JP2018147172A - Abnormality detection device, abnormality detection method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To suppress an increase in data necessary to learn the detection of abnormality.SOLUTION: An abnormality detection device includes: a learning part for learning correlation between data elements of a plurality of kinds of data acquired from a detection object in each unit classified on the basis of the height of correlation between the data elements by using a plurality of learning units generated about the unit, and outputting a learning result in the case that a detection object of abnormality is normal; and a detection part for calculating an abnormality degree showing the degree of a collapse of correlation of data element groups classified into the unit about the data element groups of a plurality of kinds of data acquired from the detection object at a plurality of timings on the basis of a learning result relating to the unit in each unit, and detecting abnormality of the detection object on the basis of the abnormality degree in each unit.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an abnormality detection device, an abnormality detection method, and a program.

  In real-time abnormality detection, various data are regularly observed, and “abnormality” is detected when the data shows a tendency different from the normal state. Here, the anomaly detection algorithm performs learning using the data of the “learning period” defined as normal in advance as teacher data, and in the “test period” in which anomaly detection is performed, the observed test data and learning Suppose that the trend of the teacher data is compared. As such an anomaly detection algorithm, an algorithm has been proposed that learns the correlation between various data during normal operation, and determines that it is “abnormal” when the correlation between the learned data collapses during the test period. (For example, Non-Patent Document 1, Non-Patent Document 2, Non-Patent Document 3).

  Such an algorithm has an advantage that abnormality detection can be performed using only normal data without using abnormal data that is difficult to determine whether it is abnormal or not.

Hodge, Victoria J., and Jim Austin. "A survey of outlier detection methodologies." Artificial intelligence review 22.2 (2004): 85-126. Mayu Hamada, Takehisa Yairi, "Detection of spacecraft anomalies by dimension reduction using auto-encoder", Proceedings of National Conference of the Japanese Society for Artificial Intelligence 28, 1-3, 2014 Ringberg, Haakon, et al. "Sensitivity of PCA for traffic anomaly detection." ACM SIGMETRICS Performance Evaluation Review 35.1 (2007): 109-120.

  However, if a lot of data with low correlation is included in the input, the pattern of the state that the data can take normally increases accordingly, so the teacher data required for learning increases, and there is not enough teacher data Accurate abnormality detection becomes difficult. In particular, when the type of data to be observed increases, such a problem becomes more prominent because data with low correlation increases.

  The present invention has been made in view of the above points, and an object thereof is to suppress an increase in data required for learning for detecting an abnormality.

  Therefore, in order to solve the above-described problem, the abnormality detection device calculates the correlation between data elements of a plurality of types of data obtained from the detection target when the abnormality detection target is normal, and the correlation between the data elements. For each unit classified based on height, a learning unit that learns using a plurality of learners generated for the unit and outputs a learning result, and a plurality of types obtained at a plurality of timings from the detection target For each data unit group of the data, for each unit, based on the learning result related to the unit, calculate the degree of abnormality indicating the degree of collapse of the correlation of the data element group classified into the unit, and for each unit And a detection unit that detects an abnormality of the detection target based on the degree of abnormality.

  An increase in data required for learning for detecting an abnormality can be suppressed.

It is a figure which shows the system configuration example in 1st Embodiment. It is a figure which shows the hardware structural example of the abnormality detection apparatus 10 in 1st Embodiment. It is a figure which shows the function structural example of the abnormality detection apparatus 10 in 1st Embodiment. It is a flowchart for demonstrating an example of the process sequence of the learning process in 1st Embodiment. It is a flowchart for demonstrating an example of the process sequence of the detection process in 1st Embodiment. It is a figure for demonstrating an auto encoder. It is a flowchart for demonstrating the process sequence which the pre-processing part 13 performs additionally in 6th Embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a diagram illustrating an example of a system configuration in the first embodiment. In FIG. 1, a network N1 is a network that is an abnormality detection target. The network N1 is configured by connecting a plurality of nodes such as routers and server devices to each other, and packets are transmitted and received between arbitrary nodes in order to provide a predetermined service.

