WO2022244077A1 - 推定装置、推定方法および推定プログラム - Google Patents
推定装置、推定方法および推定プログラム Download PDFInfo
- Publication number
- WO2022244077A1 WO2022244077A1 PCT/JP2021/018654 JP2021018654W WO2022244077A1 WO 2022244077 A1 WO2022244077 A1 WO 2022244077A1 JP 2021018654 W JP2021018654 W JP 2021018654W WO 2022244077 A1 WO2022244077 A1 WO 2022244077A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- abnormal
- similarity
- estimation
- normal
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 15
- 230000002159 abnormal effect Effects 0.000 claims abstract description 93
- 230000005856 abnormality Effects 0.000 claims abstract description 23
- 238000000605 extraction Methods 0.000 claims abstract description 18
- 239000000284 extract Substances 0.000 claims abstract description 7
- 238000012937 correction Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 23
- 238000012545 processing Methods 0.000 description 13
- 238000001514 detection method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000013135 deep learning Methods 0.000 description 7
- 230000010365 information processing Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000010454 slate Substances 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/55—Detecting local intrusion or implementing counter-measures
- G06F21/56—Computer malware detection or handling, e.g. anti-virus arrangements
- G06F21/566—Dynamic detection, i.e. detection performed at run-time, e.g. emulation, suspicious activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/045—Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/1066—Session management
- H04L65/1069—Session establishment or de-establishment
Definitions
- the present invention relates to an estimating device, an estimating method, and an estimating program.
- Non-Patent Document 1 a technique called so-called explainable AI, which explains the cause of anomalies using deep learning.
- variable-length communication data is used as an abnormality detection target to identify the cause of an abnormality. could not.
- the present invention has been made in view of the above, and it is an object of the present invention to make it possible to identify the cause of an anomaly by using variable-length communication data as an anomaly detection target.
- an estimation apparatus uses abnormal data determined to be abnormal and a plurality of normal data determined to be normal to determine similarity to the abnormal data. comparing the abnormal data with the estimated normal data with an estimating unit for estimating the normal data with the highest degree of error, and extracting the part of the abnormal data that does not have a part corresponding to the normal data as the cause of the abnormality and an extraction unit for
- FIG. 1 is a diagram for explaining an outline of an estimation device.
- FIG. 2 is a schematic diagram illustrating a schematic configuration of the estimation device.
- FIG. 3 is a diagram illustrating an extraction processing result.
- FIG. 4 is a flowchart showing an estimation processing procedure.
- FIG. 5 is a diagram for explaining the embodiment.
- FIG. 6 is a diagram illustrating a computer that executes an estimation program;
- FIG. 1 is a diagram for explaining an outline of an estimation device.
- the estimating device of the present embodiment identifies a byte location that is presumed to be the cause of an anomaly in communication data with variable-length communication data as an anomaly detection target.
- the normality determination data most similar to the abnormality determination data is identified.
- the estimating device applies dynamic programming to find the overall calculation result while recording the calculation results of the divided parts, and calculates the similarity between the abnormal judgment data and each normal judgment data. do.
- FIG. 1(c) a location with a gap is identified and assumed to be the abnormal byte that caused the abnormality determination.
- FIG. 2 is a schematic diagram illustrating a schematic configuration of the estimation device.
- the estimation device 10 is implemented by a general-purpose computer such as a personal computer, and includes an input unit 11 , an output unit 12 , a communication control unit 13 and a control unit 15 .
- the input unit 11 is implemented using input devices such as a keyboard and a mouse, and inputs various instruction information such as processing start to the control unit 15 in response to input operations by the operator.
- the output unit 12 is implemented by a display device such as a liquid crystal display, a printing device such as a printer, or the like.
- the communication control unit 13 is realized by a NIC (Network Interface Card) or the like, and controls communication between an external device such as a server and the control unit 15 via a network.
- the communication control unit 13 controls communication between the control unit 15 and a management device or the like that manages data sets and parameters to be subjected to estimation processing, which will be described later.
- the control unit 15 is implemented using a CPU (Central Processing Unit) or the like, and executes a processing program stored in memory. Thereby, the control unit 15 functions as an acquisition unit 15a, an estimation unit 15b, and an extraction unit 15c, as illustrated in FIG. It should be noted that these functional units may be implemented in different hardware, respectively or partially. For example, the estimation unit 15b and the extraction unit 15c may be implemented in different hardware. Also, the control unit 15 may include other functional units.
