Device and method for automatically analyzing malicious event logs

An AI-based chatbot engine automates endpoint threat analysis using a transformer network and LSTM, enabling efficient detection of malicious events without human intervention, suitable for on-premise and cloud-based security solutions.

JP2024543093AActive Publication Date: 2024-11-19NPCORE
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
JP2024529547
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-12-29
Filing Date
2022-11-16
Publication Date
2024-11-19
Estimated Expiration
2042-11-16

AI Technical Summary

Technical Problem

Existing solutions struggle to effectively analyze and respond to malicious code and intimidation attacks in real time, particularly at the endpoint level, without relying on professional analysts.

Method used

An AI-based chatbot engine is used to automatically analyze endpoint threat events by constructing an elastic search database management system, applying a transformer network and LSTM network, and implementing an automated behavior event analysis function for text classification, with an agent installed on user PCs to match events and transmit analysis results to an AI database.

Benefits of technology

This approach enables efficient and quick classification and analysis of large amounts of logs, automatically determining threatening events without human intervention, and can be applied to various security fields including on-premise solutions, EDR, SECaaS, and cloud-based APT and ransomware responses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024543093000001_ABST
    Figure 2024543093000001_ABST
Patent Text Reader

Abstract

A method and device for automatically analyzing malicious event logs, which are endpoint threatening events, by applying an AI-based chatbot engine is disclosed. The endpoint automatic analysis method processes logs by grouping them by process for efficient analysis of the event logs, generates sentences for process actions through a neuro-linguistic programming technique for AI analysis, digitizes actual malicious actions to use them as learning data for AI model learning, embodies a learning system based on a transformer algorithm to learn the learning data, and checks the grouped event logs in real time through an automatic event maliciousness analyzer based on a BERT and LSTM algorithm to analyze actual malicious actions, and detects malicious actions that are above a certain similarity and automatically determines them as threatening events.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an automatic analysis method for a malicious event log, and more particularly, to a method and apparatus for automatically analyzing a malicious event log, which is an endpoint threatening event, by applying an artificial intelligence (AI)-based chatbot engine. [Background technology]

[0002] As information and communications infrastructure continues to expand, various types of security threats using information and communications infrastructure (IT) are rapidly increasing. Recently, these advanced persistent threats (APTs) have frequently led to the leakage of important information within companies using malicious code, as well as the loss of focus on work due to internal users accessing non-work sites, resulting in information leakage. There is an urgent need for measures to prevent this.

[0003] In order to respond to security threats that are causing ongoing damage, it is necessary to analyze a huge amount of malicious code and threat-related data, and in order to effectively analyze related data, it is necessary to develop a malicious code learning and classification module that analyzes images through automatic learning.

[0004] Meanwhile, foreign and domestic APT solution makers related to existing malicious code detection and response technologies are offering various response solutions for each company to deal with new or mutated malicious code, but the reality is that it is not easy to respond in real time to security threats that are becoming increasingly huge and intelligent.

[0005] For this reason, endpoint detection and response (EDR) solution developers who are researching malicious code detection technology that utilizes machine learning are actively using artificial intelligence (AI) technology to detect some cyber threats that cannot be detected by existing solutions such as signature-based and rule-based solutions.

[0006] Additionally, endpoint intrusion incident response solutions that collect information from endpoint devices and automatically detect and respond to signs of cyber attacks in real time through correlation analysis and machine learning are also being actively introduced.

[0007] In addition, various threat intelligence tools for distributed remote forensics are being developed as a proactive response technology against malicious activities on business personal computers (PCs).In addition, various SAST (static application security testing) tools that can test the security of software applications developed in various languages ​​such as C / C++, Ruby, and Python are also being developed.

[0008] However, in order to effectively analyze and respond to the aforementioned malicious code and threat attacks, it would be most desirable to directly analyze the malicious code within an agent installed on a PC, terminal, server, etc., but no such solution has been proposed to date. Summary of the Invention [Problem to be solved by the invention]

[0009] The objective of the present invention is to provide an endpoint security solution that can automatically perform automatic analysis and detection of threatening events at an endpoint by utilizing a chatbot engine.

[0010] Another object of the present invention is to provide an endpoint automatic analysis device and method that can perform malicious event detection in conjunction with endpoint event detection rules by constructing an ElasticSearch database management system (DBMS), which is a large-capacity database (DB) for constructing event log datasets, constructing a transformer network and a long short-term memory (LSTM) network-based learning system for automatic analysis and detection of threat event logs, and providing an automated behavior event analysis function that can effectively classify malicious behavior events using a text classification function based on the above.

[0011] Another object of the present invention is to provide an AI-based endpoint detection and response (EDR) solution that applies a chatbot engine.

[0012] It is yet another object of the present invention to provide an endpoint automatic analysis device and method that can effectively automatically analyze malicious event logs by constructing an AI database that stores an AI module and event logs in an analysis server, installing an agent in a user PC, analyzing events of the user PC by performing rule matching using the agent, transmitting the analysis results in conjunction with the AI ​​database of the analysis server, performing grouping using process IDs and session information, generating text in order of process actions in the order of progression, transmitting the text to the AI ​​database, and constructing a data set.

[0013] Another object of the present invention is to provide an endpoint automatic analysis device and method that collects threat event data and event logs through the application of artificial intelligence technology, groups them by process identifiers and session identifiers, and groups them by process, automatically analyzes the threat process based on artificial intelligence, automatically determines threat events based on the automatic analysis, and provides analysis results and process trees of the transformer network to provide detection grounds. [Means for solving the problem]

[0014] According to one aspect of the present invention for solving the above technical problems, the malicious event log automatic analysis device is an endpoint detection & response (EDR) device for automatically analyzing and detecting events applying an artificial intelligence (AI)-based chatbot engine, and includes a processor and a memory. According to at least one instruction stored in the memory, the processor processes the event log by grouping by process for efficient analysis of the event log, generates sentences for the process actions through a natural language processing (NLP) technique for AI analysis, digitizes the malicious actions actually performed and uses them as learning data for learning an AI model, and implements a learning system based on a transformer algorithm to learn the AI ​​model using the learning data. In order to analyze actual malicious actions, the device is configured to check the grouped event logs in real time through an automatic event maliciousness analyzer based on a bidirectional encoder representations from transformers (BERT) and a long short-term memory (LSTM) algorithm, and detects and automatically determines that the malicious action target is a threatening event when the similarity is equal to or higher than a certain level.

[0015] In one embodiment, a deep learning-based chatbot engine for event log classification operates in an action sentence generation and labeling method for training an AI model using threat process actions, is designed with an optimal hierarchy based on performance based on six encoder and decoder layers of the Transformer architecture, is configured to adjust the learning rate to optimize the cost required for model training according to the learning progress time, may be configured with a model combining a Transformer-based BERT model and a dense layer, and an optimal model based on F1-score comparison between a traditional recurrent neural network (RNN) model based on LSTM and gated recurrent unit (GRU) and a Transformer-based model may be used.