  Measuring devices 20 are arranged at a plurality of locations in the network N1. The measuring device 20 collects observation data obtained by monitoring the arrangement location at a plurality of timings. Examples of collected observation data include MIB (Management Information Base) data, NetFlow flow data, CPU usage rate, and the like.

  MIB is a common policy among manufacturers for monitoring network devices. The MIB data is aggregated in units of, for example, 5 minutes, and includes “time, host name, interface (IF) name, input data amount (ibps), output data amount (obsps)”, and the like.

  NetFlow is a technology that performs network monitoring in units of flows, and information about the flows is output when communication is completed. The flow is a unit for grasping “where” and “where” “what kind of communication” “how much” is performed, and the IP address (srcIP) on the sender side of the communication , The sender side port number (srcport), the receiver side IP address (dstIP), the receiver side port number (dstport), and the communication protocol (proto). The flow data includes “flow start time, srcIP, srcport, dstIP, dstport, protocol, flow duration, total number of transmitted packets, total number of transmitted bytes”, and the like.

  The CPU usage rate is, for example, the usage rate of a CPU such as a server device or a router included in the network N1.

  Observation data collected by the measurement device 20 is collected by the abnormality detection device 10. The abnormality detection device 10 learns the characteristics at the normal time from the collected observation data, and detects the occurrence of abnormality in the observation data input thereafter based on the learning result (determines whether there is an abnormality). It is a computer. Note that a process in which normal feature learning is performed is referred to as a “learning process”. A process in which an abnormality is detected based on a result learned in the learning process is referred to as a “test process”.

  FIG. 2 is a diagram illustrating a hardware configuration example of the abnormality detection apparatus 10 according to the first embodiment. 2 includes a drive device 100, an auxiliary storage device 102, a memory device 103, a CPU 104, an interface device 105, and the like, which are mutually connected by a bus B.

  A program that realizes processing in the abnormality detection apparatus 10 is provided by a recording medium 101 such as a CD-ROM. When the recording medium 101 storing the program is set in the drive device 100, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 100. However, the program need not be installed from the recording medium 101 and may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program and also stores necessary files and data.

  The memory device 103 reads the program from the auxiliary storage device 102 and stores it when there is an instruction to start the program. The CPU 104 executes functions related to the abnormality detection device 10 according to a program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network.

  FIG. 3 is a diagram illustrating a functional configuration example of the abnormality detection device 10 according to the first embodiment. 3, the abnormality detection device 10 includes a reception unit 11, a learning process control unit 12, a preprocessing unit 13, a learning unit 14, a detection process control unit 15, a detection unit 16, and the like. Each of these units is realized by processing that one or more programs installed in the abnormality detection apparatus 10 cause the CPU 104 to execute. The abnormality detection apparatus 10 also uses a teacher data storage unit 121, a parameter storage unit 122, an observation data storage unit 123, a learning result storage unit 124, a learning data storage unit 125, and the like. Each of these storage units can be realized using, for example, a storage device that can be connected to the auxiliary storage device 102 or the abnormality detection device 10 via a network.

  In the teacher data storage unit 121, observation data that has been confirmed in advance to be collected in a normal state is stored as teacher data. However, the teacher data may be artificially created instead of being selected from the observation data.

The receiving unit 11 receives observation data from the measurement device 20. The received observation data is stored in the observation data storage unit 123. The learning process control unit 12 controls the learning process.

  The preprocessing unit 13 performs preprocessing on a set of teacher data, a set of observation data, or a set of learning data stored in the learning data storage unit 125. Pre-processing is processing such as extraction of feature amounts per unit time from a data set and normalization of extracted feature amounts. The feature amount is expressed in the form of a numerical vector. In the first learning, a teacher data group stored in the teacher data storage unit 121 is a target of preprocessing. When reception of observation data is started by the receiving unit 11, the observation data group is subjected to preprocessing. Furthermore, when the detection of the abnormality by the detection unit 16 is started and it is determined that the detection data is normal and the observation data stored in the learning data storage unit 125 as learning data reaches a predetermined number, the learning data group is subjected to preprocessing. It is said.