- CPU Central Processing Unit
- the acquisition unit 15a acquires data determined to be abnormal and a plurality of data determined to be normal. For example, the acquisition unit 15a receives abnormal data to be subjected to estimation processing (to be described later) and normal data to be used for estimation processing, via the input unit 11 or from a management device or the like that manages the results of deep learning via the communication control unit 13. data set, parameters used for estimation processing, etc.
- the acquisition unit 15a stores the acquired data in a storage unit (not shown) implemented by a semiconductor memory device such as RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or optical disk. may be stored. Alternatively, the acquiring unit 15a may transfer these pieces of information to the estimating unit 15b described below without storing them in the storage unit.
- a storage unit implemented by a semiconductor memory device such as RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or optical disk.
- the estimating unit 15b estimates normal data that maximizes the degree of similarity between the abnormal data determined to be abnormal and each of the plurality of normal data determined to be normal. Specifically, using the acquired data, the estimation unit 15b evaluates the similarity between the payload of the packet determined to be abnormal and the set of payloads of the packet determined to be normal, and determines that the packet is abnormal. Estimate the payload that is most similar to the payload of the retrieved packet.
- the estimation unit 15b applies dynamic programming to calculate the degree of similarity between abnormal data and normal data.
- the estimating device 10 processes the packet payload of one abnormal data and, for example, 100 or more normal data among the data determined to be abnormal/normal by the abnormality detection by deep learning.
- the payload is, for example, a hexadecimal character string expressed as [00 00 10 FF 10], and is a variable-length data string with a length of 1 or more.
- the estimation unit 15b calculates the degree of similarity between the abnormal data and the normal data assuming that the characters appearing in the abnormal data and the normal data continuously loop. That is, the estimating unit 15b assumes that byte characters (00 to FF) appearing in data are looped. The similarity is assumed to be the same value.
- the estimating unit 15b calculates the Y target with the highest similarity to X using dynamic programming.
- Dynamic programming can be expressed as in the following equations (1) and (2).
- the above formula (1) uses the similarity s(x i , y j ) between one character x i in the abnormal data string X and one character y j in the normal data string Y to determine the similarity between X and Y It quantifies the degree S(i, j).
- the estimation unit 15b sets the character similarity s with the byte character "00" of the normal data to be compared to +10, "01” and "02".
- the degree of similarity s of characters with "03”, “FF”, “FE”, and “FD” may be preset to +5, and the degree of similarity s to other byte characters may be preset to -5.
- the estimation unit 15b calculates the degree of similarity between the abnormal data and the normal data using the character similarity s of the abnormal data and the normal data as a value within a predetermined range.
- the estimation unit 15b evaluates the similarity between the abnormal data string X and the k-th normal data string Yk , and then evaluates the similarity between the abnormal data string X and the k+1-th normal data string Yk+1 . is repeated until the l -th normal data string Yl.
- the estimation unit 15b can use dynamic programming to compare variable-length data.
- the estimation unit 15b calculates the degree of similarity between the abnormal data string X and each normal data string Y by performing correction using the anomaly score. That is, the estimating unit 15b multiplies the above S(i, j) by the AI anomaly score (anomaly score) of the result of anomaly detection by deep learning of each normal data string Y as a bias, and obtains the abnormal data string X and each normal data string Y. For example, the estimating unit 15b biases the normal data with the lower anomaly score so that the similarity score of the normal data with the abnormal data becomes higher. Then, the estimating unit 15b specifies the normal data string Y having the highest calculated similarity as the Y target .
- the extraction unit 15c compares the abnormal data with the normal data estimated to have the highest degree of similarity, and extracts the part of the abnormal data that does not have a part corresponding to the normal data as the cause of the abnormality. Specifically, the extraction unit 15c extracts, as an abnormal portion, a portion having a gap with the estimated payload from the payload of the packet determined to be abnormal.
- the extraction unit 15c extracts the second byte of the comparison source " 11” is not found in the normal data, it is determined as an abnormal portion and extracted. In this case, the extraction unit 15c replaces the second byte of the normal data with a blank character.
- the second byte of the normal data is not "11"
- the second byte of the abnormal data and the normal data may be extracted as a gap.
- the extraction unit 15c outputs the extracted abnormal point via the output unit 12.
