Abnormal equipment detection method and device
By collecting and analyzing user operation event information on the terminal device, identifying abnormal devices that are batch controlled, solving the problem of group control equipment that is difficult to detect in the prior art, and improving the defense capabilities of the computer security system.
Patent Information
- Application Number
- CN202010754009.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-07-30
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2040-07-30
AI Technical Summary
The prior art is difficult to effectively detect and identify abnormal devices that use group control technology for batch control, especially in automated attacks or online fraud, and it is impossible to identify the controlled terminal devices in a timely manner.
By collecting user operation event information in the front-end code of the terminal device, extracting operation feature trajectories, and mapping them into two-dimensional images for clustering, the clusters containing a large number of devices are determined to be abnormal devices based on the similarity of the trajectory image.
It realizes effective detection of terminal devices that are controlled in batches, can identify automated attacks or online fraud, and improves the defense capabilities of the security system.
Smart Images

Figure CN112000559B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer security technology, and in particular, to an abnormal device detection method and apparatus.
Background Art
[0002] This section aims to provide background or context for the embodiments of the present application described in the claims. The descriptions herein are not considered prior art merely because they are included in this section.
[0003] With the large-scale development of the black industry that uses automation technology to seek illegal income, there has emerged a group control technology that can batch control a large number of computers or mobile phones for automated attacks or online fraud. For example, an attacker arranges a large number of computers or mobile phones in a room and then uses group control to attack a target website with these computers, or conducts online fraud such as "wool pulling".
Summary of the Invention
[0004] In view of this, the present application provides an abnormal device detection method and apparatus to effectively detect devices that use group control technology to batch control a large number of terminals for automated attacks or online fraud.
[0005] The specific technical solutions are as follows:
[0006] In a first aspect, the present application provides an abnormal device detection method, which includes:
[0007] A threat perception platform obtains user operation event information occurring in implementing a preset function on a web page collected by front-end code running on a terminal device;
[0008] Extract operation feature trajectories from the user operation event information;
[0009] Map the operation feature trajectories corresponding to each terminal device onto a two-dimensional image respectively to obtain a trajectory image corresponding to each terminal device;
[0010] Cluster the trajectory images corresponding to each terminal device based on the similarity between the trajectory images to obtain one or more clusters;
[0011] Determine that the terminal devices included in the clusters with the number of devices greater than or equal to a preset first quantity threshold are abnormal devices.
[0012] According to a preferred embodiment of the present application, the front-end code includes: script JS code embedded in a web page, code embedded in a mobile application, or code embedded in a desktop client.
[0013] According to a preferred embodiment of the present application, the operation event information includes: mouse event information;
[0014] Extracting the operation feature trajectory from the user operation event information includes:
[0015] The coordinate data of the mouse at each time point is extracted from the mouse event information to obtain the coordinate track of the mouse.
[0016] According to a preferred embodiment of the present application, the operation event information includes: keyboard event information;
[0017] Extracting the operation feature trajectory from the user operation event information includes:
[0018] The time interval between pressing each key in sequence or the time interval between pressing and releasing each key is extracted from the keyboard event information to obtain a track of the keyboard tapping interval.
[0019] According to a preferred embodiment of the present application, the operation event information includes: touch screen event information;
[0020] Extracting the operation feature trajectory from the user operation event information includes:
[0021] The coordinate data of the touch screen position at each time point is extracted from the touch screen event information to obtain the coordinate trajectory of the touch screen.
[0022] According to a preferred embodiment of the present application, the operation event information includes: motion sensor event information;
[0023] Extracting the operation feature trajectory from the user operation event information includes:
[0024] Extracting sensor data corresponding to each time point from the motion sensor event information;
[0025] The motion state trajectory is obtained according to the sensor data corresponding to each time point.