  The pre-processing unit 13 also generates or normalizes parameters for normalizing observation data or learning data (hereinafter referred to as “normalization parameters”) when performing pre-processing on the teacher data group or learning data group. The updated normalization parameter is stored in the parameter storage unit 122.

  The learning unit 14 performs learning based on teacher data or learning data. The learning result by the learning unit 14 is stored in the learning result storage unit 124.

  The detection process control unit 15 controls the detection process.

  The detection unit 16 uses a numerical vector generated when the observation data stored in the observation data storage unit 123 is preprocessed by the preprocessing unit 13 and a learning result stored in the learning result storage unit 124. The occurrence of abnormality is detected based on this. Specifically, the detection unit 16 detects the occurrence of an abnormality by calculating a difference from the learning result as a degree of abnormality for the preprocessed numerical vector and comparing the degree of abnormality with a threshold value. The value before normalization of the numerical vector in which no abnormality is detected is stored in the learning data storage unit 125 as learning data.

  Hereinafter, a processing procedure executed by the abnormality detection apparatus 10 will be described. FIG. 4 is a flowchart for explaining an example of the processing procedure of the learning process in the first embodiment. In the following, for the sake of convenience, an example in which flow data is a processing target will be described.

  When the learning process is started, the learning process control unit 12 acquires a teacher data group from the teacher data storage unit 121, and inputs the teacher data group to the preprocessing unit 13 (S101).

  Subsequently, the preprocessing unit 13 divides the input teacher data group into sets for each unit time (S102). The teacher data storage unit 121 stores teacher data for a unit time × U period (hereinafter referred to as “learning period”). Therefore, the teacher data group is divided into U sets.

  Subsequently, the preprocessing unit 13 extracts a feature amount according to the purpose for each divided set, and generates a multidimensional numerical vector having the extracted feature amount as an element of each dimension (S103).

  For example, it is assumed that the unit time is 1 minute, and the preprocessing unit 13 extracts the feature amount every minute. Further, the feature amount is assumed to be the total number of transmitted bytes of each protocol (TCP, UDP). In this case, assuming that the flow start time of the first teacher data is 12:00, the pre-processing unit 13 sets the flow start time t of all the teacher data to 11:55:00 <= t <12: For a set of teacher data (flow data) such as 00:00, the total number of transmitted bytes of all flows whose protocol is TCP, the total number of transmitted bytes of all flows whose protocol is UDP, and the like are calculated. A two-dimensional numerical vector having a quantity as an element of each dimension is generated. Similarly, numerical vectors are generated for (U-1) other sets.

  Note that the attribute of the feature amount can be specified as a combination such as “TCP and transmission port number 80”. Further, if each flow is considered to have a value such as “number of flows: 1”, the total number of flows of each attribute can be calculated in the same manner and regarded as a feature amount.

  Subsequently, the preprocessing unit 13 calculates the maximum value xmax_i of each metric i (each dimension i) in each numerical vector, and stores the calculated xmax_1 in the parameter storage unit 122 (S104). That is, in the first embodiment, the maximum value xmax_i of each metric i is a normalization parameter.

  Here, U = 3. Further, it is assumed that the numerical vector generated in step S103 is {{80, 20}, {90, 35}, {100, 50}}. This is because the total number of TCP transmission bytes and the total number of UDP transmission bytes in a certain three minutes are “TCP: 80 bytes, UDP: 20 bytes”, “TCP: 90 bytes, UDP: 35 bytes”, and “TCP: 100 bytes, UDP: "50 bytes". In this case, the maximum value xmax_i of each metric of these numerical vectors is {100, 50} (that is, xmax_1 = 100, xmax_2 = 50).

  Subsequently, the preprocessing unit 13 normalizes each numerical vector based on the normalization parameter (S105). Normalization is performed by dividing the value of the metric i of each numerical vector by the maximum value xmax_i. Therefore, the normalized numerical vector is {{0.8, 0.4}, {0.9, 0.7}, {1, 1}}.

  Subsequently, the learning unit 14 learns the numerical vector using a learning device (S106). The learning result is stored in the learning result storage unit 124.