- the extracting unit 15c outputs a pair of payloads of abnormal data and normal data to the output unit 12 such as a display, and highlights and displays a location with a gap determined as an abnormal location.
- the extraction unit 15 c may output the information on the extracted abnormal location to another information processing device via the communication control unit 13 .
- FIG. 3 is a diagram illustrating an extraction processing result.
- FIG. 3 exemplifies normal data having the highest degree of similarity with abnormal data, and portions of the abnormal data having gaps with the normal data.
- FIG. 3 as shown in bold, "0X86 0X8C 0X5F" is displayed as an abnormal location with a gap.
- FIG. 4 is a flowchart showing an estimation processing procedure.
- the flowchart of FIG. 4 is started, for example, when an operation input instructing the start of estimation processing is performed.
- the acquisition unit 15a acquires abnormal data determined to be abnormal and a plurality of normal data determined to be normal (step S1).
- the estimation unit 15b creates a pair of abnormal data and normal data (step S2). Further, the estimation unit 15b estimates the pair having the maximum similarity between the abnormal data and the normal data among the created pairs (step S3).
- the estimation unit 15b uses dynamic programming to calculate the similarity of each pair. At that time, the estimating unit 15b calculates the degree of similarity of each pair assuming that the characters appearing in the abnormal data and the normal data continuously loop. Also, the estimation unit 15b calculates the similarity of each pair by setting the similarity of the characters of the abnormal data and the normal data to values within a predetermined range. The estimation unit 15b also calculates the similarity of each pair by performing correction using the anomaly score.
- the extraction unit 15c also compares the abnormal data with the normal data estimated to have the highest degree of similarity, and extracts the part of the abnormal data that has no part corresponding to the normal data and has gaps as the cause of the abnormality. (Step S4).
- the extraction unit 15c outputs to the output unit 12, for example, emphasizing and displaying the location with the gap determined as the abnormal location (step S5). This completes a series of estimation processes.
- the estimating unit 15b estimates normal data that maximizes the degree of similarity between the abnormal data determined to be abnormal and each of the plurality of normal data determined to be normal.
- the extraction unit 15c compares the abnormal data with the normal data estimated to have the highest degree of similarity, and extracts the part of the abnormal data that does not have a part corresponding to the normal data as the cause of the abnormality.
- the estimation device 10 can identify the part of the abnormal data that is most similar to the normal data that differs from the normal data as the cause of the abnormality, regardless of the lengths of the normal data and the abnormal data.
- the estimating apparatus 10 can identify the cause of the abnormality by using the communication data of variable length as the object of abnormality detection.
- the estimation unit 15b also applies dynamic programming to calculate the degree of similarity between the abnormal data and the normal data. In this way, the estimating apparatus 10 can identify the cause of an anomaly with high accuracy by calculating the degree of similarity between abnormal data and normal data using variable-length communication data as an anomaly detection target. Become.
- the estimation unit 15b calculates the degree of similarity between the abnormal data and the normal data assuming that the characters appearing in the abnormal data and the normal data continuously loop. In this way, the estimation device 10 can identify the cause of the abnormality by specifically and efficiently calculating the similarity.
- the estimation unit 15b calculates the degree of similarity between the abnormal data and the normal data, with the degree of similarity between the characters of the abnormal data and that of the normal data as values within a predetermined range. In this way, the estimating device 10 can identify the cause of the abnormality with high accuracy by specifically and efficiently calculating the degree of similarity.
- the estimation unit 15b also calculates the degree of similarity between the abnormal data and the normal data by performing correction using the anomaly score. In this way, the estimation device 10 can identify the cause of the abnormality by specifically calculating the similarity with high accuracy.
- FIG. 5 is a diagram for explaining the embodiment.
- the accuracy of estimating the byte location of abnormal communication data that occurs in a cyberattack scenario assumed below was measured.
- each byte was converted from a hexadecimal number (0x00 to 0xff) to a numerical value (0 to 255) in order to obtain a data format that can be used in dynamic programming.
- FIG. 5 illustrates the evaluation results of the example. In the evaluation, it was confirmed whether or not the estimated byte strings of the abnormal locations completely matched for each packet, and it was determined as correct when they matched perfectly, and as an error when they did not match perfectly.
- the abnormal location could be estimated in all packets. If the abnormal byte sequence is inserted in two places, it cannot be estimated correctly with two packets, and if the abnormal byte sequence is inserted in three places, it can be estimated correctly with six packets. Although it was not, it was confirmed that it can be estimated with an accuracy of 90% or more as a whole.
