4 , Figure 4 The flow distribution diagram according to an embodiment of the present application is schematically shown. Figure 4As shown in the figure, in a coordinate system where the horizontal axis is time and the vertical axis is the number of packets, the solid line is used to represent the distribution of the actual system traffic, and the dotted line is used to represent the distribution of the attack traffic (i.e., malicious access data). Specifically, the actual system traffic tends to 0 after 80 seconds, while the attack traffic grows exponentially between 20 seconds and 80 seconds, drops sharply at 80 seconds, and grows exponentially again after 80 seconds, and stabilizes at 100 seconds. It can be seen that the attack traffic far exceeds the actual system traffic. If the target access data is malicious access data, the traffic distribution of the target access data can be Figure 4 The distribution of attack traffic is shown in .

[0115] and Figure 4 Similarly, see Figure 5 , Figure 5 A schematic diagram of flow distribution according to another embodiment of the present application is shown. Figure 5 As shown in the figure, in a coordinate system with time as the horizontal axis and the number of packets as the vertical axis, the solid line is used to represent the distribution of the actual system traffic, and the dotted line is used to represent the distribution of attack traffic (i.e., malicious access data). Specifically, the actual system traffic tends to 0 after 80 seconds, while the attack traffic grows exponentially between 20 seconds and 80 seconds, drops sharply at 80 seconds, and grows exponentially again after 80 seconds, and tends to stabilize at 100 seconds. Although after 100 seconds, Figure 4 The number of attack traffic packets in is much higher than Figure 5 However, since its exponential growth from 20s to 80s is different from the access frequency of legitimate access data, Figure 5 The dotted part in is also the distribution of attack traffic. Optionally, if the target access data is malicious access data, the traffic distribution of the target access data can also be Figure 5 The distribution of attack traffic is shown in .

[0116] Based on this, the posterior information corresponding to the target access data is calculated as the confidence according to the prior information and the likelihood function, including: substituting the prior information P(R) and the likelihood function P(X|R) into the expression To calculate the posterior information P(R|X) corresponding to the target access data; where R is a random variable, the posterior information P(R|X) can be used as the prior information for the next iteration, indicating the distribution of the confidence of the access source IP after the observed traffic changes.

[0117] It can be seen that the implementation of this optional embodiment can improve the effectiveness of the confidence level. Compared with the prior art method of directly obtaining the confidence level from the database, it can avoid the problem of limited coverage of the access source IP address in the database itself, so that no matter what target access data is received, the confidence level that matches it can be calculated, thereby improving the accuracy of determining malicious access data.

[0118] In step S340, if at least one of the matching result, the traffic value and the confidence meets the preset determination condition, the target access data is determined to be malicious access data.

[0119] The preset determination condition is used to limit the condition under which the target access data becomes malicious access data. Optionally, if at least one of the matching result, the flow value, and the confidence meets the preset determination condition, the method of determining that the target access data is malicious access data can be specifically: if the matching result, the flow value, and the confidence meet the preset determination condition, the target access data is determined to be malicious access data.

[0120] In addition, after determining that the target access data is malicious access data, the above method may also include the following steps: parsing the target access data to obtain information about key fields in the target access data; wherein the key fields may include fields to which the access source IP belongs; and further, the malicious access database and / or the confidence database may be updated according to the access source IP of the target access data. Based on this, the above method may also include the following steps: adding the access source IP in the target access data to a rejection response list; wherein the rejection response list may include access source IPs corresponding to different malicious access data. Furthermore, it may also include: when new access data is received, obtaining the access source IP of the new access data, and if the access source IP of the new access data belongs to the rejection response list, discarding the new access data.

[0121] In addition, after determining that the target access data is malicious access data, the above method may further include the following steps: generating a reporting request according to the target access data and sending the reporting request to a cloud server, so as to realize cloud recording of the target access data.

[0122] In addition, after determining that the target access data is malicious access data, the above method may further include: generating alarm information according to the malicious access data and feeding back the alarm information to the administrator terminal to prompt the administrator to process the malicious access data in a timely manner.

[0123] As an optional embodiment, the above method also includes: calculating the traffic threshold corresponding to the current moment based on the traffic at the historical moment; if the traffic value of the target access data is greater than or equal to the traffic threshold, then determining that the traffic value meets the preset determination condition; if the matching result is used to indicate that the target access data matches the malicious access database, then determining that the matching result meets the preset determination condition; if the confidence is a divergent result, then determining that the confidence meets the preset determination condition.