  Subsequently, the learning process control unit 12 waits for the learning data for the learning period to be stored (accumulated) in the learning data storage unit 125 (S107). That is, the standby is continued until U number of numerical vectors before normalization are stored in the learning data storage unit 125. The learning data storage unit 125 stores a numerical vector determined to be normal (no abnormality has occurred) by the detection unit 16.

  When the numerical vectors for the learning period are stored in the learning data storage unit 125 (Yes in S107), the learning processing control unit 12 acquires the numerical vector group from the learning data storage unit 125, and preprocesses the numerical vector group. Input to the unit 13 (S108). The acquired numerical vector group is deleted from the learning data storage unit 125. Subsequently, step S104 and subsequent steps are executed for the numerical vector group. Therefore, in the next step S105, normalization is performed based on the newly calculated xmax_i.

  FIG. 5 is a flowchart for explaining an example of the processing procedure of the detection processing in the first embodiment. The processing procedure in FIG. 5 may be started any time after step S106 in FIG. 4 has been executed at least once. That is, the processing procedure of FIG. 5 is executed in parallel with the processing procedure of FIG.

In step S201, the detection processing control unit 15 waits for the unit time to elapse. The unit time is the same length as the unit time in the description of FIG. During this standby, the observation data collected in real time and received by the receiving unit 11 is stored in the observation data storage unit 123. When the unit time has elapsed (Yes in S201), the detection processing control unit 15 The observation data group for the time is acquired from the observation data storage unit 123, and the observation data group is input to the preprocessing unit 13 (S202).

  Subsequently, the preprocessing unit 13 extracts a feature amount according to the purpose from the observation data group, and generates a multidimensional numerical vector having the extracted feature amount as an element of each dimension (S203). For example, the total number of transmitted bytes of all flows whose protocol is TCP and the total number of transmitted bytes of all flows whose protocol is UDP are extracted, and a two-dimensional numerical vector having these as elements of each dimension is generated. Here, one numerical vector is generated.

  Subsequently, the preprocessing unit 13 normalizes the generated numerical vector based on the maximum value xmax_i stored in the parameter storage unit 122 (S204). That is, each metric i of the numeric vector is divided by the maximum value xmax_i.

  For example, when step S104 of FIG. 4 is executed only once based on the teacher data, the maximum value xmax_i is {100, 50}. Therefore, when the numerical vector is {60, 40}, the numerical vector is normalized to {0.6, 0.8}.

  Subsequently, the detection unit 16 executes an abnormality determination process (S205). In the abnormality determination process, whether or not there is an abnormality in the network N1 is determined based on the normalized numerical vector and the latest learning result stored in the learning result storage unit 124.

  When it is determined that there is no abnormality (Yes in S206), the detection processing control unit 15 stores the numerical vector before normalization of the numerical vector in the learning data storage unit 125 as learning data (S207). When it is determined that there is an abnormality (No in S206), the numerical vector before normalization of the numerical vector is not stored in the learning data storage unit 125. Therefore, the learning data storage unit 125 stores only normal numerical vectors.

  Subsequently, step S201 and subsequent steps are repeated. Note that, in the process of repeating step S201 and subsequent steps, the normalization parameter used in step S204 is updated as needed in step S104 of FIG. 4 being executed in parallel. As a result, the numerical vector can be normalized in consideration of the trend of the input observation data.

  For example, when U = 3, step S207 is executed three times, and {{60, 40}, {45, 20}, {30, 30}} is stored in the learning data storage unit 125. In this case, it is updated to xmax_1 = 60 and xmax_2 = 40, and the update result is reflected in the parameter storage unit 122.

  In the above description, an example in which the observation data is flow data has been described. However, flow data, MIB data, and a CPU usage rate may be received in parallel as observation data. In this case, each step of the processing procedure of FIGS. 4 and 5 may be executed for each data type (flow data, MIB data, and CPU usage rate).

  For example, for MIB data given in a format such as {hostID, interfaceID, ibps, obsps}, “host IDa ibps in unit time”, “host IDa obsps in unit time”, “host IDb in unit time” Ibps of host IDb in unit time "..." interfaces IDx ibs in unit time "," interfaceIDx obsps in unit time "," interfaceIDy ibps in unit time "," interfaceIDy obsps in unit time " It is possible to extract a numerical vector like

  Next, an example of step S106 in FIG. 4 and step S205 in FIG. 5 will be described. In steps S <b> 106 and S <b> 205, a numerical vector group assigned with the data type as a label is input to the learning unit 14 or the detection unit 16. In the present embodiment, the label is any one of “flow data”, “MIB data”, and “CPU usage rate”. For example, the label is given to the teacher data and the observation data by the measuring device 20 or the receiving unit 11. That is, the label to be given to the observation data can be specified based on the observation data collection source. The label is inherited by a numerical vector generated by the preprocessing unit 13.

  In step S106 of FIG. 4, the learning unit 14 generates a learning device for each data type. The learning unit 14 classifies the numerical vector based on the label given to the input numerical vector, and inputs the numerical vector to the learning device corresponding to the classification result. In the present embodiment, a “flow data learning device”, a “MIB data learning device”, and a “CPU usage rate learning device” are generated. As a learning device, an auto encoder (Non-Patent Document 2) or a principal component analysis (Non-Patent Document 3) that performs abnormality detection by learning a correlation between numerical vector metrics can be used. In this embodiment, an example in which an auto encoder is used as a learning device will be described.

  FIG. 6 is a diagram for explaining the auto encoder. The auto encoder is an anomaly detection algorithm based on deep learning. The auto encoder utilizes the fact that the input data at normal time has a correlation between metrics and can be compressed to a low dimension. Since the correlation between the input data is lost at the time of abnormality, the compression is not performed correctly, and the difference between the input data and the output data becomes large.

As shown in (1) of FIG. 6, the learning device (auto encoder) generated by the learning unit 14 performs learning so that the output layer (Layer L ₃ ) is close to the input layer (Layer L ₁ ). Specifically, the learning unit 14 duplicates the numerical vector, applies one to the input layer, applies the other to the output layer, performs learning, and outputs a learning result. The learning result is stored in the learning result storage unit 124. The learning result is a parameter group for the learning device. Since learning devices are generated for each data type, learning results are also output for each data type and stored in the learning result storage unit 124.

  On the other hand, similarly to the learning unit 14, the detection unit 16 also generates a learning device for each data type. As the learning device, a method corresponding to the learning device generated by the learning unit 14 in the auto encoder, the principal component analysis, or the like can be used as in the learning device generated by the learning unit 14.

  In step S205 in FIG. 5, the detection unit 16 performs “flow data learning device”, “MIB data learning device”, and “CPU usage rate learning” based on the learning result stored in the learning result storage unit 124. Is created. That is, the learning device generated by the detection unit 16 is the same as the learning device generated by the learning unit 14 when the learning result is output. As shown in (2) of FIG. 6, the detection unit 16 inputs the numerical vector for each data type input in step S205 to a learning device corresponding to the data type of the numerical vector, and inputs data to the learning device. The distance between the output data and the output data (an index indicating the degree of collapse of the correlation between metrics) is calculated as the degree of abnormality. In the present embodiment, a mean squared error (MSE) that is a distance between the input layer and the output layer of the auto encoder is calculated as the degree of abnormality. The calculation formula of MSE is as follows.

本実施の形態では、フローデータのＭＳＥ、ＭＩＢデータのＭＳＥ、ＣＰＵ使用率のＭＳＥの３種のＭＳＥが得られる。検知部１６は、得られたＭＳＥの平均を、最終的な異常度として計算し、最終的な異常度が予め定められた閾値を超えていた場合に異常であると判定する。そうでない場合、検知部１６は、正常とであると判定する。

In the present embodiment, three types of MSEs are obtained: MSE for flow data, MSE for MIB data, and MSE for CPU usage. The detection unit 16 calculates the average of the obtained MSEs as the final abnormality degree, and determines that the abnormality is abnormal when the final abnormality degree exceeds a predetermined threshold. Otherwise, the detection unit 16 determines that it is normal.

  As described above, according to the first embodiment, a learning device is generated for each type of data, and learning and abnormality detection are performed. Here, it is estimated that metrics (data elements) belonging to the same data type have high correlation. Therefore, it is possible to reduce the possibility that data with low correlation is input to the same learning device. As a result, an increase in data required for learning for detecting an abnormality can be suppressed.

  Next, a second embodiment will be described. In the second embodiment, differences from the first embodiment will be described. Points that are not particularly mentioned in the second embodiment may be the same as those in the first embodiment.

  In the second embodiment, the detection unit 16 calculates the weighted average of the degree of abnormality output from each learning device as the final degree of abnormality. At this time, an average value of MSE when a numerical vector group based on teacher data or learning data is input to the learning device is used as a weight.

  Therefore, in the second embodiment, every time the learning unit 14 executes Step S106 in FIG. 4, the learning result output from the learning device for each data type based on the teacher data or the numerical vector group of the learning data is displayed. When storing in the learning result storage unit 124, for each data type, a numerical vector for each data type is input to the learning device based on the learning result. By doing so, the learning unit 14 calculates the degree of abnormality for each data type and each numerical vector, and further calculates the average of the degree of abnormality for each data type. For example, if U = 3, three abnormalities are calculated for each data type, and an average of the abnormalities is calculated for each data type. The average degree of abnormality for each data type is stored in the learning result storage unit 124 together with the learning result. Therefore, “MSE average of flow data”, “MSE average of MIB data”, and “MSE average of CPU usage rate” are stored. Hereinafter, these are denoted as β ′ _ {train, 1}, β ′ _ {train, 2}, and β ′ _ {train, 3}, respectively.

  In the detection process, when calculating the average of the MSE obtained by inputting a numerical vector for each data type based on the observation data to each learning device, the data type having a larger MSE average based on the teacher data or the learning data, It is conceivable that the MSE based on the observation data also increases. Therefore, the detection unit 16 calculates a weighted average for the degree of abnormality for each data type, using the average of MSEs based on the teacher data or the learning data stored in the learning result storage unit 124 as a weight.

Specifically, the MSE when a numerical vector based on flow data, MIB data, and CPU usage rate observation data is input to the learning device based on the learning result is β_ {test, 1}, β_ {test, 2 }, Β_ {test, 3}, the detection unit 16 calculates the final abnormality degree β based on the following calculation formula.
β = (β_ {test, 1} / β ′ _ {train, 1} + β_ {test, 2} / β ′ _ {train, 2} + β_ {test, 3} / β ′ _ {train, 3}) / (1 / β ′ _ {train, 1} + 1 / β ′ _ {train, 2} + 1 / β ′ _ {train, 3})
This is because the weighting factor is the reciprocal of the average of MSEs based on teacher data or learning data (1 / β ′ _ {train, i}), and the larger the MSE based on teacher data or learning data, the larger the observed data. It shows that the weight of MSE based on is reduced.

  As described above, according to the second embodiment, the final abnormality degree can be calculated in the detection process in consideration of the difference in the degree of abnormality between the data types at the normal time.

  Next, a third embodiment will be described. In the third embodiment, differences from the first embodiment will be described. Points not particularly mentioned in the third embodiment may be the same as those in the first embodiment.

  In the third embodiment, the detection unit 16 determines whether there is an abnormality for each learner (that is, for each data type), and determines that there is an abnormality for at least one data type. Is determined to be “abnormal”.

  In the detection process, for each data type, the MSE obtained when a numerical vector based on the observation data is input to the learning device related to the data type is represented by β_ {test, 1}, β_ {test, 2}, β_ {test. , 3}. Here, it is assumed that the threshold is predetermined for each data type, and is expressed as θ_1, θ_2, and θ_3, respectively. In this case, for each learning device i, the detection unit 16 determines that there is an abnormality when β_ {test, i} ≧ θ_i, and that there is no abnormality when it is not. In the present embodiment, the presence / absence of abnormality is determined for each of the three types of learning devices of “flow data”, “MIB data”, and “CPU usage rate”, and at least one of them is determined to be “abnormal”. If there is a failure, the final determination of whether there is an abnormality is “abnormal”, and if not, “abnormal” is determined.

  As described above, according to the third embodiment, the same effects as those of the first embodiment can be obtained.

  Next, a fourth embodiment will be described. In the fourth embodiment, differences from the third embodiment will be described. Points that are not particularly mentioned in the fourth embodiment may be the same as those in the third embodiment.

  In the fourth embodiment, the detection unit 16 determines the presence / absence of abnormality for each learning device of each data type, and then determines the final determination only when it is determined that there is “abnormality” for all learning devices. The result is “abnormal”. For example, the final determination result is “abnormal” only when it is determined “abnormal” for all three learning devices of “flow data”, “MIB data”, and “CPU usage rate”. In other cases, the final determination result is “no abnormality”.

  As described above, according to the fourth embodiment, an effect similar to that of the first embodiment can be obtained.

  Next, a fifth embodiment will be described. In the fifth embodiment, differences from the third embodiment will be described. Points that are not particularly mentioned in the fifth embodiment may be the same as those in the third embodiment.

  In the fifth embodiment, the detection unit 16 determines the presence / absence of abnormality for each learning device of each data type, and then learns the number of learning devices determined as “abnormal” and “abnormal”. The final presence / absence of abnormality is determined by majority decision with the number of vessels. For example, when two or more learners out of three types of “flow data”, “MIB data”, and “CPU usage rate” are determined to be “abnormal”, the final determination result is “abnormal” Otherwise, the final determination result is “no abnormality”. If the number of learners is an even number, the number of “abnormal” and the number of “abnormal” are the same, and the handling is either “abnormal” or “abnormal” or randomly Whether to decide or the like is predetermined.

  As described above, according to the fifth embodiment, the same effect as that of the first embodiment can be obtained.

  Next, a sixth embodiment will be described. In the sixth embodiment, differences from the above embodiments will be described. Points that are not particularly mentioned in the sixth embodiment may be the same as those in each of the above embodiments.

  In the sixth embodiment, an example will be described in which a learning device is generated for each cluster based on the correlation between metrics of numerical vectors for each data type, not for each data type. That is, in each of the above embodiments, based on the estimation that each data element (metric) belonging to the same data type will have a high correlation, the data type is set to a high correlation between data elements (between metrics). Used as a unit to be classified based on. On the other hand, in the sixth embodiment, the data element group is not based on such estimation, but actually based on the high correlation between the data elements (between each metric). ) And the set is a unit classified based on the high correlation between data elements (between metrics).

  First, in the sixth embodiment, in step S103 of FIG. 4 and step S203 of FIG. 5, one numerical vector x is generated for each unit time, not for each data type. For example, one numerical vector x including each metric of the numerical vector of the flow data, each metric of the numerical vector of the MIB data, and each metric of the CPU usage rate is generated. A numerical vector x in a unit time t is expressed as x_ {i, t} (i = 1,..., N, t = 1,..., U).

  Further, the preprocessing unit 13 executes the processing procedure shown in FIG. 7 subsequent to step S103 in FIG.

  FIG. 7 is a flowchart for explaining a processing procedure additionally executed by the preprocessing unit 13 in the sixth embodiment.

  In step S301, the preprocessing unit 13 assigns an independent ID to each metric of the numerical vector x.

  Subsequently, the preprocessing unit 13 calculates a Pearson correlation coefficient for every set of two metrics (S302). That is, the correlation coefficient α_ {i, j} between metrics i and j is (x_ {i, 1},..., X_ {i, T}) and (x_ {j, 1},. ., {J, U}) and Pearson correlation coefficients (i = 1,..., N, j = 1,..., N, i <j).

  Subsequently, the preprocessing unit 13 clusters the IDs of the metrics into a predetermined number K of groups based on the Pearson correlation coefficient α_ {i, j} using a multidimensional scaling method (S303). Subsequently, the preprocessing unit 13 stores correspondence information between IDs and clusters indicating in which cluster each ID is classified in the learning result storage unit 124 (S304).

  Note that the processing procedure of FIG. 7 may be executed once. That is, it does not have to be executed following step S108 in FIG.

  In other cases, the data type in each of the above embodiments may be replaced with a cluster. For example, in step S <b> 106 of FIG. 4, the learning unit 14 generates a learning device for each cluster based on the correspondence information stored in the learning result storage unit 124 and performs learning. The metric corresponding to the ID classified into the cluster corresponding to the learner is input to each learner among the normalized numerical vectors. The learning result is stored in the learning result storage unit 124 for each cluster.

  5, the detection unit 16 generates a learning device for each cluster based on the learning result for each cluster stored in the learning result storage unit 124. The detection unit 16 inputs, to each learning device, a metric corresponding to an ID classified into a cluster to which the learning device corresponds, among the normalized numerical vectors. In the detection process (FIG. 5), for example, following step S <b> 203, the preprocessing unit 13 may assign an independent ID to each vector of the numeric vectors, similarly to step S <b> 301 in FIG. 7.

  As described above, according to the sixth embodiment, a learning device can be generated for each metric group having a higher correlation.

  Each of the above embodiments may be applied to data collected from other than the network. For example, the above-described embodiments may be applied to data collected from a computer system.

  In each of the above embodiments, the preprocessing unit 13 is an example of a classification unit.

  As mentioned above, although the Example of this invention was explained in full detail, this invention is not limited to such specific embodiment, In the range of the summary of this invention described in the claim, various deformation | transformation・ Change is possible.

DESCRIPTION OF SYMBOLS 10 Abnormality detection apparatus 11 Receiving part 12 Learning process control part 13 Preprocessing part 14 Learning part 15 Detection process control part 16 Detection part 20 Measuring apparatus 100 Drive apparatus 101 Recording medium 102 Auxiliary storage apparatus 103 Memory apparatus 104 CPU
105 interface device 121 teacher data storage unit 122 parameter storage unit 123 observation data storage unit 124 learning result storage unit 125 learning data storage unit B bus N1 network

Claims (8)

When the abnormality detection target is normal, the correlation between data elements of a plurality of types of data obtained from the detection target is determined for each unit classified based on the level of correlation between the data elements. A learning unit that learns using a plurality of learners generated for units and outputs a learning result;
Regarding data element groups of a plurality of types of data obtained from the detection target at a plurality of timings, the correlation of the data element groups classified into the units is broken based on the learning results of the units for each unit. A degree of abnormality indicating a degree of the detection, a detection unit that detects the abnormality of the detection target based on the degree of abnormality for each unit;
An abnormality detection device characterized by comprising: The unit is a unit for each type.
The abnormality detection device according to claim 1. When the abnormality detection target is normal, the data element group of a plurality of types of data obtained from the detection target has a classification unit that classifies into a plurality of sets based on the level of correlation,
The unit is a unit for each set.
The abnormality detection device according to claim 1. The detector is
Average degree of abnormality per unit,
Or, the weighted average of the degree of abnormality for each unit, with the degree of abnormality calculated based on the learning result for each unit as the data element group when the abnormality detection target is normal,
Or the degree of abnormality related to at least one of the units exceeds a threshold,
Or, the degree of abnormality related to all the units exceeds a threshold,
Or the number of units whose abnormalities exceed a threshold,
Detecting an abnormality of the detection target based on
The abnormality detection device according to any one of claims 1 to 3, wherein When the abnormality detection target is normal, the correlation between data elements of a plurality of types of data obtained from the detection target is determined for each unit classified based on the level of correlation between the data elements. A learning procedure for learning using a plurality of learners generated for units and outputting a learning result,
Regarding data element groups of a plurality of types of data obtained from the detection target at a plurality of timings, the correlation of the data element groups classified into the units is broken based on the learning results of the units for each unit. A detection procedure for calculating the degree of abnormality indicating the degree of detection and detecting the abnormality of the detection target based on the degree of abnormality for each unit;
An abnormality detection method characterized in that the computer executes. The unit is a unit for each type.
The abnormality detection method according to claim 5. A classification procedure for classifying data element groups of a plurality of types of data obtained from the detection target when the abnormality detection target is normal into a plurality of sets based on the level of correlation,
The unit is a unit for each set.
The abnormality detection method according to claim 5.   The program for functioning a computer as each part as described in any one of Claims 1 thru | or 4.

Images