[0026] According to a preferred embodiment of the present application, the method further comprises:
[0027] The threat perception platform obtains the network environment information of the terminal device collected by the front-end code;
[0028] Clustering the network environment information of each terminal device within the same time period to obtain more than one cluster;
[0029] It is determined that the terminal devices included in the cluster including a number of devices greater than a preset second number threshold are abnormal devices.
[0030] According to a preferred embodiment of the present application, the network environment information includes at least one of the following:
[0031] The network address information of each terminal device in the intranet, the network address information of the connected access device, and the identification information of the connected base station.
[0032] In a second aspect, the present application provides an abnormal device detection device, the device comprising:
[0033] An information acquisition unit is used to acquire user operation event information that occurs when implementing a preset function on a web page collected by a front-end code running on a terminal device;
[0034] A trajectory extraction unit, used to extract an operation feature trajectory from the user operation event information;
[0035] An image mapping unit, used to map the operation feature trajectory corresponding to each terminal device onto a two-dimensional image to obtain a trajectory image corresponding to each terminal device;
[0036] A clustering processing unit, used for clustering the trajectory images corresponding to each terminal device based on the similarity between the trajectory images to obtain more than one cluster;
[0037] The abnormality determination unit is used to determine that the terminal devices included in the cluster whose number of devices is greater than or equal to a preset first number threshold are abnormal devices.
[0038] According to a preferred embodiment of the present application, the front-end code includes: script JS code embedded in a web page, code embedded in a mobile application, or code embedded in a desktop client.
[0039] According to a preferred embodiment of the present application, the operation event information includes: mouse event information, and the trajectory extraction unit is specifically used to extract the coordinate data of the mouse at each time point from the mouse event information to obtain the coordinate trajectory of the mouse; and / or,
[0040] The operation event information includes: keyboard event information, the trajectory extraction unit is specifically used to extract the time interval between pressing each key in sequence or the time interval between pressing and releasing each key from the keyboard event information to obtain the trajectory of the keyboard tapping interval; and / or,
[0041] The operation event information includes: touch screen event information, and the trajectory extraction unit is specifically used to extract the coordinate data of the touch screen position at each time point from the touch screen event information to obtain the coordinate trajectory of the touch screen; and / or,
[0042] The operation event information includes: motion sensor event information, and the trajectory extraction unit is specifically used to extract sensor data corresponding to each time point from the motion sensor event information, and obtain the motion state trajectory according to the sensor data corresponding to each time point.
[0043] According to a preferred embodiment of the present application, the information acquisition unit is further used to acquire the network environment information of the terminal device collected by the front-end code;
[0044] The cluster processing unit is further used to cluster the network environment information of each terminal device within the same time period to obtain more than one cluster;
[0045] The abnormality determination unit is further configured to determine that the terminal devices included in the cluster including a number of devices greater than a preset second number threshold are abnormal devices.
[0046] According to a preferred embodiment of the present application, the network environment information includes at least one of the following:
[0047] The network address information of each terminal device in the intranet, the network address information of the connected access device, and the identification information of the connected base station.
[0048] In a third aspect, the present application provides a device, comprising:
[0049] one or more processors;
[0050] a storage device for storing one or more programs,
[0051] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.
[0052] In a fourth aspect, the present application provides a storage medium comprising computer executable instructions, which are used to perform the method described above when executed by a computer processor.
[0053] It can be seen from the above technical scheme that the present application obtains the user operation event information that occurs when implementing the preset functions on the web page collected by the front-end code, and extracts the operation feature trajectory from it to obtain the trajectory image corresponding to the terminal device, and identifies whether the terminal device is an abnormal device based on the consistency reflected by the trajectory image. That is, if a large number of terminal devices show highly consistent operations when implementing the preset functions, these terminal devices may be terminal devices that are controlled in batches for automated attacks or online fraud.