[0124] Specifically, the flow threshold corresponding to the current moment is calculated based on the flow at the historical moment, including: obtaining the flow at the historical moment (i) λ = {x i-k+1 , x i-k+2 ,......,x i}, and for the flow λ={x i-k+1 , x i-k+2 ,......,x i}Perform feature learning to construct the following expression corresponding to the current moment (i+1); predict the flow k at the current moment (i+1) according to the following expression, and then determine the flow threshold μ corresponding to the current moment (i+1) according to k; wherein the distribution of flow k can satisfy the Poisson distribution.

[0125]

[0126] Among them, for the historical moment (i), λ=C i +T i +R i , C i , T i , R i They are periodic term, trend term and residual term respectively. Specifically, P is the period, a n and b n is a system of Fourier series; T i =(i+a(i)δ)*i+(m+a(i)γ), i+a(i)δ is the slope that changes with time, and m+a(i)γ is the bias that changes with time; The residual term at historical moment (i) is the sum of the residual terms of the previous p time points plus the sum of the fitting errors of the previous q time points plus the random error term ε i , ε i Satisfies the standard normal distribution. According to λ=C i +T i +R i By learning the features of the current moment (i+1), we can construct the λ=EC i+1 +ET i+1 +ER i+1 ,λ=EC i+1 +ETi+1 +ER i+1 It can be substituted into the above expression to participate in the calculation of the traffic threshold.

[0127] In addition, if the confidence is a converged result and the converged result does not depend on the prior information, it is determined that the confidence does not meet the preset determination condition.

[0128] It can be seen that the implementation of this optional embodiment can reduce the probability of missed detection and the probability of misjudgment of normal access by determining multiple conditions.

[0129] See also Figure 6 , Figure 6 The flowchart of the method for determining malicious access data according to an embodiment of the present application is schematically shown. Figure 6 As shown, the method for determining malicious access data may include: steps S600 to S680.

[0130] Step S600: Parse the legitimate access data into structured data, and determine the structured data as a user portrait; wherein the structured data includes multiple preset fields and field information corresponding to the multiple preset fields; the multiple preset fields include at least one of traffic composition, access source IP, access operator, regional affiliation and access frequency of the access source IP.

[0131] Step S610: construct a malicious access database according to the malicious access data in the historical determination results, and synchronously update the malicious access database in real time according to the malicious access data update message in the cloud server.

[0132] Step S620: parse the target source address in the target access data, and detect whether the target source address hits the malicious source address set in the malicious access database. If so, determine that the target access data matches the malicious access database.

[0133] Step S630: Determine a target user profile corresponding to the target source address from the user profile, and determine the access frequency in the target user profile as the traffic value corresponding to the target access data.

[0134] Step S640: Determine the prior information of the target access data according to the confidence database; wherein the confidence database includes the confidence corresponding to at least one of the legitimate access data and the malicious access data.

[0135] Step S650: Determine the traffic distribution of the access frequency in the target user portrait per unit time, and calculate the likelihood function of the target access data based on the traffic distribution.

[0136] Step S660: Calculate the a posteriori information corresponding to the target access data as the confidence level according to the a priori information and the likelihood function.

[0137] Step S670: Calculate the traffic threshold corresponding to the current moment based on the traffic at the historical moment. If the traffic value of the target access data is greater than or equal to the traffic threshold, then the traffic value is determined to meet the preset judgment condition; if the matching result is used to indicate that the target access data matches the malicious access database, then the matching result is determined to meet the preset judgment condition; if the confidence is a divergent result, then the confidence is determined to meet the preset judgment condition.

[0138] Step S680: If at least one of the matching result, the traffic value and the confidence meets the preset determination condition, the target access data is determined to be malicious access data.

[0139] It should be noted that steps S600 to S680 are Figure 3 The steps and their embodiments shown correspond to each other. For the specific implementation of steps S600 to S680, please refer to Figure 3 The steps and embodiments shown are not described in detail here.

[0140] It can be seen that implementation Figure 6 The method shown can determine malicious access data based on user portraits and malicious access databases, improve the accuracy of malicious access data determination, and reduce the probability of missed determination, thereby helping to avoid malicious access data attacks on computing resources. In addition, malicious access data determination can be performed through user portraits and malicious access databases to reduce the probability of false determination, thereby helping to avoid false cleaning of legitimate access data.