[0016] In one embodiment, an AI module for event analysis may be coupled with the EDR system, where the AI ​​module may be coupled with a cloud-based EDR solution to provide an integrated service.

[0017] In one embodiment, the AI ​​modules may be managed by an appliance-type management server that is deployed at each site, or may be directly serviced on a cloud-based network.

[0018] A method for automatically analyzing malicious event logs according to another aspect of the present invention for solving the above technical problems comprises constructing an artificial intelligence module and a database for storing event logs in an integrated analysis server, installing an agent at an endpoint, and performing rule matching on the event logs in the agent to analyze the malicious event logs, the method including the steps of: performing grouping on the event logs using a process ID and session information; generating sentences in the order of process actions based on the event logs; and automatically analyzing the malicious event logs at the endpoint based on a dataset included in the sentences generated in the order of actions.

[0019] A method for automatically analyzing malicious event logs, according to yet another aspect of the present invention for solving the above technical problems, includes a step of processing logs by grouping them by process for efficient analysis of the event logs; a step of generating sentences for process actions through NLP (Natural Language Processing) techniques for AI analysis; a step of digitizing actual malicious actions and using them as learning data for learning an AI model; a step of generating a learning system based on a transformer algorithm to learn an AI model from the learning data; a step of checking the grouped event logs in real time through an automatic event maliciousness analyzer based on BERT and LSTM algorithms to analyze actual malicious actions; and a step of detecting and automatically determining that the target of the malicious action is a threatening event when it is similar to or above a certain level.

[0020] According to yet another aspect of the present invention for solving the above technical problems, an automatic analysis device for malicious event logs comprises: an artificial intelligence module and a database for storing event logs in an integrated analysis server; an agent is installed in an endpoint; and the agent performs rule matching for the event logs to analyze the malicious event logs. The apparatus includes a processor and a memory for storing at least one instruction executed by the processor, and the processor is configured to perform the steps of: performing grouping of the event logs using a process ID and session information according to the at least one instruction; generating a sentence in the order of process actions based on the event log; and automatically analyzing the malicious event log at the endpoint based on a dataset included in the sentence generated in the order of actions.

[0021] According to yet another aspect of the present invention for solving the above technical problems, there is provided an automatic endpoint analyzer for endpoint detection & response (EDR) using an AI-based chatbot engine, the automatic endpoint analyzer including a processor and a memory, and the processor is configured to: process the event log by grouping by process for efficient analysis, generate sentences for the process actions through a natural language processing (NLP) technique for AI analysis, digitize the actual malicious actions and use them as learning data for learning the AI ​​model, and implement a learning system based on a transformer algorithm to learn the AI ​​model with the learning data, and check the grouped event logs in real time through an automatic event maliciousness analyzer based on a bidirectional encoder representations form transformers (BERT) and a long short-term memory (LSTM) algorithm to analyze actual malicious actions, and detect the malicious action target if it is above a certain similarity, and automatically determine that it is a threatening event.

[0022] In one embodiment, the Transformer model for the Transformer algorithm may have an encoder layer and a decoder layer, and may be configured to generate position information of malicious behavior by calculating the position of words using the following equation (1), which is a cosine function, when the value obtained by adding 1 to the position of the embedding dimension in the embedding vector of each word in the postional encoding of the input layer is odd.

[0023] In one embodiment, the Transformer model for the Transformer algorithm may have an encoder layer and a decoder layer, and may be configured to generate position information of malicious behavior by calculating the position of words using the following equation (mathematical formula), which is a sine function, when the value obtained by adding 1 to the position of the embedding dimension in the embedding vector of each word in the postional encoding of the input layer is an even number.

[0024] In one embodiment, the decoder structure including the decoder hierarchy may be trained to predict words at each time point from a sentence matrix, and may be configured to apply a layer that masks future words so that future words cannot be referenced to the earliest stage of a decoder sub-layer. Effect of the Invention

[0025] According to the present invention, the device and method for automatically analyzing malicious event logs applying an artificial intelligence (AI)-based chatbot engine applies an endpoint detection and response (EDR) solution as a core engine and can be used as an analysis module for a solution that requires efficient and rapid classification and analysis of a large amount of logs, and can be used as a solution that automatically determines whether or not there is an infringement when a threatening act occurs using AI, even without the need for professional analysts.

[0026] In addition, the AI-based automatic analysis according to the present invention is not limited to endpoint event log analysis, but can be applied to a visualization platform that can test malicious code, greatly increasing the reliability of the analysis results of malicious code and malicious behavior, and has the advantage of being immediately applicable to cloud-based security service products such as SECaaS (security as a service).

[0027] The above-mentioned malicious event log automatic analysis device and method of the present invention can be effectively applied to the following fields. In the APT response field, it can be applied to an on-premise type solution for intelligent persistent threat response. In the EDR solution field, it can be applied to endpoint event behavior analysis, cause analysis and response solutions. In the SECaaS field, it can be applied to a cloud-based APT and ransomware response solution. And in the security operation field, it can be applied to the endpoint threat information visualization field for security operation automation. [Brief description of the drawings]