Brief Description of the Drawings
[0054] Figure 1 An exemplary system architecture to which the abnormal device detection method or apparatus according to an embodiment of the present invention can be applied is shown;
[0055] Figure 2 A flow chart of an abnormal device detection method provided in Embodiment 2 of the present application;
[0056] Figure 3A flow chart of an abnormal device detection method provided in Embodiment 3 of the present application;
[0057] Figure 4 A structural diagram of a device provided in Embodiment 4 of the present application;
[0058] Figure 5 A block diagram of an exemplary computer system / server suitable for use in implementing embodiments of the present invention is shown. [Specific implementation method]
[0059] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application is described in detail below with reference to the accompanying drawings and specific embodiments.
[0060] Embodiment 1
[0061] Figure 1 An exemplary system architecture to which the abnormal device detection method or apparatus according to an embodiment of the present invention can be applied is shown.
[0062] like Figure 1 As shown, the system architecture may include a terminal device 101, a network 102 and a server 103. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.
[0063] The user can use the terminal device 101 to interact with the server 103 through the network 102. Various applications can be installed on the terminal device 101, such as voice interaction applications, web browser applications, communication applications, etc.
[0064] The terminal device 101 can be any terminal device, including but not limited to a smart phone, a smart tablet, a laptop, a PC, a smart wearable device, etc. In the terminal device 101, web pages can be browsed and operated through a browser, a mobile application (referring to an application installed in a mobile device), and a desktop client (referring to a client installed in a PC or a laptop). In this application, code can be embedded in a web page, a mobile application, or a desktop client, which is called a front-end code, which is responsible for collecting user operation event information occurring on the web page and the network environment information of the terminal device, and uploading it to the threat perception platform.
[0065] The threat perception platform can be set up and run in the above-mentioned server 103. It can be implemented as multiple software or software modules (for example, to provide distributed services), or it can be implemented as a single software or software module, which is not specifically limited here. Server 103 can be a single server or a server group consisting of multiple servers. The threat perception platform uses the user operation event information collected by the front-end code running on the terminal device to implement the preset function on the web page to detect abnormal devices. The specific detection method will be described in detail in Example 2.
[0066] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.
[0067] Embodiment 2
[0068] Figure 2 This is a flow chart of the abnormal device detection method provided in the second embodiment of the present application, which is executed by the threat perception platform. Figure 2 As shown in , the method may include the following steps:
[0069] In 201, the threat perception platform obtains user operation event information that occurs when implementing a preset function on a web page collected by a front-end code running on a terminal device.
[0070] The abnormal behavior identification in this application is targeted at web pages. Based on the strong interactivity of web pages, this application can embed JS code in the web page (the JS code runs after the web page is loaded), embed code in the mobile application or embed code in the desktop client, and use these codes to collect user operation event information on the web page. Since the core idea of this application is to determine whether there are a large number of terminal devices that perform highly consistent operations when implementing the same function to detect abnormal devices, the front-end code can collect user operation event information that occurs when implementing preset functions on the web page. For example, collect user operation event information that occurs when implementing the login function on the web page; for another example, collect user operation event information that occurs when purchasing a specific product on the web page, and so on.
[0071] The collected operation event information may include mouse event information and keyboard event information occurring on the web page of the desktop client, touch screen event information and motion sensor event information occurring on the web page of the mobile application, etc.
[0072] The front-end code can upload the collected user operation event information that occurs when implementing preset functions on the web page to the threat perception platform in a streaming or periodic manner so that the threat perception platform can store it. The threat perception platform can obtain the user operation event information that occurs on a specific web page, and obtain the device information from the user operation event information through the session information, including but not limited to the user ID (identification), application ID or device ID. The application ID can be the ID of the desktop client or the ID of the mobile application. If the user is anonymous, a visitor, etc. during the process of browsing the web page, the user ID is usually not carried in the session information, but the application ID or device ID may be carried. If the user is logged in during the process of browsing the web page, the user ID is usually carried in the session information. But usually the device ID is carried.
[0073] In 202, the threat perception platform performs data cleaning and normalization processing on the collected user operation event information.