[0141] Furthermore, in this exemplary embodiment, a device for determining malicious access data is also provided. Figure 7 As shown, the malicious access data determination device 700 may include: a user portrait generation unit 701, a data calculation unit 702 and a malicious access determination unit 703, wherein:

[0142] A user portrait generating unit 701, configured to generate a user portrait based on the collected legal access data;

[0143] The data calculation unit 702 is used to determine the matching result between the target access data and the malicious access database when the target access data is detected, and calculate the flow value corresponding to the target access data according to the user profile;

[0144] The data calculation unit 702 is further used to determine the confidence level corresponding to the target access data according to the user portrait and the malicious access database;

[0145] The malicious access determination unit 703 is used to determine that the target access data is malicious access data when at least one of the matching result, the traffic value and the confidence meets the preset determination condition.

[0146] It can be seen that implementation Figure 7 The device shown can determine malicious access data based on user portraits and malicious access databases, improve the accuracy of malicious access data determination, and reduce the probability of missed determination, thereby helping to avoid malicious access data attacks on computing resources. In addition, malicious access data determination can be performed through user portraits and malicious access databases to reduce the probability of false determination, thereby helping to avoid false cleaning of legitimate access data.

[0147] In an exemplary embodiment of the present application, the above-mentioned device further includes:

[0148] A database construction unit (not shown), used to construct a malicious access database according to the malicious access data in the historical determination result before the data calculation unit 702 determines the matching result between the target access data and the malicious access database;

[0149] The database update unit (not shown) is used to synchronously update the malicious access database in real time according to the malicious access data update message in the cloud server.

[0150] It can be seen that the implementation of this optional embodiment can improve the subsequent calculation accuracy of matching results, traffic values ​​and confidence levels by building and updating the malicious access database, thereby improving the accuracy of determining malicious access data.

[0151] In an exemplary embodiment of the present application, the user profile generation unit 701 generates a user profile according to the collected legal access data, including:

[0152] Parse legal access data into structured data, and identify the structured data as user profiles;

[0153] Among them, the structured data includes multiple preset fields and field information corresponding to the multiple preset fields; the multiple preset fields include at least one of traffic composition, access source IP, access operator, regional affiliation and access frequency of access source IP.

[0154] It can be seen that the implementation of this optional embodiment can help improve the recording and acquisition of access frequency of target access data through the structured representation of legitimate access data, so as to determine malicious access data based on the access frequency of the target access data.

[0155] In an exemplary embodiment of the present application, the data calculation unit 702 determines the matching result between the target access data and the malicious access database, including:

[0156] Parse the target source address in the target access data;

[0157] Detect whether the target source address hits the malicious source address set in the malicious access database;

[0158] If so, it is determined that the target access data matches the malicious access database.

[0159] It can be seen that the implementation of this optional embodiment can improve the efficiency of determining malicious access data by associating the target source address with the malicious source address set, thereby facilitating the cleaning of malicious access data as soon as possible and avoiding the impact on the response efficiency of normal access.

[0160] In an exemplary embodiment of the present application, the data calculation unit 702 calculates the traffic value corresponding to the target access data according to the user portrait, including:

[0161] Determine a target user profile corresponding to the target source address from the user profiles;

[0162] The access frequency in the target user portrait is determined as the traffic value corresponding to the target access data.

[0163] It can be seen that implementing this optional embodiment can determine the flow value corresponding to the current target access data, and judging the target access data as malicious access data based on the flow value can help reduce the normal business cleaning damage rate and the attack traffic leakage cleaning rate.

[0164] In an exemplary embodiment of the present application, the data calculation unit 702 determines the confidence level corresponding to the target access data according to the user portrait and the malicious access database, including:

[0165] Determine the prior information of the target access data according to the confidence database; wherein the confidence database includes the confidence corresponding to at least one of the legitimate access data and the malicious access data;

[0166] Determine the traffic distribution of the access frequency in the target user profile per unit time, and calculate the likelihood function of the target access data based on the traffic distribution;

[0167] The posterior information corresponding to the target access data is calculated as the confidence according to the prior information and the likelihood function.

[0168] It can be seen that the implementation of this optional embodiment can improve the effectiveness of the confidence level. Compared with the prior art method of directly obtaining the confidence level from the database, it can avoid the problem of limited coverage of the access source IP address in the database itself, so that no matter what target access data is received, the confidence level that matches it can be calculated, thereby improving the accuracy of determining malicious access data.

[0169] In an exemplary embodiment of the present application, the above-mentioned device further includes:

[0170] A condition determination unit (not shown) is used to calculate a flow threshold corresponding to the current moment according to the flow at the historical moment, and if the flow value of the target access data is greater than or equal to the flow threshold, it is determined that the flow value meets the preset determination condition;

[0171] The condition determination unit is further used to determine that the matching result meets the preset determination condition when the matching result is used to indicate that the target access data matches the malicious access database;

[0172] The condition determination unit is further used to determine whether the confidence meets a preset determination condition if the confidence is a divergent result.