[0028] [Figure 1] 1 is a diagram illustrating the main configuration and operating principle of an automatic event analysis and detection system (hereinafter, simply referred to as "automatic analysis device") applying an artificial intelligence (AI)-based chatbot engine according to one embodiment of the present invention. [Diagram 2] 1 is a diagram for explaining an intrusion threat AI analysis process applied to endpoint detection & response (EDR) that can be adopted in the automatic analysis device of FIG. [Diagram 3] FIG. 2 is a diagram for explaining an AI-based threatening behavior detection function applied to an EDR that can be adopted in the automatic analysis device of FIG. [Figure 4] FIG. 2 is a schematic exemplary diagram of an application of an AI analysis module that can be adopted in the automatic analysis device of FIG. 1. [Diagram 5] FIG. 2 is a schematic diagram for explaining an AI engine for automatic analysis of a chatbot engine-based threat event log that can be adopted in the automatic analysis device of FIG. 1. [Figure 6] FIG. 2 is a schematic configuration diagram of an EDR system to which an AI module that employs a chatbot engine that can be adopted in the automatic analysis device of FIG. 1 is applied. [Figure 7]FIG. 2 is a diagram for explaining an EDR solution and an AI module linkage interface that can be adopted in the automated analyzer of FIG. 1. [Figure 8] FIG. 2 is a schematic block diagram of an AI module application configuration for event analysis that can be employed in the automated analysis device of FIG. 1. [Figure 9] 11 is an exemplary diagram illustrating a process of bundling session IDs and process IDs and grouping them by processor in a method for automatically analyzing a malicious event log according to another embodiment of the present invention (hereinafter, simply referred to as an "automatic analysis method"); [Figure 10] FIG. 10 is an exemplary diagram illustrating a malicious event in which normal actions are gathered together to perform a ransomware action in the automatic analysis method of FIG. [Figure 11] 10 is an exemplary diagram illustrating a malicious event in which normal actions are collected and a network information is collected or transmitted in the automatic analysis method of FIG. 9 . [Figure 12] 10 is an exemplary diagram illustrating a malicious event that does not include "terminated" in the event type in the automatic analysis method of FIG. 9; [Figure 13] FIG. 10 is a block diagram of a Transformer model network architecture that can be employed in the automated analysis method of FIG. [Figure 14] FIG. 14 is an exemplary diagram for explaining the structure of the transformer model in FIG. 13. [Figure 15] FIG. 14 is an exemplary diagram illustrating yet another configuration that can be adopted in the Transformer model of FIG. 13, which is a text classification structure using BERT and a dense layer. [Figure 16] FIG. 16 is an example diagram of text classification using the LSTM of FIG. 15, which can be used in conjunction with or instead of the Transformer model of FIG. 13. [Figure 17] 2 is a block diagram illustrating a form of security service provided by the automatic analysis device of FIG. 1. FIG. [Figure 18] FIG. 2 is a block diagram for explaining a performance evaluation process for AI-based automatic threat event analysis of the automatic analysis device of FIG. 1. [Figure 19] FIG. 11 is a block diagram illustrating the main configuration of an automatic analyzer according to still another embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0029] The present invention can be modified in various ways and can have various embodiments, and a specific embodiment will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to a specific embodiment, and it should be understood that the present invention includes all modifications, equivalents, and alternatives within the spirit and technical scope of the present invention. In describing each drawing, similar reference numerals are used for similar components.

[0030] Terms such as first, second, A, B, etc. may be used to describe various components, but the components should not be limited by these terms. These terms are used only to distinguish one component from another. For example, a first component may be named a second component and similarly, the second component may be named a first component without departing from the scope of the invention. The term "and / or" includes a combination of multiple associated listed items or any multiple associated listed items.

[0031] When a component is said to be "coupled" or "connected" to another component, it should be understood that it may be directly coupled or connected to the other component, but there may be other components in between. Conversely, when a component is said to be "directly coupled" or "directly connected" to another component, it should be understood that there are no other components in between.

[0032] The terms used in this application are merely used to describe certain embodiments and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "include" or "have" are intended to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and should be understood not to preclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0033] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which this invention pertains. Terms as defined in commonly used dictionaries should be interpreted to have a meaning consistent with the meaning they have in the context of the relevant art, and should not be interpreted in an idealized or overly formal sense unless expressly defined in this application.

[0034] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings. In order to facilitate an overall understanding of the present invention, the same reference numerals are used for the same components in the drawings, and duplicated descriptions of the same components are omitted.

[0035] FIG. 1 is a diagram illustrating the schematic configuration and operating principle of a device (hereinafter, simply referred to as an "automatic analysis device") that automatically analyzes event logs of malicious events, which are endpoint threatening events, by applying an artificial intelligence (AI)-based chatbot engine according to one embodiment of the present invention.

[0036] Referring to FIG. 1, an automated analysis device 100 includes a first module 110 for grouping, a second module 120 for storage, a third module 130 for construction, a fourth module 140 for analysis, and a fifth module 150 for automatic judgment.

[0037] The first module 110 groups logs collected from a user's personal computer (PC). The second module 120 quantifies and stores the collected event logs and grouped logs. The third module 130 builds a data set based on the quantified logs. The fourth module 140 performs automatic analysis of the event logs based on a transformer model. The fifth module 150 automatically determines threat events based on the results of the automatic analysis of the event logs.

[0038] The Transformer model for the Transformer algorithm has an encoder layer and a decoder layer, and can be configured to generate position information of malicious behavior by calculating the position (pos) of a word using the following equation (1), which is a cosine function, when the value obtained by adding 1 to the position of the embedding dimension in the embedding vector of each word in the postional encoding (PE) of the input layer is odd.

number

[0039] In the formula 1, D indicates the number of input dimensions of the event analyzer, and i indicates the order of the input dimensions.

[0040] In addition, the Transformer model for the Transformer algorithm may be configured to have an encoder layer and a decoder layer, and generate position information of malicious behavior by calculating the position of words using the following equation (2), which is a sine function, when the value obtained by adding 1 to the position of the embedding dimension in the embedding vector of each word in the postional encoding of the input layer is an even number.

number

[0041] In the formula 2, D indicates the number of input dimensions of the event analyzer, and i indicates the order of the input dimensions.

[0042] The automatic analysis device 100 may be connected to an artificial intelligence (AI) analysis web management system 200 through a network. The AI ​​analysis web management system 200 may be installed in an AI analysis server connected to a user's PC, and may include a module 210 for performing user management for administrators, a module 220 for monitoring the collection and analysis status, a module 230 for managing the collection and analysis system, and a module 240 for managing the AI ​​analysis status.

[0043] The above-mentioned automatic analysis device 100 is an endpoint detection & response (EDR) device for automatic analysis and detection of events using an AI-based chatbot engine, and includes a processor and a memory. In accordance with at least one instruction stored in the memory, the processor: processes logs by grouping them by process for efficient analysis of the event log, generates sentences for process actions through a natural language processing (NLP) technique for AI analysis, digitizes actual malicious actions and uses them as learning data for learning an AI model, and embodies a learning system based on a transformer algorithm to train an AI model with such learning data. In order to analyze actual malicious actions, the grouped event logs are checked in real time through an automatic event maliciousness analyzer based on a bidirectional encoder representations form transformers (BERT) and a long short-term memory (LSTM) algorithm, and if the target of the malicious action is more than a certain similarity, it is detected and automatically determined to be a threatening event.

[0044] The deep learning-based chatbot engine for event log classification operates in an action sentence generation and labeling method to allow the chatbot engine to learn threatening process actions, and is designed with an optimal hierarchy based on performance based on six encoder and decoder layers of the transformer architecture. It is configured to adjust the learning rate to optimize the cost required for model learning according to the learning progress time, and can be configured as a model that combines a transformer-based BERT model and a dense layer, and can use the optimal model based on the comparison of the F1-score between traditional RNN (recurrent neural network) models based on LSTM and GRU (gated recurrent unit) and transformer-based models.

[0045] In addition, the AI ​​module for event analysis can be linked to the EDR system. Here, the AI ​​module can provide integrated services by linking with a cloud-based EDR solution. Such AI modules can be managed by an appliance-type management server located at each site, or can be directly serviced on a cloud-based network.