- the estimating device 10 can be implemented by installing an estimating program that executes the above estimating process as package software or online software on a desired computer.
- the information processing device can function as the estimation device 10 by causing the information processing device to execute the above estimation program.
- information processing devices include mobile communication terminals such as smartphones, mobile phones and PHS (Personal Handyphone Systems), and slate terminals such as PDAs (Personal Digital Assistants).
- the functions of the estimation device 10 may be implemented in a cloud server.
- FIG. 6 is a diagram showing an example of a computer that executes an estimation program.
- Computer 1000 includes, for example, memory 1010 , CPU 1020 , hard disk drive interface 1030 , disk drive interface 1040 , serial port interface 1050 , video adapter 1060 and network interface 1070 . These units are connected by a bus 1080 .
- the memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012 .
- the ROM 1011 stores a boot program such as BIOS (Basic Input Output System).
- BIOS Basic Input Output System
- Hard disk drive interface 1030 is connected to hard disk drive 1031 .
- Disk drive interface 1040 is connected to disk drive 1041 .
- a removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1041, for example.
- a mouse 1051 and a keyboard 1052 are connected to the serial port interface 1050, for example.
- a display 1061 is connected to the video adapter 1060 .
- the hard disk drive 1031 stores an OS 1091, application programs 1092, program modules 1093 and program data 1094, for example. Each piece of information described in the above embodiment is stored in the hard disk drive 1031 or the memory 1010, for example.
- the estimation program is stored in the hard disk drive 1031 as a program module 1093 in which instructions to be executed by the computer 1000 are written, for example.
- the hard disk drive 1031 stores a program module 1093 that describes each process executed by the estimation device 10 described in the above embodiment.
- data used for information processing by the estimation program is stored as program data 1094 in the hard disk drive 1031, for example. Then, the CPU 1020 reads out the program module 1093 and the program data 1094 stored in the hard disk drive 1031 to the RAM 1012 as necessary, and executes each procedure described above.
- program module 1093 and program data 1094 related to the estimation program are not limited to being stored in the hard disk drive 1031.
- they are stored in a removable storage medium and read by the CPU 1020 via the disk drive 1041 or the like.
- the program module 1093 and program data 1094 related to the estimation program are stored in another computer connected via a network such as LAN (Local Area Network) or WAN (Wide Area Network), and via network interface 1070 It may be read by CPU 1020 .
- LAN Local Area Network
- WAN Wide Area Network
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Virology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Devices For Executing Special Programs (AREA)
- Debugging And Monitoring (AREA)
Abstract
Description
図1は、推定装置の概要を説明するための図である。図1に示すように、本実施形態の推定装置は、可変長の通信データを異常検知の対象として、通信データの異常の原因と推定されるバイト箇所を特定する。具体的には、図1(a)に示すように、異常と判定された通信データ(異常判定データ)と複数の正常と判定された通信データ(正常判定データ)とのペアについて、図1(b)に示すように、異常判定データと最も似ている正常判定データを特定する。その際に、推定装置は、複数に分割された部分の計算結果を記録しながら全体の計算結果を求める動的計画法を適用して、異常判定データと各正常判定データとの類似度を算出する。そのうち、図1(c)に示すように、ギャップがある箇所を特定し、これを異常判定の原因となった異常バイトと推定する。