[0173] It can be seen that the implementation of this optional embodiment can reduce the probability of missed detection and the probability of misjudgment of normal access by determining multiple conditions.

[0174] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0175] Since the various functional modules of the malicious access data determination device of the example embodiment of the present application correspond to the steps of the example embodiment of the malicious access data determination method mentioned above, for details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the malicious access data determination method mentioned above in the present application.

[0176] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.

[0177] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0178] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0179] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0180] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0181] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for determining malicious access to data, characterized in that: include: Generate user profiles based on the collected legitimate access data; When target access data is detected, a matching result between the target access data and a malicious access database is determined, and a flow value corresponding to the target access data is calculated according to the user portrait; Determining the confidence level corresponding to the target access data according to the user portrait and the malicious access database; If at least one of the matching result, the traffic value and the confidence meets a preset determination condition, the target access data is determined to be malicious access data; Wherein, determining the confidence level corresponding to the target access data according to the user portrait and the malicious access database includes: Extract the target access source from the target access data; detect whether there is prior information corresponding to the target access source in the confidence database; if there is no prior information corresponding to the target access source, the target access source is randomly assigned as the prior information of the target access source; if the prior information exists, read the prior information; wherein the confidence database includes the confidence corresponding to at least one of the legitimate access data and the malicious access data; Determine the traffic distribution of the access frequency in the target user profile within a unit time, and calculate the likelihood function of the target access data according to the traffic distribution; wherein the target user profile is determined from the user profile, and the target user profile corresponds to the target source address in the target access data; The a posteriori information corresponding to the target access data is calculated according to the prior information and the likelihood function as the confidence.

2. The method according to claim 1, characterized in that Before determining the matching result between the target access data and the malicious access database, the method further includes: Constructing the malicious access database according to the malicious access data in the historical determination results; The malicious access database is synchronously updated in real time according to the malicious access data update message in the cloud server.

3. The method according to claim 1, characterized in that: Generate user profiles based on the collected legitimate access data, including: Parsing the legal access data into structured data, and determining the structured data as the user portrait; Among them, the structured data includes multiple preset fields and field information corresponding to the multiple preset fields respectively; the multiple preset fields include at least one of traffic composition, access source IP, access operator, regional affiliation and access frequency of the access source IP.

4. The method according to claim 1, characterized in that: Determining a matching result between the target access data and a malicious access database includes: Parsing the target source address in the target access data; Detecting whether the target source address hits the malicious source address set in the malicious access database; If yes, it is determined that the target access data matches the malicious access database.

5. The method according to claim 4, characterized in that Calculating the traffic value corresponding to the target access data according to the user profile includes: Determine a target user profile corresponding to the target source address from the user profiles; The access frequency in the target user portrait is determined as the traffic value corresponding to the target access data.

6. The method according to claim 1, characterized in that The method further comprises: Calculate the flow threshold corresponding to the current moment according to the flow at the historical moment, and if the flow value of the target access data is greater than or equal to the flow threshold, determine that the flow value meets the preset determination condition; If the matching result is used to indicate that the target access data matches the malicious access database, then determining that the matching result meets the preset determination condition; If the confidence level is a divergent result, it is determined that the confidence level meets the preset determination condition.

7. A malicious access data determination device, characterized in that: include: A user portrait generation unit, used to generate a user portrait based on the collected legal access data; A data calculation unit, configured to, when target access data is detected, determine a matching result between the target access data and a malicious access database, and calculate a flow value corresponding to the target access data according to the user portrait; The data calculation unit is further used to determine the confidence level corresponding to the target access data according to the user portrait and the malicious access database; a malicious access determination unit, configured to determine that the target access data is malicious access data when at least one of the matching result, the traffic value and the confidence meets a preset determination condition; The data calculation unit determines the confidence level corresponding to the target access data according to the user portrait and the malicious access database, including: Extract the target access source from the target access data; detect whether there is prior information corresponding to the target access source in the confidence database; if there is no prior information corresponding to the target access source, the target access source is randomly assigned as the prior information of the target access source; if the prior information exists, read the prior information; wherein the confidence database includes the confidence corresponding to at least one of the legitimate access data and the malicious access data; Determine the traffic distribution of the access frequency in the target user profile within a unit time, and calculate the likelihood function of the target access data according to the traffic distribution; wherein the target user profile is determined from the user profile, and the target user profile corresponds to the target source address in the target access data; The a posteriori information corresponding to the target access data is calculated according to the prior information and the likelihood function as the confidence.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 6 by executing the executable instructions.