[0074] The data cleaning of user operation event information may include, but is not limited to, filtering out user operation event information with incorrect data format or missing data, supplementing certain user operation event information, etc.
[0075] In 203, the threat perception platform extracts operation feature trajectories from the user operation event information.
[0076] Depending on the user operation event information, the extracted operation feature trajectory is also different. For mouse event information, it is mainly the mouse coordinate data at each time point, that is, each data point includes three-dimensional features: x-axis coordinate, y-axis coordinate and time. Then according to the time sequence, the coordinate trajectory of the mouse is obtained.
[0077] For keyboard event information, what can reflect human characteristics or machine characteristics is usually the keyboard tapping interval, including the time interval between pressing each key or the time interval between each key being pressed and being released. Therefore, the time interval between pressing each key in sequence or the time interval between pressing each key and being released in the process of realizing the preset function can be extracted from the keyboard event information to obtain the track of the keyboard tapping interval.
[0078] For touch screen event information, similar to mouse event information, it mainly contains the touch screen position data at each time point, that is, each data point includes three-dimensional features: x-axis coordinate, y-axis coordinate and time. Then, according to the time sequence, the coordinate track of the touch screen is obtained.
[0079] For motion sensor event information, the sensor data corresponding to each time point can be extracted from the motion sensor data information, and the motion state trajectory can be obtained based on the sensor data corresponding to each time point. The motion sensor can be a gyroscope, an acceleration sensor, a velocity sensor, etc. The sensor data at each time point can reflect the motion state of the terminal device at each time point, such as a stationary state, a handheld state, a flat state, a vertical state, etc. Taking the gyroscope as an example, each data point includes four-dimensional features: angular velocity and time relative to the X, Y, and Z axes. Then, according to the order of time, the angular velocity information at each time point is obtained, which reflects the posture of the terminal device.
[0080] In 204 , the operation feature trajectories corresponding to the terminal devices are respectively mapped onto the two-dimensional image to obtain the trajectory images corresponding to the terminal devices.
[0081] The operation feature trajectories corresponding to each terminal device are basically multi-dimensional feature data, and these multi-dimensional feature data are represented by two-dimensional images using a visualization method.
[0082] For three-dimensional feature data such as the coordinate trajectory of the mouse and the coordinate trajectory of the touch screen, they can be represented by scatter plots, bubble plots, etc., that is, mapped into two-dimensional bar charts, pie charts, scatter plots, bubble plots, etc.
[0083] Taking the coordinate trajectory of the mouse as an example, it can be mapped into a scatter plot. The horizontal axis in the scatter plot corresponds to the x-axis coordinate of the mouse data point, and the vertical axis in the scatter plot corresponds to the y-axis coordinate of the mouse data point. The position of the scatter point in the scatter plot corresponds to the coordinate position of the mouse data point, and the scatter points use different colors or data labels to represent each time point.
[0084] For two-dimensional feature data such as the trajectory of the time interval of keyboard tapping, it can be represented by a line graph, a bar graph, a pie chart, etc., that is, mapped into a two-dimensional line graph. For example, the horizontal axis of the line graph corresponds to the time point, the vertical axis corresponds to the time interval value, the points on the line graph correspond to the keyboard data points, and then the points are connected into a line.
[0085] For feature data with more than four bits, such as motion state trajectory, it can be represented by radar charts, that is, mapped into two-dimensional radar charts, etc. Taking the motion state trajectory generated by the gyroscope as an example, the three points of the triangle in the radar chart correspond to the angular velocities relative to the X, Y, and Z axes in the gyroscope data, and the distances of the three points from the center point of the radar chart correspond to the angular velocity values relative to the X, Y, and Z axes. Different colors or digital labels of the triangle correspond to different time points.
[0086] In 205 , based on the similarity between the trajectory images, the trajectory images corresponding to each terminal device are clustered to obtain one or more clusters.