図2は、推定装置の概略構成を例示する模式図である。図2に例示するように、推定装置10は、パソコン等の汎用コンピュータで実現され、入力部11、出力部12、通信制御部13、および制御部15を備える。
次に、図4を参照して、本実施形態に係る推定装置10による推定処理について説明する。図4は、推定処理手順を示すフローチャートである。図4のフローチャートは、例えば、推定処理の開始を指示する操作入力があったタイミングで開始される。
図5は、実施例を説明するための図である。本実施例では、以下に示すように想定されたサイバー攻撃シナリオで発生する異常な通信データのバイト箇所の推定精度を計測した。
上記実施形態に係る推定装置10が実行する処理をコンピュータが実行可能な言語で記述したプログラムを作成することもできる。一実施形態として、推定装置10は、パッケージソフトウェアやオンラインソフトウェアとして上記の推定処理を実行する推定プログラムを所望のコンピュータにインストールさせることによって実装できる。例えば、上記の推定プログラムを情報処理装置に実行させることにより、情報処理装置を推定装置10として機能させることができる。また、その他にも、情報処理装置にはスマートフォン、携帯電話機やPHS(Personal Handyphone System)等の移動体通信端末、さらには、PDA(Personal Digital Assistant)等のスレート端末等がその範疇に含まれる。また、推定装置10の機能を、クラウドサーバに実装してもよい。
11 入力部
12 出力部
13 通信制御部
15 制御部
15a 取得部
15b 推定部
15c 抽出部
Claims (7)
- 異常と判定された異常データと正常と判定された複数の正常データのそれぞれとの類似度が最大となる正常データを推定する推定部と、
前記異常データと類似度が最大と推定された正常データとを比較して、該正常データに対応する部分がない該異常データの部分を、異常の原因箇所として抽出する抽出部と、
を有することを特徴とする推定装置。 - 前記推定部は、動的計画法を適用して前記類似度を算出することを特徴とする請求項1に記載の推定装置。
- 前記推定部は、異常データおよび正常データに出現する文字が連続してループするものとして類似度を算出することを特徴とする請求項2に記載の推定装置。
- 前記推定部は、異常データのおよび正常データの文字の類似度を所定の範囲の値として、前記類似度を算出することを特徴とする請求項2に記載の推定装置。
- 前記推定部は、アノマリスコアを用いた補正を行うことにより、前記類似度を算出することを特徴とする請求項2に記載の推定装置。
- 推定装置が実行する推定方法であって、
異常と判定された異常データと正常と判定された複数の正常データのそれぞれとの類似度が最大となる正常データを推定する推定工程と、
前記異常データと類似度が最大と推定された正常データとを比較して、該正常データに対応する部分がない該異常データの部分を、異常の原因箇所として抽出する抽出工程と、
を含んだことを特徴とする推定方法。 - コンピュータに、
異常と判定された異常データと正常と判定された複数の正常データのそれぞれとの類似度が最大となる正常データを推定する推定ステップと、
前記異常データと類似度が最大と推定された正常データとを比較して、該正常データに対応する部分がない該異常データの部分を、異常の原因箇所として抽出する抽出ステップと、
を実行させることを特徴とする推定プログラム。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP21940697.2A EP4325385A1 (en) | 2021-05-17 | 2021-05-17 | Estimation device, estimation method, and estimation program |
US18/290,452 US20240256667A1 (en) | 2021-05-17 | 2021-05-17 | Estimation device, estimation method, and estimation program |
PCT/JP2021/018654 WO2022244077A1 (ja) | 2021-05-17 | 2021-05-17 | 推定装置、推定方法および推定プログラム |
AU2021445975A AU2021445975A1 (en) | 2021-05-17 | 2021-05-17 | Estimation device, estimation method, and estimation program |
JP2023522024A JPWO2022244077A1 (ja) | 2021-05-17 | 2021-05-17 | |
CN202180097987.1A CN117296068A (zh) | 2021-05-17 | 2021-05-17 | 估计装置、估计方法以及估计程序 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/018654 WO2022244077A1 (ja) | 2021-05-17 | 2021-05-17 | 推定装置、推定方法および推定プログラム |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022244077A1 true WO2022244077A1 (ja) | 2022-11-24 |
Family
ID=84141360
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/018654 WO2022244077A1 (ja) | 2021-05-17 | 2021-05-17 | 推定装置、推定方法および推定プログラム |
Country Status (6)
Country | Link |
---|---|
US (1) | US20240256667A1 (ja) |
EP (1) | EP4325385A1 (ja) |
JP (1) | JPWO2022244077A1 (ja) |
CN (1) | CN117296068A (ja) |
AU (1) | AU2021445975A1 (ja) |
WO (1) | WO2022244077A1 (ja) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007515867A (ja) * | 2003-11-12 | 2007-06-14 | ザ トラスティーズ オブ コロンビア ユニヴァーシティ イン ザ シティ オブ ニューヨーク | 正常データのnグラム分布を用いてペイロード異常を検出するための装置、方法、及び媒体 |
-
2021
- 2021-05-17 EP EP21940697.2A patent/EP4325385A1/en active Pending
- 2021-05-17 US US18/290,452 patent/US20240256667A1/en active Pending
- 2021-05-17 CN CN202180097987.1A patent/CN117296068A/zh active Pending
- 2021-05-17 JP JP2023522024A patent/JPWO2022244077A1/ja active Pending
- 2021-05-17 WO PCT/JP2021/018654 patent/WO2022244077A1/ja active Application Filing
- 2021-05-17 AU AU2021445975A patent/AU2021445975A1/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007515867A (ja) * | 2003-11-12 | 2007-06-14 | ザ トラスティーズ オブ コロンビア ユニヴァーシティ イン ザ シティ オブ ニューヨーク | 正常データのnグラム分布を用いてペイロード異常を検出するための装置、方法、及び媒体 |