[0046] Fig. 2 is a diagram for explaining an AI analysis process of an infringement threat applied to an endpoint detection & response (EDR) that can be adopted in the automatic analysis device of Fig. 1. Fig. 3 is a diagram for explaining an AI-based threatening behavior detection function applied to an EDR that can be adopted in the automatic analysis device of Fig. 1. And Fig. 4 is a schematic example diagram of an AI analysis module application that can be adopted in the automatic analysis device of Fig. 1.

[0047] Referring to FIG. 2, the intrusion threat AI analysis process applied to EDR, which can be adopted in an automatic analysis device, can standardize and store event logs by group in the analysis system AI DB in the EDR system or analysis system (S21).

[0048] Next, the analysis logs can be grouped by processor identifier (process ID) and session (session) (S22).

[0049] Next, action sentences can be generated from the event log (S23).

[0050] Next, the behavioral text can be analyzed using an AI platform (S24).

[0051] Next, a threatening event can be automatically determined based on the analyzed behavioral text (S25).

[0052] Next, the automatic judgment results can be transmitted to a web server DB, e.g., an Elastic DB, and the analysis and judgment results can be transmitted to a distributed system AI DB, and the threat event tree and analysis information can be transmitted to a display device for visualization (S26, S31).

[0053] The event log stored in the analysis system AI DB can be transmitted to an agent installed in the user's computer and used by the agent to collect information on threats of infringement (S27).

[0054] Next, the agent can automatically detect threatening behavior based on the collected infringement threat information (S28).

[0055] Next, the event logs collected through automatic detection of threatening behavior can be reported to the analysis system AI DB (S30).

[0056] That is, as shown in FIG. 3, the AI-based threatening behavior detection method applied to the EDR can be configured to perform an automatic analysis step (S32), a data collection step (S33), a log grouping step (S34), a threat detection step (S35), and a threatening event information visualization step (S36) after an automatic judgment step (S31) of a threatening event.

[0057] In other words, as shown in FIG. 4, after collecting an event log (S41), the system may be configured to perform a step of generating an event action statement (S42), a step of extracting features based on AI model learning by applying rules (S43), and a step of transmitting the result data and automatically determining whether or not the data is malicious (S44).

[0058] As described above with reference to Figures 2 and 4, the threat event automatic analysis and detection AI module applying a chatbot engine, which is a type of automatic analysis device, can be linked with an EDR system for endpoint security.

[0059] The AI ​​module can be configured to perform interface migration work to transfer event log data transferred to an existing web database to a newly constructed AI analysis database in order to apply AI to an existing EDR system.

[0060] The AI ​​module can also be equipped with an ElasticSearch DBMS (DB management system) for large-capacity databases (DBs) to build event log datasets.

[0061] In addition, the AI ​​module can be equipped with a transformer algorithm-based learning system for automatic analysis and detection of threat event logs.

[0062] The AI ​​module may also include functionality for automated behavioral event analysis that can classify malicious behavior events using a text classification function, and components corresponding to such functionality.

[0063] Additionally, the AI ​​module may be configured to detect malicious events in conjunction with endpoint event detection rules.

[0064] For the above-mentioned configuration, the AI ​​module collects threat event data, collects event logs, groups them by process ID and session ID, and groups them by process to automatically analyze threat processes based on AI, automatically judge threat events based on the results of the automatic analysis, and visualizes and displays the automatic analysis and judgment results of threat events and the process tree through a web user interface (Web UI).

[0065] In this way, in this embodiment, the event log can be automatically analyzed to automatically determine whether or not an event is malicious, and an automated system for event analysis can be constructed to obtain two advantages: high accuracy and rapid analysis.

[0066] FIG. 5 is a schematic diagram for explaining an AI engine for automatic analysis of a chatbot-based threat event log that can be adopted in the automatic analysis device of FIG.

[0067] Referring to Figure 5, the AI ​​engine that can be used in the automatic analysis device is a kind of chatbot engine that applies EDR, and performs a primary analysis of events extracted from an endpoint using rules (S51, S52), stores the analysis results in the AI ​​analysis server DB (S53, 54), and the AI ​​module can perform analysis log grouping of the stored data by process ID and session identifier. The rules can include indicators of compromise (IOC) and MITRE ATT&CK (adversarial tactics, techniques and common knowledge) attack methods.

[0068] In addition, the AI ​​engine can generate event action sentences that take the order of the event group into consideration, and can collect data by storing the generated action sentences in the AI ​​DB and constructing them as a dataset (S56). By using such a dataset, it is possible to prepare a trained analyzer that can be used for model training of a transformer-based model or an RNN series.

[0069] According to this configuration, the input event log is automatically analyzed by the learned analyzer and the classification probability is calculated, and based on this, automatic judgment of the threatening event is performed. The analysis and judgment results are stored in the web server DB, and the transformer-based automatic analysis and judgment results and the process tree action sequence can be visualized and provided to the user through the web user interface manager (web UI manager).

[0070] In addition, the AI ​​engine groups the action event logs collected through the agent using process IDs and sessions, etc., and creates a dataset by generating threatening action events as action sentences (S57). Using the action event dataset thus created, the AI ​​engine can automatically detect threatening event logs based on the analysis results from a transformer-based analyzer for speed and overall syntax analysis of long sentences, a text classification technique (S58, S59).

[0071] The automatically detected threat events can be stored in a web server DB, for example, an elastic DB, and used for automatic threat event judgment (S59). The analysis and judgment results can be stored in the web server DB or elastic DB (S60), and the analysis and judgment results can be displayed through a user interface (UI) (S61).

[0072] Fig. 6 is a schematic diagram of an EDR system to which an AI module using a chatbot engine that can be used in the automatic analyzer of Fig. 1 is applied. Fig. 7 is a diagram for explaining an EDR solution that can be used in the automatic analyzer of Fig. 1 and an AI module linking interface.

[0073] 6, the AI-based EDR system 100 using a chatbot engine is a type of automatic analysis device and may include an AI module 160 and an AI database 170 that stores an event log, and may be configured to analyze events of a user PC by performing rule matching with an agent installed in the user PC on a network through the AI ​​module, and to transmit the analysis result to a user PC, an analysis server, an elastic DB 260, etc. on the network in conjunction with the AI ​​database 170 of the analysis server. A web browser-based user interface 270 is installed in the elastic DB 260 to allow access to the user PC and other user terminals and to communicate with the user PC.

[0074] The main operating principle of the AI ​​module will be described below with reference to Figure 7. The process described below can be associated with a component that performs a corresponding function.

[0075] When an event occurs, the AI ​​module collects event logs from the agent (71). The collected logs are stored in a specific folder. Next, rule matching is performed through the rule module (72) and the results are stored in a specific folder. The collected logs and matching results can be provided to a user's PC on the web through the manager (73) or stored in DB (74). Here, the manager 73 can be constructed in server hardware or a cloud environment and can be linked to the AI ​​module like a DB server in a virtualized operating system.

[0076] Next, the logs stored in the DB 74 are grouped (75), and the grouped logs can be generated as an action sentence (76). The generated action sentence 76 can be stored in the database 74.

[0077] Also, machine learning (77) can be performed based on the logs and matching results stored in DB74, thereby creating a learning model file (78). And, the previously created action sentences 76 can be used to create the learning model file.

[0078] Next, action sentence analyzed results (79) can be generated using the learning model file. Then, an automatic judgement of threats (81) can be made based on the generated action sentence analyzed results (79) and a threshold setting (80), and if the judgment result is above or below a predetermined threshold result (82), the result can be configured to be stored in a manager DB 83 (83).

[0079] In other words, the analysis results attempted by the agent are called up, and grouping is performed using the process ID and session information, and sentences are generated in the order of progress and process actions, and then the sentences are transmitted to an artificial intelligence database (AI DB) to construct a data set.

[0080] FIG. 8 is a schematic block diagram of an AI module application configuration (EDR solution) for event analysis that can be adopted in the automatic analysis device of FIG.

[0081] 8, an EDR system corresponding to an EDR solution may broadly include an EDR integrated management server 300 and an agent 100. That is, the EDR system of this embodiment may be constructed as an AI-based EDR system that applies an AI module for event analysis.

[0082] The EDR integrated management server (hereinafter, simply referred to as "integrated management server") 300 may include a user interface (UI, 310), an AI-based event analysis module 320, a database management system (DBMS, 330), a plurality of behavior analysis engines 350, a server series operating system 360 such as Windows Server 2016R2, a Windows operating system (Windows OS), a platform 370 such as ESXi installed on an HPE ProLiant server, cloud computing services such as Amazon Web Services (AWS) and Microsoft Azure, cloud infrastructure for public institutions such as NHN Toast, and hardware (380) supporting the same. The hardware 380 may be cloud-based hardware.

[0083] The EDR system can collect event information from an agent (180) of the endpoint 100, transmit it to the integrated management server 300, and store the corresponding information in a DB management system 330 in the integrated management server 300. The stored information can be sequentially collected by an AI-based event analysis module 320 to perform an AI-based event analysis, and can be configured to apply the analysis results to a detection rule (rule) 182 in the endpoint 100.

[0084] The endpoint 100 may include a Windows operating system 102 and PC hardware (H / W) 104, but is not limited to this, and may include other operating systems such as the Android operating system that provide an environment in which an agent 180 can be installed and run.

[0085] The AI-based event analysis module 320 of the integrated management server 300 and the agent 180 of the endpoint 100 according to this embodiment are devices for performing the automatic analysis method of malicious event logs of this embodiment, and can be configured to perform the steps of: processing logs by grouping them by process for efficient analysis of the event logs; generating sentences for process actions through NLP (Natural Language Processing) techniques for AI analysis; digitizing actual malicious actions and using them as learning data for learning an AI model; generating a learning system based on a transformer algorithm to learn the learning data; checking the grouped event logs in real time through an automatic event maliciousness analyzer based on BERT and LSTM algorithms to analyze actual malicious actions; and detecting when the target of the malicious action is above a certain similarity and automatically determining that it is a threatening event.

[0086] FIG. 9 is an exemplary diagram illustrating a process of bundling session IDs and process IDs and grouping them by processor in an automatic malicious event log analysis method (or simply, an automatic analysis method) according to another embodiment of the present invention.

[0087] Referring to FIG. 9, the grouping process for automatic analysis of malicious event logs may include a log collection step (S91) and a grouping step (S92), and may further include a UI display step (S93) for displaying the grouped data in a user interface.

[0088] In a log collection step (S91), an event log is collected and stored for each session ID (SID) and process ID (PID).

[0089] In the grouping step (S92), the collected event logs are grouped by session identifier or process identifier.

[0090] FIG. 10 is an exemplary diagram illustrating a malicious event in which normal actions are gathered together to perform a ransomware action in the automatic analysis method of FIG.

[0091] 10, a malicious event in which normal actions are combined to perform ransomware actions can include simultaneous execution of start program registration (S101) for maintaining persistence, desktop screen change (S102) for requesting money, and file name change (S103) for file encryption. Such simultaneous events can be considered as a type of ransomware operation and can be determined as malicious actions (S104).

[0092] FIG. 11 is an exemplary diagram for explaining a malicious event that collects network information or transmits information by collecting normal actions in the automatic analysis method of FIG.

[0093] 11, a malicious event, which is a collection of normal actions to collect or transmit network information, may include a case where a process is executed (S111), a file is created or written (S112), and a network communication is performed (S113) simultaneously. Such a simultaneous event may be classified as a suspicious malicious event and may be determined as a suspicious malicious action (S114).

[0094] As described above with reference to Figures 9 to 11, the automatic analysis method can use an event log grouping technique for classifying process actions. That is, when only one event log is analyzed, the corresponding event log may be a threatening action event, but in most cases it is a normal action event, and actions determined to be normal gather together to carry out threatening actions, so grouping is performed in chronological order using session IDs such as parent process ID and current process ID, and malicious events can be analyzed through this.

[0095] FIG. 12 is an exemplary diagram for explaining a malicious event that does not include "terminated" in the event type in the automatic analysis method of FIG.

[0096] 12, the automatic analysis method can use a process action sentence generation process using an event log for the NLP technique. That is, if there is no action termination (Terminated, S122) in the grouped event log, it means that the process does not proceed to the end, so in the event group where the Terminated event exists, an event type, a changed value, and a process execution path are generated in consideration of the action order, and a malicious event log can be automatically analyzed using this.

[0097] In addition, a data set can be constructed with action sequence sentences to generate a learning model. In this case, sentences generated by the event action sentence generator can be stored in the database of the AI ​​analysis server, and labeling can be performed on the event action sentences generated to detect threatening events.

[0098] FIG. 13 is a block diagram for a Transformer model network architecture that can be employed in the automated analysis method of FIG.

[0099] Referring to FIG. 13, the automatic analysis device can use a learning system based on a transformer algorithm for AI analysis.

[0100] The learning system based on the Transformer algorithm is capable of parallel processing and has excellent performance in understanding the meaning between words, and can be composed of six encoder and decoder layers.

[0101] For example, the automatic analysis device inputs data in which the embedding of an event log is encoded in relation to the position of occurrence (positional encoding) to a first module, and through a first process (S132) of the first module, processes the input data through an encoder self-attention having multi-head self-attention, generalizes (add & norm) the input data and the result processed by the encoder self-attention, performs FFNN as a position criterion, generalizes the result by combining it with the generalized data, and outputs it.

[0102] Next, the automated analyzer can input the processing result of the first process (S132) to the multi-head self-attention of the second process of the second module. The second process (S134) of the second module can further include a masked decoder self-attention having a masked multi-head self-attention as a previous stage of the multi-head self-attention. The processing result of the masked decoder self-attention can be generalized by combining it with the input data of the corresponding module and then input to the multi-head self-attention. At this time, the multi-head self-attention can correspond to the encoder-decoder attention.

[0103] The output of the second process (S134) may be output through an output terminal such as a softmax of a dense neural network.

[0104] The relationship between the two steps (S132, S134) of the first and second modules described above can be applied equally to two adjacent layers of multiple processes performed in multiple layers, respectively. That is, the automatic analysis device can simultaneously perform automatic judgments for each event log group in parallel through the Transformer algorithm.

[0105] In addition, when attention is performed, the number of heads that proceed in parallel is set to 8, and the loss function can adopt a cross-entropy function to solve multi-class classification problems. In the case of the learning rate for optimizing the loss function, the magnitude of the learning rate can be gradually reduced as the learning progresses, and the value can be tuned so that the loss function is easier to converge.

[0106] FIG. 14 is an exemplary diagram for explaining the structure of the transformer model of FIG.

[0107] Referring to Figure 14, the Transformer model can be composed of an encoder layer (S142) and a decoder layer (S144). In the input layer, postional encoding adds positional information to the embedding vector of each word and can be used as the model input.

[0108] In addition, the decoder structure may be configured to receive a text matrix after positional encoding in the same manner as the encoder structure. The decoder structure may then be trained to predict words at each point in time from the text matrix. In addition, a layer that masks future words so that future words cannot be referenced may be applied to the most advanced stage of the decoder sublayer.

[0109] FIG. 15 is an exemplary diagram illustrating a text classification structure using BERT and a dense layer, which can be adopted in the Transformer model of FIG. 13.

[0110] Referring to FIG. 15, the automatic analyzer can use an automatic event analyzer (S136) using BERT and LSTM models. This analyzer (S136) can use the BERT model, which has the advantage of fine-tuning to find and classify topics in text. In this case, the BERT model can be pre-trained and used with dense layers (S138) having outputs equal to the number of labels to be trained at the time of final classification.

[0111] In addition, when using an LSTM model, it has better performance in processing long sequence inputs than a traditional RNN, and since the sequential event characteristics of the threat process make it more likely that long sentences will be formed, it is preferable to use an LSTM model rather than a traditional RNN. Also, since it is widely used in various natural language processing such as text classification and chatbot systems, it is possible to selectively use it by comparing its performance with a transformer-based model.

[0112] FIG. 16 is an example diagram of text classification using the LSTM of FIG. 15, which can be used in conjunction with or as an alternative to the Transformer model of FIG.

[0113] Referring to Figure 16, a Transformer-based BERT model and a model using LSTM and GRU can be trained as a text classification or question-answer model using the same dataset, and the validation data and test dataset results can be compared to selectively use a model with a high f1-score.

[0114] For example, for the text input "I always really hate FMD," the text is preprocessed through an embedding layer (S161) and multiple LSTMs (S162), trained through a convolution layer (S163), and then output as an automatic analysis result through a max pooling layer (S164) and a fully-connected layer (S165). The automatic analysis result can be set as a malignant event (+), a non-malignant event (-), or a decision pending (0).

[0115] The computing device for event analysis described above (corresponding to the automatic analysis device) and the AI ​​module that constitutes at least a part of this computing device can be configured in conjunction with an EDR system.

[0116] It can be embodied as an AI module-linked EDR system that can manage and provide services by placing an appliance-type management server at each site, or as a SECaaS type that manages and provides services on a cloud-based basis.

[0117] According to this embodiment, the AI ​​module can provide an integrated service in conjunction with a cloud-based EDR solution that already provides certain services. In this case, the setting interface of the AI ​​module and the analyzed result information can be configured to be provided in conjunction with a GUI, which is a management system for the EDR system.

[0118] In addition, the intelligent EDR analysis system (hereinafter simply referred to as the analysis system) can include an endpoint security solution that uses a chatbot engine to automatically analyze and detect threat events. This analysis system is implemented in the form of an agent installed on the user's PC to collect events, and the collected events can be stored in the AI ​​DB after a primary analysis using the Yara rule. The analysis results collected in the AI ​​DB can then be processed into event groups by process ID and session, and the processed events can be automatically analyzed through an AI analyzer, and the automatic event judgment results based on the automatic analysis results can be stored in the web server DB.

[0119] In addition, the analysis system can visualize and display the analysis results and judgment results using a web browser-based user interface.

[0120] The analysis system is a type of automatic threat event detection system that can automatically detect threat events through AI-based syntax analysis of event actions. It can automatically determine threat events based on the results of the automatic detection. It can also link with a blacklist to block the inflow of new variants of malicious code, and after determining threat processes through action analysis, it can update the blacklist through a web user interface. The analysis system can also be configured to detect threat events by using the Yara rules to detect events collected from the user's PC.

[0121] In addition, the analysis system collects information on processes, registries, networks, and files generated on endpoints, such as user PCs, and receives attack tactics, techniques, and methods provided by MITRE ATT&CK, and can provide detection functions with a high ratio of None, Telemetry, General Behavior, and Tactic in detection information.

[0122] In addition, the analysis system can automatically analyze event logs through AI analysis functions to determine whether or not there is maliciousness and infringement, and output judgment information. This judgment information includes attack tactics, attack techniques, and attack method information provided by MITRE ATT&CK, and can be increased and stored up to the general behavior and tactical levels.

[0123] FIG. 17 is a block diagram for explaining a form of security service provided by the automatic analysis device of FIG.

[0124] Referring to FIG. 17, the security service form can be embodied in the form of an endpoint threatening behavior detection EDR product to which a chatbot engine is applied.

[0125] Such an automatic analysis device for security services may be constructed with an external server 400 for learning data collection, security notification, and backup, and may communicate with other devices via HTTP. The external server 400 may include a short message service server 410, an update server 420, a virus total server 430, a bitdefender server 440, a mail server 450, a backup server 460, etc.

[0126] Here, the integrated management server 300 for managing the EDR solution is a type of manager, and can be constructed on server hardware or in a cloud environment, installed on a virtualized operating system, and installed to work in conjunction with a DB server.

[0127] In addition, the AI-based event analysis system using the automatic analysis device can be installed in the endpoint 100 or the integrated management server 300, and can be implemented in a virtual environment of a PC hardware or cloud environment, and can be operated in an operating system such as a Windows server. Also, an agent (Agent, 180) for collecting endpoint events and responding to threat events can be configured to operate in a specific endpoint such as Windows 7, Windows 10, etc.

[0128] In addition, the endpoint threatening behavior detection system using a chatbot engine is a type of AI-based event analysis system that uses an automatic analysis device, and performs rule matching on the event log generated on the user's PC and transmits it to the DBMS as a user's PC event log, groups the user's PC event log collected in the DBMS as a process tree and then stores it in the DBMS, generates sentences from the collected event log process tree in the order of actions, and uses the generated sentences as an AI model learning dataset to generate a Transpoker-based or LSTM-based deep learning-based AI model.

[0129] In addition, the above-mentioned system can transmit event logs generated in endpoints 100 such as actual user PCs to the AI ​​analysis system of the integrated management server 300, perform automatic analysis using the generated AI model, and output the similarity. It can also transmit the results of the automatic threat process judgment analysis and the automatic judgment results to the DBMS, and visualize and display the process tree and the AI ​​automatic analysis and judgment results through the Web UI.

[0130] In addition, the endpoint threatening behavior detection system using the chatbot engine described above may have the following module configuration: That is, the system may include a process tree behavior sequence sentence generation module, a Transformer network and LSTM-based network model learning module using a tensorflow framework, an automatic analysis and similarity output module using a Transformer network-based and LSTM network-based learning model, a library for data set processing, an automatic threat process detection module based on the automatic analysis results, and a visualization module of the analysis results and automatic judgment results through a web user interface.

[0131] The libraries may include one or more selected from the Scikit-learn, pandas, and numpy libraries.

[0132] According to this embodiment, behavioral information is collected from endpoints and stored in a central server, and the process of automatically analyzing security threat events is carried out through AI analysis of the stored behavioral information. This makes it possible to efficiently and quickly classify and analyze a large number of logs, and even without the need for professional analysts, AI can automatically determine whether or not there is an infringement when a threatening behavior occurs.

[0133] In addition, automated analysis using AI can be applied to not only endpoint event log analysis but also to a visualization platform that can test malicious code, greatly increasing the reliability of the analysis results of malicious code and malicious behavior. This has the advantage of being immediately applicable to cloud-based security service products such as SECaaS.

[0134] FIG. 18 is a block diagram for explaining a performance evaluation process for the AI-based automatic threat event analysis of the automatic analysis device of FIG.

[0135] Referring to FIG. 18, performance evaluation of the AI-based automatic threat event analysis method can be performed as follows.

[0136] First, in the event log collection step (S181), malicious information is collected from five malicious information collection channels known to execute malicious code, such as Virus Total, Virus Sign, Bitdefender, etc., and 200 malicious files per malicious information collection channel and 1,000 routine files held by the program itself can be used as samples for performance evaluation.

[0137] Here, a test bed for evaluating automatic analysis of threatening events can be constructed by utilizing the "Virtualization-Based Malicious Behavior Manual Analysis Visualization Platform," which is a type of automatic analysis device described in this embodiment.

[0138] Next, when an event log is collected due to the execution of malicious code, automatic detection of threatening events is performed through the chatbot engine (S182). The automatic detection results due to the execution of malicious code at an endpoint, etc., can be configured to be visualized on the user interface along with the results of rule analysis (S185) (S186). Through the visualized information, detection performance confirmation and reports can be provided to users, etc.

[0139] Next, the auto-detection results can be transmitted to a visualization system (S184) through an event auto-analysis process (S183).

[0140] Next, the automated event analysis results can be checked through the EDR GUI of the visualization system (S184) linked to the AI ​​module, and the test results can be measured by checking the testbed UI.

[0141] According to the above-mentioned embodiment, it is possible to effectively respond to unknown security threats and new and variant threats that neutralize existing antiviruses. In addition, by establishing an automatic response system for cyber threats through IOC-based forensic analysis, it is possible to significantly improve human error and time limitations that are dependent on manual analysis. In addition, by introducing AI-based event analysis technology, it is possible to efficiently establish an autonomous and evolving threat response system by generating and distributing rules through an automated analysis system. In addition, by sharing the latest threat information with other institutions and other systems, it is possible to generate and distribute reliable information, which can contribute to shortening the response time to malicious threats and minimizing cyber damage.

[0142] FIG. 19 is a block diagram illustrating the main configuration of an image-based malicious code detection device according to still another embodiment of the present invention.

[0143] The malicious event log automatic analysis device 1000 (simply referred to as the automatic analysis device) of this embodiment can be installed as at least a part of a server-side EDR system, or can be installed as at least a part of an endpoint agent.

[0144] 19, the automated analyzer 1000 may include at least one processor 1100, a memory 1200, and a transceiver with a communication interface 1300 that is connected to a network to perform communication. The automated analyzer 1000 may further include an input interface device 1400, an output interface device 1500, and a storage device 1600. Each component included in the automated analyzer 1000 may be connected to a bus 1700 to perform communication.

[0145] However, each component included in the automated analyzer 1000 may be connected through an individual interface or individual bus centered on the processor 1100, instead of the common bus 1700. For example, the processor 1100 may be connected to at least one of the memory 1200, the transceiver device 1300, the input interface device 1400, the output interface device 1500, and the storage device 1600 through a dedicated interface.

[0146] The processor 1100 may execute program commands stored in at least one of the memory 1200 and the storage device 1600. The processor 1100 may refer to a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which the method according to the embodiment of the present invention is performed.

[0147] Each of the memory 1200 and the storage device 1600 may be composed of at least one of a volatile storage medium and a non-volatile storage medium, for example, the memory 1200 may be composed of at least one of a read only memory (ROM) and a random access memory (RAM).

[0148] At least one instruction stored in memory 1200 or storage device 1600 or loaded into processor 1100 for execution may be configured to cause the processor to perform the following steps: process the event log by grouping it by process for efficient analysis of the event log; generate sentences for process actions through NLP (Natural Language Processing) techniques for AI analysis; digitize actual malicious actions and use them as learning data for learning an AI model; generate a learning system based on the Transformer algorithm to train an AI model with the learning data; check the grouped event logs in real time through an automatic event maliciousness analyzer based on BERT and LSTM algorithms to analyze actual malicious actions; and detect when the target of the malicious action is above a certain similarity and automatically determine that it is a threatening event.

[0149] In addition, the operations of the methods according to the embodiments of the present invention described above may be embodied as computer readable programs or codes in a computer readable recording medium. The computer readable recording medium includes all kinds of recording devices in which data that can be read by a computer system is stored. In addition, the computer readable recording medium may be distributed among computer systems connected to a network, so that the computer readable programs or codes may be stored and executed in a distributed manner.

[0150] Additionally, the computer readable recording medium may include hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. The program instructions may include not only machine code, such as produced by a compiler, but also high-level language code that may be executed by a computer using an interpreter, etc.

[0151] Although some aspects of the invention have been described in the context of an apparatus, it may also be presented as a corresponding method description, where a block or apparatus corresponds to a method step or a feature of a method step. Similarly, aspects described in the context of a method may also be presented as a corresponding block or item or feature of a corresponding apparatus. Some or all of the method steps may be performed by (or using) a hardware apparatus, such as, for example, a microprocessor, a programmable computer, or an electronic circuit. In some embodiments, one or more of the most important method steps may be performed by such an apparatus.

[0152] In some embodiments, a programmable logic device (e.g., a field programmable gate array) may be used to perform some or all of the functionality of the methods described herein. In some embodiments, a field programmable gate array may work in conjunction with a microprocessor to perform one of the methods described herein. In general, it is preferred that the methods be performed by some hardware device.

Claims

1. A method for analyzing malicious event logs by constructing an artificial intelligence module and a database for storing event logs in an integrated analysis server, installing an agent in an end point, and performing rule matching on the event logs in the agent, performing grouping of event logs using process IDs and session information; generating a sentence in the order of process actions based on the event log; and A method for automated analysis of an endpoint, comprising: analyzing an event log at the endpoint based on a data set including sentences generated in the order of actions.

2. The generating step is performed based on a Transformer model; The transformer model comprises an encoder layer and a decoder layer, [0010] 2. The method of claim 1, wherein, in a positional encoding (PE) of an input layer of the encoder layer, when a value obtained by adding 1 to a position of an embedding dimension in an embedding vector of each word is odd, the method generates position information of malicious behavior by calculating a position (pos) of the word using the equation (1), which is a cosine function.

3. The generating step is performed based on a Transformer model; The transformer model comprises an encoder layer and a decoder layer, [0025] 2. The method of claim 1, wherein positional encoding of an input layer of the encoder layer generates positional information of malicious behavior by calculating the position of the word using the equation (2), which is a sine function, when a value obtained by adding 1 to the position of an embedding dimension in an embedding vector of each word is an even number.

4. The generating step is performed based on a transformer model, the transformer model having an encoder layer and a decoder layer, The method for automated endpoint analysis according to claim 1, wherein the decoder structure including the decoder hierarchy is trained to predict words at each time point from a sentence matrix, and a layer that masks words at future times so that future words cannot be referenced is applied to the most advanced stage of the decoder sublayer.

5. The method of claim 1 , further comprising providing an analysis result of a transformer network and a process tree to provide a detection basis for a malicious event log or a threatening event log obtained in the analyzing step.

6. processing the event logs by grouping them by process for efficient analysis; generating sentences for process actions through NLP (Natural Language Processing) techniques for AI analysis; The stage of digitizing actual malicious behavior and using it as learning data for AI model training; generating a learning system based on a transformer algorithm for learning the learning data; checking the grouped event logs in real time through an event analyzer that automatically analyzes whether an event is malicious based on BERT and LSTM algorithms in order to analyze actual malicious behavior; and An automated endpoint analysis method, comprising a step of detecting a malicious behavior target having a certain degree of similarity or more and automatically determining that the event is a threatening event.

7. The transformer model for the transformer algorithm comprises an encoder layer and a decoder layer, [0010] The method of claim 6, wherein the method is configured to generate position information of malignant behavior by calculating the position of the word using the equation (1), which is a cosine function, when a value obtained by adding 1 to a position of an embedding dimension in an embedding vector of each word in a positional encoding of an input layer of the encoder layer is odd.

8. The transformer model for the transformer algorithm comprises an encoder layer and a decoder layer, [0025] The method of claim 6, wherein the method is configured to generate position information of malignant behavior by calculating the position of a word using the sine function, Equation 2, when a value obtained by adding 1 to a position of an embedding dimension in an embedding vector of each word in a positional encoding of an input layer of the encoder layer is an even number.

9. The transformer model for the transformer algorithm comprises an encoder layer and a decoder layer, The method for automated endpoint analysis according to claim 6, wherein the decoder structure including the decoder hierarchy is trained to predict words at each time point from a sentence matrix, and a layer that masks words at future times so that future words cannot be referenced is applied to the most advanced stage of the decoder sublayer.

10. An endpoint automatic analysis device for endpoint detection & response (EDR) using an AI-based chatbot engine, The method includes: executing a program on the processor; and executing a program on the memory, the program being executed by the processor according to at least one instruction stored in the memory. An automatic endpoint analyzer that processes logs by grouping them by process for efficient analysis of the event log, generates sentences for process actions through NLP (Natural Language Processing) techniques for AI analysis, digitizes actual malicious actions to use them as learning data for AI model learning, implements a learning system based on a transformer algorithm to learn the learning data, and checks grouped event logs in real time through an automatic event maliciousness analyzer based on BERT (bidirectional encoder representations form transformers) and LSTM (long short-term memory) algorithms to analyze actual malicious actions, and detects malicious actions that are above a certain similarity and automatically determines them as threatening events.

11. The transformer model for the transformer algorithm comprises an encoder layer and a decoder layer, [0010] The endpoint automatic analysis device of claim 10, configured to generate position information of malignant behavior by calculating the position (pos) of a word using the equation (1), which is a cosine function, when a value obtained by adding 1 to a position of an embedding dimension in an embedding vector of each word in a positional encoding of an input side layer of the encoder layer is odd.

12. The transformer model for the transformer algorithm comprises an encoder layer and a decoder layer, [0025] The endpoint automatic analysis device of claim 10, configured to generate position information of malignant behavior by calculating the position of a word using the equation (2), which is a sine function, when a value obtained by adding 1 to a position of an embedding dimension in an embedding vector of each word in a positional encoding of an input layer of the encoder layer is an even number.

13. The transformer model for the transformer algorithm comprises an encoder layer and a decoder layer, The endpoint automatic analysis device of claim 10, wherein the decoder structure including the decoder hierarchy is trained to predict words at each time point from a sentence matrix, and a layer that masks future words so that future words cannot be referenced is applied to the most advanced stage of the decoder sublayer.

Citation Information

Patent Citations

  • System and method of machine learning of malware detection model

    JP2019057268A

  • Method and system for detecting event of vehicle cyber-attack

    JP2019145081A

  • Script detection device, method and program

    JP2020160679A

  • Program Recording Medium for providing endoscopic image information analysis service that analyzes lesions of the digestive tract based on predictive models

    KR1020210109880A

  • Composite comprising nickel supported on porous alumina carrier and manufacturing method thereof

    KR1020220036473A