[0087] After the above processing, there are trajectory images corresponding to each terminal device corresponding to the same function implementation on the web page. After clustering these trajectory images based on similarity, each cluster contains terminal devices with highly similar trajectory images. Here, the embodiment of the present application does not limit the clustering method, and the similarity threshold used in clustering can be set according to the experience value or experimental value.
[0088] In 206, it is determined that the terminal devices included in the cluster including the number of devices greater than or equal to a preset first number threshold are abnormal devices.
[0089] For the coordinate trajectory of the mouse, when operating the mouse to achieve a certain function, the mouse position is usually different between different users. If there are a large number of terminal devices with highly consistent mouse trajectories, that is, the number of terminal devices included in a cluster is greater than or equal to the preset first number threshold, it means that it is not a manual operation, but a batch manipulation of terminal devices using an automated method. The terminal devices included in the cluster are marked as abnormal devices.
[0090] As for the trajectory of keyboard tapping intervals, when tapping the keyboard to input information to achieve a certain function, the time interval between keys or the time interval between each key being pressed and popped up is usually different among different users. If there are a large number of terminal devices with highly consistent keyboard tapping intervals, that is, the number of terminal devices contained in a cluster of the two-dimensional image formed by the keyboard tapping interval trajectory after clustering is greater than or equal to the preset first quantity threshold, it means that it is not a manual operation, but a batch manipulation of terminal devices using an automated method, and the terminal devices contained in the cluster are marked as abnormal devices.
[0091] The principle of the coordinate track of the touch screen is similar to that of the coordinate track of the mouse.
[0092] As for the motion state trajectory, it is usually more suitable for mobile terminal devices. When users use mobile terminal devices to implement a certain function, the mobile terminal devices will inevitably have some shaking, jittering, movement, etc., and these "motion" states are different between different users. If there are a large number of mobile terminal devices whose motion states are highly consistent when implementing a function, that is, the number of terminal devices contained in a cluster of the two-dimensional image formed by the motion state trajectory after clustering is greater than or equal to the preset first number threshold, then it means that it is not human operation, but the result of batch control of terminal devices using an automated method.
[0093] In actual situations, the user completing the preset function on the web page may not be a single type of operation, but may be a combination of multiple types of operations. For example, for the implementation of the login operation, it may include mouse operation and keyboard input operation. In this case, the above-mentioned trajectory extraction, mapping, clustering and other processing can be performed on the mouse event information and the keyboard event information respectively. If the terminal device is identified as an abnormal terminal device through the mouse event information, and the terminal device is also identified as an abnormal terminal device through the keyboard event information, then the terminal device is finally determined to be an abnormal terminal device. Alternatively, if the terminal device is identified as an abnormal terminal device through the mouse event information, or if the terminal device is identified as an abnormal terminal device through the keyboard event information, then the terminal device can be determined to be an abnormal terminal device.
[0094] The identified abnormal terminal device information can be displayed to the administrator through the interface provided by the threat perception platform, or through other means such as system messages, text messages, and emails. In addition, the abnormal terminal device identification, user operation event information corresponding to the abnormal terminal device, and functions on the web page can also be displayed to the administrator. In this way, the administrator can analyze the information and further block the corresponding account or add a specific user or device to the blacklist.
[0095] Embodiment 3
[0096] Figure 3 This is a flow chart of the abnormal device detection method provided in Example 3 of this application, which is executed by the threat perception platform. Figure 3 As shown in , the method may include the following steps:
[0097] In 301, the threat perception platform obtains user operation event information that occurs when implementing a preset function on a web page collected by a front-end code running on a terminal device, as well as network environment information of the terminal device.
[0098] Among them, the network environment information of the terminal device collected by the front-end code includes the network address information of each terminal device in the intranet where the terminal device is located, the network address information of the connected access device, the identification information of the connected base station, etc.
[0099] Step 302 is the same as step 202 in the second embodiment and will not be described in detail.
[0100] In 303, the threat perception platform clusters the network environment information of each terminal device within the same time period to obtain more than one cluster.
[0101] The network environment information of the terminal device collected by the front-end code may be multiple pieces of information. By quantifying and mapping these pieces of information, a multi-dimensional network environment feature vector can be obtained. Clustering is performed based on the similarity between the network environment feature vectors of each terminal device. Each cluster obtained by clustering is a collection of terminal devices with highly similar network environments.
[0102] In 304, it is determined that the terminal devices included in the cluster including the number of devices greater than or equal to the preset second number threshold are abnormal devices.
[0103] Normally, there will not be too many terminal devices in the same network environment, such as a family or a room. If a large number of terminal devices are in one room, it is likely that these terminal devices are controlled in batches and are abnormal devices.
[0104] However, there are some special cases. For example, a company or an office building may have a large number of terminal devices. In this case, these types of network environments can be filtered.
[0105] It should be noted here that the "first" and "second" in the "first quantity threshold" and "second quantity threshold" involved in this application are merely names to distinguish the two quantity thresholds, and there is no limitation on the order, quantity and priority.
[0106] Steps 305 to 308 are the same as steps 203 to 206 in the second embodiment and are not described in detail here.
[0107] The difference between this embodiment and the second embodiment is that an anomaly detection method based on network environment information is added. In the third embodiment, anomaly detection based on network environment information is performed first, and then anomaly detection based on user operation event information is performed, but the present application is not limited to this execution order, and the two anomaly detection methods can be performed in any order or simultaneously.
[0108] The above is a detailed description of the method provided in the present application. The following is a detailed description of the device provided in the present application in conjunction with an embodiment.
[0109] Embodiment 4
[0110] Figure 4 This is a device structure diagram provided in the fourth embodiment of the present application. The device is set on the server side to realize the functions of the above-mentioned threat perception platform. Figure 4 As shown in , the device may include: an information acquisition unit 01, a trajectory extraction unit 02, an image mapping unit 03, a clustering processing unit 04 and an abnormality determination unit 05. The main functions of each unit include:
[0111] The information acquisition unit 01 is used to acquire user operation event information that occurs when implementing a preset function on a web page collected by a front-end code running on a terminal device.
[0112] The front-end code includes: script JS code embedded in the web page, code embedded in the mobile application, or code embedded in the desktop client, etc.
[0113] The track extraction unit 02 is used to extract the operation feature track from the user operation event information.
[0114] The operation event information may include at least one of mouse event information, keyboard event information, touch screen event information and motion sensor event information.
[0115] When the operation event information includes mouse event information, the track extraction unit 02 is specifically used to extract the coordinate data of the mouse at each time point from the mouse event information to obtain the coordinate track of the mouse.
[0116] When the operation event information includes keyboard event information, the trajectory extraction unit 02 is specifically used to extract the time interval between pressing each key in sequence or the time interval between pressing and releasing each key from the keyboard event information to obtain the trajectory of the keyboard tapping interval.
[0117] When the operation event information includes touch screen event information, the track extraction unit 02 is specifically used to extract the coordinate data of the touch screen position at each time point from the touch screen event information to obtain the coordinate track of the touch screen.
[0118] When the operation event information includes motion sensor event information, the trajectory extraction unit 02 is specifically used to extract sensor data corresponding to each time point from the motion sensor event information, and obtain the motion state trajectory according to the sensor data corresponding to each time point.
[0119] The image mapping unit 03 is used to map the operation feature tracks corresponding to each terminal device onto a two-dimensional image to obtain a track image corresponding to each terminal device. For the specific mapping method, please refer to the relevant description in the second embodiment.
[0120] The clustering processing unit 04 is used to cluster the trajectory images corresponding to each terminal device based on the similarity between the trajectory images to obtain more than one cluster.
[0121] The abnormality determination unit 05 is used to determine that the terminal devices included in the cluster whose number of devices is greater than or equal to a preset first number threshold are abnormal devices.
[0122] Furthermore, the information acquisition unit 01 is also used to obtain network environment information of the front-end code collection terminal device.
[0123] The network environment information may include at least one of the following: network address information of each terminal device in the intranet, network address information of the connected access device, and identification information of the connected base station.
[0124] The clustering processing unit 04 is further used to cluster the network environment information of each terminal device within the same time period to obtain more than one cluster.
[0125] The abnormality determination unit 05 is further configured to determine that the terminal devices included in the cluster including a number of devices greater than a preset second number threshold are abnormal devices.
[0126] Figure 5 A block diagram of an exemplary computer system / server 012 suitable for use in implementing embodiments of the present invention is shown. Figure 5 The computer system / server 012 shown is merely an example and should not limit the functionality and scope of use of embodiments of the present invention.
[0127] like Figure 5 As shown, computer system / server 012 is in the form of a general-purpose computing device. Components of computer system / server 012 may include, but are not limited to: one or more processors or processing units 016, system memory 028, and bus 018 connecting different system components (including system memory 028 and processing unit 016).
[0128] Bus 018 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.
[0129] The computer system / server 012 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer system / server 012, including volatile and non-volatile media, removable and non-removable media.
[0130] System memory 028 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 030 and / or cache memory 032. Computer system / server 012 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 034 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5not shown, usually called a "hard drive"). Although Figure 5 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 018 via one or more data medium interfaces. The memory 028 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.
[0131] A program / utility 040 having a set (at least one) of program modules 042 may be stored, for example, in the memory 028. Such program modules 042 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 042 generally perform the functions and / or methods of the embodiments described herein.
[0132] The computer system / server 012 may also communicate with one or more external devices 014 (e.g., keyboard, pointing device, display 024, etc.). In the present invention, the computer system / server 012 communicates with an external radar device, and may also communicate with one or more devices that enable a user to interact with the computer system / server 012, and / or communicate with any device that enables the computer system / server 012 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 022. Furthermore, the computer system / server 012 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 020. As shown, the network adapter 020 communicates with other modules of the computer system / server 012 through a bus 018. It should be understood that although Figure 5 Not shown, other hardware and / or software modules may be used in conjunction with computer system / server 012, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0133] The processing unit 016 executes various functional applications and data processing by running the programs stored in the system memory 028, such as implementing the method flow provided by the embodiment of the present invention.
[0134] The above-mentioned computer program may be set in a computer storage medium, that is, the computer storage medium is encoded with a computer program, and when the program is executed by one or more computers, the one or more computers execute the method flow and / or device operation shown in the above-mentioned embodiment of the present invention. For example, the method flow provided by the embodiment of the present invention is executed by the above-mentioned one or more processors.
[0135] With the development of time and technology, the meaning of medium is becoming more and more extensive, and the propagation path of computer programs is no longer limited to tangible media, but can also be downloaded directly from the network, etc. Any combination of one or more computer-readable media can be used. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, - but not limited to - electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media (non-exhaustive list) include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing programs, which can be used by or in combination with instruction execution systems, devices or devices.
[0136] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals 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 a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0137] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0138] Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0139] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.
Claims
1. A method for detecting abnormal equipment, characterized in that: The method includes: The threat perception platform obtains user operation event information that occurs when implementing preset functions on a web page collected by the front-end code running on the terminal device; Extracting operation feature tracks from the user operation event information; Mapping the operation feature trajectories corresponding to each terminal device onto the two-dimensional image to obtain the trajectory image corresponding to each terminal device; Based on the similarity between the trajectory images, the trajectory images corresponding to each terminal device are clustered to obtain more than one cluster; Determine that the terminal device corresponding to the trajectory image included in the cluster including a number of devices greater than or equal to a preset first number threshold is an abnormal device; Extracting the operation feature trajectory from the user operation event information includes at least one of the following items: The operation event information includes: mouse event information, from which the coordinate data of the mouse at each time point is extracted to obtain the coordinate track of the mouse; The operation event information includes: keyboard event information, from which the time interval between pressing each key in sequence or the time interval between pressing and releasing each key is extracted to obtain a track of keyboard tapping intervals; The operation event information includes: touch screen event information, from which coordinate data of the touch screen position at each time point is extracted to obtain a coordinate trajectory of the touch screen; The operation event information includes: motion sensor event information, from which sensor data corresponding to each time point is extracted; and a motion state trajectory is obtained according to the sensor data corresponding to each time point.
2. The method according to claim 1, characterized in that The front-end code includes: script JS code embedded in a web page, code embedded in a mobile application, or code embedded in a desktop client.
3. The method according to any one of claims 1 to 2, characterized in that The method further includes: The threat perception platform obtains the network environment information of the terminal device collected by the front-end code; Clustering the network environment information of each terminal device within the same time period to obtain more than one cluster; It is determined that the terminal device corresponding to the network environment information included in the cluster including a number of devices greater than a preset second number threshold is an abnormal device.
4. The method according to claim 3, characterized in that: The network environment information includes at least one of the following: The network address information of each terminal device in the intranet, the network address information of the connected access device, and the identification information of the connected base station.
5. An abnormal equipment detection device, characterized in that: The device includes: An information acquisition unit is used to acquire user operation event information that occurs when implementing a preset function on a web page collected by a front-end code running on a terminal device; A trajectory extraction unit, used to extract an operation feature trajectory from the user operation event information; An image mapping unit, used to map the operation feature trajectory corresponding to each terminal device onto a two-dimensional image to obtain a trajectory image corresponding to each terminal device; A clustering processing unit, used for clustering the trajectory images corresponding to each terminal device based on the similarity between the trajectory images to obtain more than one cluster; an abnormality determination unit, configured to determine that a terminal device corresponding to a trajectory image included in a cluster including a number of devices greater than or equal to a preset first number threshold is an abnormal device; The operation event information includes: mouse event information, and the trajectory extraction unit is specifically used to extract the coordinate data of the mouse at each time point from the mouse event information to obtain the coordinate trajectory of the mouse; and / or, The operation event information includes: keyboard event information, the trajectory extraction unit is specifically used to extract the time interval between pressing each key in sequence or the time interval between pressing and releasing each key from the keyboard event information to obtain the trajectory of the keyboard tapping interval; and / or, The operation event information includes: touch screen event information, and the trajectory extraction unit is specifically used to extract the coordinate data of the touch screen position at each time point from the touch screen event information to obtain the coordinate trajectory of the touch screen; and / or, The operation event information includes: motion sensor event information, and the trajectory extraction unit is specifically used to extract sensor data corresponding to each time point from the motion sensor event information, and obtain the motion state trajectory according to the sensor data corresponding to each time point.
6. The device according to claim 5, characterized in that The front-end code includes: script JS code embedded in a web page, code embedded in a mobile application, or code embedded in a desktop client.
7. The device according to any one of claims 5 to 6, characterized in that The information acquisition unit is further used to acquire the network environment information of the terminal device collected by the front-end code; The cluster processing unit is further used to cluster the network environment information of each terminal device within the same time period to obtain more than one cluster; The abnormality determination unit is further used to determine that the terminal device corresponding to the network environment information included in the cluster whose number of devices is greater than a preset second number threshold is an abnormal device.
8. The device according to claim 7, characterized in that The network environment information includes at least one of the following: The network address information of each terminal device in the intranet, the network address information of the connected access device, and the identification information of the connected base station.
9. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.
10. A storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to perform the method according to any one of claims 1 to 4.
Citation Information
Patent Citations
Network data flow detection method and device
CN110213227A
Econnoisseur identification method and device based on user behavior detection and electronic equipment
CN110363540A
Attack source detection method and device, equipment and computer storage medium
CN110958208A