Non-Patent Citations (3)
Title |
---|
FUKAI, KEN : "Estimating the causative function of performance failure by analyzing the execution path", IPSJ SIG TECHNICAL REPORT, vol. 2015-OS-135, no. 12, 17 November 2015 (2015-11-17), JP , pages 1 - 7, XP009541616, ISSN: 2188-8795 * |
WILLIAM BRIGUGLIOSHERIF SAAD, INTERPRETING MACHINE LEARNING MALWARE DETECTORS WHICH LEVERAGE N-GRAM ANALYSIS, 14 April 2021 (2021-04-14), Retrieved from the Internet <URL:https://arxiv.org/abs/2001.10916.pdf>> |
XIAO ZHANGMANISH MARWAHI-TA LEEMARTIN ARLITTDAN GOLDWASSER, ACE-AN ANOMALY CONTRIBUTION EXPLAINER FOR CYBER-SECURITY APPLICATIONS, 14 April 2021 (2021-04-14), Retrieved from the Internet <URL:https://arxiv.org/pdf/1912.00314.pdf>> |
Also Published As
Publication number | Publication date |
---|---|
JPWO2022244077A1 (ja) | 2022-11-24 |
EP4325385A1 (en) | 2024-02-21 |
AU2021445975A1 (en) | 2023-11-16 |
US20240256667A1 (en) | 2024-08-01 |
CN117296068A (zh) | 2023-12-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8401982B1 (en) | Using sequencing and timing information of behavior events in machine learning to detect malware | |
JP6697123B2 (ja) | プロファイル生成装置、攻撃検知装置、プロファイル生成方法、および、プロファイル生成プログラム | |
US20230362182A1 (en) | Abnormality sensing device and abnormality sensing method | |
US11212297B2 (en) | Access classification device, access classification method, and recording medium | |
WO2018066516A1 (ja) | 攻撃コード検知装置、攻撃コード検知方法及び攻撃コード検知プログラム | |
EP3293657B1 (en) | Analysis method, analysis device, and analysis program | |
EP3404572B1 (en) | Attack code detection device, attack code detection method, and attack code detection program | |
CN109992969B (zh) | 一种恶意文件检测方法、装置及检测平台 | |
CN110750789B (zh) | 解混淆方法、装置、计算机设备和存储介质 | |
US10970391B2 (en) | Classification method, classification device, and classification program | |
EP3312755B1 (en) | Method and apparatus for detecting application | |
JP6915305B2 (ja) | 検知装置、検知方法および検知プログラム | |
Pranav et al. | Detection of botnets in IoT networks using graph theory and machine learning | |
WO2022244077A1 (ja) | 推定装置、推定方法および推定プログラム | |
EP3504597B1 (en) | Identification of deviant engineering modifications to programmable logic controllers | |
KR101625890B1 (ko) | 인터넷 응용 트래픽 프로토콜의 시그니처 변경 탐지를 위한 테스트 자동화 방법 및 시스템 | |
CN116458119B (zh) | 估计装置、估计方法以及记录介质 | |
CN115134153A (zh) | 安全评估方法、装置和模型训练方法、装置 | |
JP6740184B2 (ja) | 付与装置、付与方法および付与プログラム | |
WO2022259330A1 (ja) | 推定装置、推定方法および推定プログラム | |
WO2022249472A1 (ja) | 検知装置、検知方法および検知プログラム | |
US11934427B2 (en) | Data classification apparatus, data classification method and program | |
Eresheim et al. | Anomaly Detection Support Using Process Classification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21940697 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023522024 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2021445975 Country of ref document: AU Ref document number: AU2021445975 Country of ref document: AU |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202180097987.1 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2021940697 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18290452 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2021445975 Country of ref document: AU Date of ref document: 20210517 Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2021940697 Country of ref document: EP Effective date: 20231113 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |