CN109688112A - Industrial Internet of Things unusual checking device - Google Patents
Industrial Internet of Things unusual checking device Download PDFInfo
- Publication number
- CN109688112A CN109688112A CN201811490982.1A CN201811490982A CN109688112A CN 109688112 A CN109688112 A CN 109688112A CN 201811490982 A CN201811490982 A CN 201811490982A CN 109688112 A CN109688112 A CN 109688112A
- Authority
- CN
- China
- Prior art keywords
- things
- industrial internet
- unusual checking
- internet
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1425—Traffic logging, e.g. anomaly detection
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1416—Event detection, e.g. attack signature detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1441—Countermeasures against malicious traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
A kind of industry Internet of Things unusual checking device, described device includes: model acquiring unit, is suitable for obtaining corresponding industrial Internet of Things unusual checking model；The industry Internet of Things unusual checking model is to be trained to obtain to acquired original network traffic data using deepness auto encoder and depth feedforward neural network；Behavioral value unit is suitable for the industrial Internet of Things network flow data input industrial Internet of Things unusual checking model to be detected obtaining corresponding industrial Internet of Things unusual checking result.The accuracy of industrial Internet of Things unusual checking can be improved in above-mentioned scheme.
Description
Technical field
The invention belongs to industrial internet of things field, fill more particularly to a kind of industrial Internet of Things unusual checking
It sets.
Background technique
The industrial intelligent that industrial cloud, industrial big data and intelligent equipment are constituted has become the aobvious of infant industry form
Work feature.The data analysis in cloud and application, local field control, the data processing and response of edge side, three ends combine
The stage construction trend that interconnects that cooperative development is formed also brings the mass upgrade of industry.
Industrial Internet of Things needs hundreds of millions of terminal industrial equipments to be connected into internet, so that the work of script relative closure
Industry control network becomes more and more open.It is open while bring convenient and efficiency, it loophole quantity and is formed effectively using loophole
The quantity of attack is also constantly riseing, and industrial network security is made to be faced with great challenge.
In the prior art, in order to detect industrial Internet of Things network attack, it is necessary to which on-premise network intruding detection system is for supervising
Depending on and detection whole network system in suspicious event, method is divided into detection based on signature and based on abnormal detection two
Kind, but it is low there is detection accuracy the problems such as.
Summary of the invention
Present invention solves the technical problem that being how to improve the accuracy of industrial Internet of Things unusual checking.
In order to achieve the above object, the present invention provides a kind of industrial Internet of Things unusual checking device, described device packet
It includes:
Model acquiring unit is suitable for obtaining corresponding industrial Internet of Things unusual checking model；The industry Internet of Things
Unusual checking model is using deepness auto encoder and depth feedforward neural network to acquired primitive network flow
Data are trained to obtain；
Behavioral value unit is suitable for the industrial Internet of Things network flow data input industrial Internet of Things to be detected is different
Normal behavioral value model obtains corresponding industrial Internet of Things unusual checking result.
It optionally, further include model training unit, suitable for obtaining the original network traffic data in industrial Internet of Things；By institute
The original network traffic data of acquisition is pre-processed, and pretreated original network traffic data is obtained；The pretreatment packet
Include network flow characteristic conversion and feature normalization operation；Using the deepness auto encoder algorithm to pretreated original
Network flow data carries out unmarked training, obtains the estimation parameter of the industrial Internet of Things unusual checking model；Using
Depth feedforward neural network and pretreated original network traffic data have carried out label training, different to the industrial Internet of Things
The estimation parameter of normal behavioral value model optimizes, and obtains the industrial Internet of Things unusual checking model.
Optionally, the model training unit, suitable for being carried out using following formula to extracted network flow characteristic
Normalization:
Wherein, Z(i)The i-th network flow characteristic after indicating normalization, v(i)Indicate extracted i-th
A network flow characteristic, μ indicate feature v(i)Mean value, σ indicate feature v(i)Standard deviation.
Optionally, the estimation ginseng for the industrial Internet of Things unusual checking model that the model training list training obtains
Number, including weight and deviation.
Optionally, described device further include:
Alarm Unit, suitable for exporting corresponding alarm prompt when detecting industrial Internet of Things abnormal behaviour.
Optionally, described device further include:
It signs storage unit, suitable for when detecting industrial Internet of Things abnormal behaviour, from detected industrial Internet of Things
Corresponding signed data is extracted in abnormal behaviour and is stored in preset log database.
Optionally, the original network traffic data include source IP address, purpose IP address, source port, target port and
The information of protocol type.
Compared with prior art, the invention has the benefit that
Above-mentioned scheme, by obtaining corresponding industrial Internet of Things unusual checking model, and by industry to be detected
The Internet of Things network flow data input industrial Internet of Things unusual checking model, it is abnormal to obtain corresponding industrial Internet of Things
Behavioral value is as a result, since the industrial Internet of Things unusual checking model is to be feedovered using deepness auto encoder and depth
Neural network is trained to obtain to acquired original network traffic data, therefore industrial Internet of Things abnormal behaviour inspection can be improved
The accuracy of survey.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is the flow diagram of the industrial Internet of Things anomaly detection method of one of embodiment of the present invention；
Fig. 2 is the structural schematic diagram of the industrial Internet of Things unusual checking device of one of embodiment of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.Related directionality instruction in the embodiment of the present invention (such as upper and lower, left and right,
It is forward and backward etc.) it is only used for the relative positional relationship explained under a certain particular pose (as shown in the picture) between each component, movement feelings
Condition etc., if the particular pose changes, directionality instruction is also correspondingly changed correspondingly.
As stated in the background art, there is Detection accuracies for industrial Internet of Things anomaly detection method in the prior art
Low problem.
Technical solution of the present invention, which passes through, obtains corresponding industrial Internet of Things unusual checking model, and will be to be detected
The industrial Internet of Things network flow data input industrial Internet of Things unusual checking model, obtains corresponding industrial Internet of Things
Unusual checking is as a result, since the industrial Internet of Things unusual checking model is using deepness auto encoder and depth
Feedforward neural network is trained to obtain to acquired original network traffic data, therefore industrial Internet of Things exception row can be improved
For the accuracy of detection.
It is understandable to enable above-mentioned purpose of the invention, feature and beneficial effect to become apparent, with reference to the accompanying drawing to this
The specific embodiment of invention is described in detail.
Fig. 1 is a kind of flow diagram of industrial Internet of Things anomaly detection method of the embodiment of the present invention.Referring to figure
1, a kind of industry Internet of Things anomaly detection method can specifically include following step:
Step S101: corresponding industrial Internet of Things unusual checking model is obtained；The industry Internet of Things abnormal behaviour
Detection model is to be carried out using deepness auto encoder and depth feedforward neural network to acquired original network traffic data
Training obtains.
In specific implementation, when being trained to the industrial Internet of Things unusual checking model, available work
Original network traffic data in industry Internet of Things；Wherein, the original network traffic data includes source IP address, destination IP
Location, source port, target port and protocol type information.
Then, acquired original network traffic data is pre-processed, obtains pretreated primitive network flow
Data.In an embodiment of the present invention, carrying out pretreatment to acquired original network traffic data includes network flow characteristic
Conversion and feature normalization operation.
Wherein, when carrying out network flow characteristic conversion to acquired original network traffic data, it is assumed that subsequent training
Obtained industrial Internet of Things unusual checking model receives the data characteristics of numeric type, therefore needing to pass through will be from primitive network stream
The each symbolic feature values extracted in amount data are converted to numerical characteristics value.For example, NSL-KDD data set has many symbols
They can be each mapped to 1,2 and 3 etc. including the protocol type with nominal value, such as ICMP, TCP and UDP by attribute.
Because deep learning depends on weight, different characteristic dimensions can be by data skew to specific level, may
Cause certain weights to update faster than other, therefore needs that network flow characteristic is normalized.Implement in the present invention one
In example, network flow characteristic is normalized using 0 mean normalization (Z-score normalization), that is, is adopted
Network flow characteristic is normalized with following formula:
Wherein, Z(i)The i-th network flow characteristic after indicating normalization, v(i)Indicate that extracted i-th of network flow is special
Sign, μ indicate feature v(i)Mean value, σ indicate feature v(i)Standard deviation.
Network flow characteristic after normalized will obey standardized normal distribution.
It, can be special using the network flow after normalized after obtaining the network flow characteristic after normalized
It levies data and constructs corresponding training set and test set, and successively use depth automatic using the corresponding training set of building and test set
Encoder algo and depth feedforward neural network carry out lasting training and obtain corresponding industrial Internet of Things unusual checking mould
Type.Specifically, pretreated original network traffic data is carried out without mark using the deepness auto encoder algorithm first
Note training obtains the estimation parameter of the industrial Internet of Things unusual checking model, including weight and deviation.Then, it will instruct
The estimation parameter of the industrial Internet of Things unusual checking model got is as input, then uses depth Feedforward Neural Networks
Network and pretreated original network traffic data have carried out label training, to the industrial Internet of Things unusual checking model
Estimation parameter optimize, finally obtain the industrial Internet of Things unusual checking model.
Step S102: by the industrial Internet of Things network flow data input industrial Internet of Things abnormal behaviour inspection to be detected
Model is surveyed, corresponding industrial Internet of Things unusual checking result is obtained.
In specific implementation, it when getting the industrial Internet of Things unusual checking model that training obtains, can adopt
The abnormal behaviour in industrial Internet of Things is detected with the industrial Internet of Things unusual checking model, namely to industrial object
Attack present in networking is detected.
In specific implementation, the industrial Internet of Things anomaly detection method can also include:
Step S103: when detecting industrial Internet of Things abnormal behaviour, corresponding alarm prompt is exported.
In specific implementation, when confirmly detecting the abnormal behaviour in industrial Internet of Things, namely detection attack
When, it can be generated and export corresponding warning information, so that related personnel can take appropriate measures, ensure industrial Internet of Things
Net the normal operation at network.
In specific implementation, the industrial Internet of Things anomaly detection method can also include:
Step S104: corresponding signed data is extracted from detected industrial Internet of Things abnormal behaviour and is stored in pre-
If behavior database in.
In specific implementation, when confirmly detecting the abnormal behaviour in industrial Internet of Things, namely detection attack
When, by extracting corresponding signed data from detected industrial Internet of Things abnormal behaviour and being stored in preset behavior number
According in library, the industrial Internet of Things abnormal behaviour inspection can be carried out using the data stored in the behavior database so as to subsequent
The optimization of model is surveyed, to further increase the accuracy of industrial Internet of Things unusual checking.
The above-mentioned industrial Internet of Things anomaly detection method in the embodiment of the present invention is described in detail, and below will
The above-mentioned corresponding device of method is introduced.
Fig. 2 shows the structural schematic diagrams of the industrial Internet of Things unusual checking device of one of embodiment of the present invention.
Referring to fig. 2, the industrial Internet of Things unusual checking device 20 of one of embodiment of the present invention may include model acquiring unit
201 and behavioral value unit 202, in which:
The model acquiring unit 201 is suitable for obtaining corresponding industrial Internet of Things unusual checking model；The industry
Internet of Things unusual checking model is using deepness auto encoder and depth feedforward neural network to acquired original net
Network data on flows is trained to obtain.
The behavioral value unit 202 is suitable for industrial Internet of Things network flow data to be detected inputting the industry
Internet of Things unusual checking model obtains corresponding industrial Internet of Things unusual checking result.
In specific implementation, the industrial Internet of Things unusual checking device 20 of one of embodiment of the present invention can also wrap
Model training unit 203 is included, in which:
The model training unit 203, suitable for obtaining the original network traffic data in industrial Internet of Things；It will be acquired
Original network traffic data is pre-processed, and obtains pretreated original network traffic data wherein, the primitive network stream
Amount data may include the information of source IP address, purpose IP address, source port, target port and protocol type；The pretreatment
Including network flow characteristic conversion and feature normalization operation；Using the deepness auto encoder algorithm to pretreated original
Beginning network flow data carries out unmarked training, obtains the estimation parameter of the industrial Internet of Things unusual checking model,
In, the estimation parameter for the industrial Internet of Things unusual checking model that the model training list training obtains, including weight
And deviation；Label training is carried out using depth feedforward neural network and pretreated original network traffic data, to described
The estimation parameter of industrial Internet of Things unusual checking model optimizes, and obtains the industrial Internet of Things unusual checking mould
Type.
In an embodiment of the present invention, the model training unit 203, suitable for using following formula to extracted net
Network traffic characteristic is normalized:
Wherein, Z(i)The i-th network flow characteristic after indicating normalization, v(i)Indicate extracted i-th
A network flow characteristic, μ indicate feature v(i)Mean value, σ indicate feature v(i)Standard deviation.
In specific implementation, described device 20 can also include Alarm Unit 205, in which:
The Alarm Unit 205, suitable for when detecting industrial Internet of Things abnormal behaviour, exporting corresponding alarm prompt letter
Breath.
In specific implementation, described device 20 can also include signature storage unit 206, in which:
The signature storage unit 206, suitable for when detecting industrial Internet of Things abnormal behaviour, from detected industry
Corresponding signed data is extracted in Internet of Things abnormal behaviour and is stored in preset log database.
The embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer instruction, described
The step of industrial Internet of Things anomaly detection method is executed when computer instruction is run.Wherein, the industrial object
Networking anomaly detection method refers to being discussed in detail for preceding sections, repeats no more.
The embodiment of the invention also provides a kind of terminal, including memory and processor, energy is stored on the memory
Enough computer instructions run on the processor, the processor execute the industry when running the computer instruction
The step of Internet of Things anomaly detection method.Wherein, the industrial Internet of Things anomaly detection method refers to aforementioned
Partial is discussed in detail, and repeats no more.
Using the above scheme in the embodiment of the present invention, by obtaining corresponding industrial Internet of Things unusual checking mould
Type, and by the industrial Internet of Things network flow data input industrial Internet of Things unusual checking model to be detected, it obtains
Corresponding industry Internet of Things unusual checking is as a result, since the industrial Internet of Things unusual checking model is using depth
Autocoder and depth feedforward neural network are trained to obtain to acquired original network traffic data, therefore can be improved
The accuracy of industrial Internet of Things unusual checking.
The basic principles, main features and advantages of the present invention have been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, the present invention
Claimed range is delineated by the appended claims, the specification and equivalents thereof from the appended claims.
Claims (7)
1. a kind of industry Internet of Things unusual checking device characterized by comprising
Model acquiring unit is suitable for obtaining corresponding industrial Internet of Things unusual checking model；The industry Internet of Things is abnormal
Behavioral value model is using deepness auto encoder and depth feedforward neural network to acquired original network traffic data
It is trained to obtain；
Behavioral value unit is suitable for the industrial Internet of Things network flow data input industrial Internet of Things exception row to be detected
For detection model, corresponding industrial Internet of Things unusual checking result is obtained.
2. industry Internet of Things unusual checking device according to claim 1, which is characterized in that further include model training
Unit, suitable for obtaining the original network traffic data in industrial Internet of Things；Acquired original network traffic data is carried out pre-
Processing, obtains pretreated original network traffic data；The pretreatment includes network flow characteristic conversion and feature normalizing
Change operation；Unmarked training is carried out to pretreated original network traffic data using the deepness auto encoder algorithm,
Obtain the estimation parameter of the industrial Internet of Things unusual checking model；Using depth feedforward neural network and pretreated
Original network traffic data has carried out label training, carries out to the estimation parameter of the industrial Internet of Things unusual checking model
Optimization obtains the industrial Internet of Things unusual checking model.
3. industry Internet of Things unusual checking device according to claim 2, which is characterized in that the model training list
Member, suitable for extracted network flow characteristic is normalized using following formula:
Wherein, Z(i)The i-th network flow characteristic after indicating normalization, v(i)Indicate extracted i-th of network flow characteristic, μ
Indicate feature v(i)Mean value, σ indicate feature v(i)Standard deviation.
4. industry Internet of Things unusual checking device according to claim 3, which is characterized in that the model training list
The estimation parameter for the industrial Internet of Things unusual checking model that training obtains, including weight and deviation.
5. industry Internet of Things unusual checking device according to claim 1-4, which is characterized in that also wrap
It includes:
Alarm Unit, suitable for exporting corresponding alarm prompt when detecting industrial Internet of Things abnormal behaviour.
6. industry Internet of Things unusual checking device according to claim 5, which is characterized in that further include:
It signs storage unit, it is abnormal from detected industrial Internet of Things suitable for when detecting industrial Internet of Things abnormal behaviour
Corresponding signed data is extracted in behavior and is stored in preset log database.
7. industry Internet of Things unusual checking device according to claim 1, which is characterized in that the primitive network stream
Amount data include the information of source IP address, purpose IP address, source port, target port and protocol type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811490982.1A CN109688112A (en) | 2018-12-06 | 2018-12-06 | Industrial Internet of Things unusual checking device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811490982.1A CN109688112A (en) | 2018-12-06 | 2018-12-06 | Industrial Internet of Things unusual checking device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109688112A true CN109688112A (en) | 2019-04-26 |
Family
ID=66186459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811490982.1A Pending CN109688112A (en) | 2018-12-06 | 2018-12-06 | Industrial Internet of Things unusual checking device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109688112A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110365703A (en) * | 2019-07-30 | 2019-10-22 | 国家电网有限公司 | Internet-of-things terminal abnormal state detection method, apparatus and terminal device |
| CN111163115A (en) * | 2020-04-03 | 2020-05-15 | 深圳市云盾科技有限公司 | Internet of things safety monitoring method and system based on double engines |
| CN113783717A (en) * | 2021-08-12 | 2021-12-10 | 北京邮电大学 | Smart city network flow prediction method and system |
| CN114520736A (en) * | 2022-01-24 | 2022-05-20 | 广东工业大学 | Internet of things security detection method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298202A (en) * | 2014-10-21 | 2015-01-21 | 张晓华 | Industrial field intelligent monitoring terminal based on internet of things |
| CN105629790A (en) * | 2016-01-29 | 2016-06-01 | 广州能迪能源科技股份有限公司 | Data management platform and method based on industrial IOT (Internet of Things) |
| US20170347283A1 (en) * | 2016-05-31 | 2017-11-30 | At&T Intellectual Property I, L.P. | System and method for event based internet of things (iot) device status monitoring and reporting in a mobility network |
| CN107944552A (en) * | 2017-12-19 | 2018-04-20 | 电子科技大学 | A kind of industrial Internet of Things parameter prediction method based on Elman neutral nets |
| CN108429753A (en) * | 2018-03-16 | 2018-08-21 | 重庆邮电大学 | A kind of matched industrial network DDoS intrusion detection methods of swift nature |
-
2018
- 2018-12-06 CN CN201811490982.1A patent/CN109688112A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298202A (en) * | 2014-10-21 | 2015-01-21 | 张晓华 | Industrial field intelligent monitoring terminal based on internet of things |
| CN105629790A (en) * | 2016-01-29 | 2016-06-01 | 广州能迪能源科技股份有限公司 | Data management platform and method based on industrial IOT (Internet of Things) |
| US20170347283A1 (en) * | 2016-05-31 | 2017-11-30 | At&T Intellectual Property I, L.P. | System and method for event based internet of things (iot) device status monitoring and reporting in a mobility network |
| CN107944552A (en) * | 2017-12-19 | 2018-04-20 | 电子科技大学 | A kind of industrial Internet of Things parameter prediction method based on Elman neutral nets |
| CN108429753A (en) * | 2018-03-16 | 2018-08-21 | 重庆邮电大学 | A kind of matched industrial network DDoS intrusion detection methods of swift nature |
Non-Patent Citations (1)
| Title |
|---|
| AL-HAWAWREH等: ""Identification of malicious activities in industrial internet of things based on deep learning models"", 《JOURNAL OF INFORMATION SECURITY AND APPLICATIONS》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110365703A (en) * | 2019-07-30 | 2019-10-22 | 国家电网有限公司 | Internet-of-things terminal abnormal state detection method, apparatus and terminal device |
| CN111163115A (en) * | 2020-04-03 | 2020-05-15 | 深圳市云盾科技有限公司 | Internet of things safety monitoring method and system based on double engines |
| CN113783717A (en) * | 2021-08-12 | 2021-12-10 | 北京邮电大学 | Smart city network flow prediction method and system |
| CN113783717B (en) * | 2021-08-12 | 2023-03-24 | 北京邮电大学 | Smart city network flow prediction method and system |
| CN114520736A (en) * | 2022-01-24 | 2022-05-20 | 广东工业大学 | Internet of things security detection method, device, equipment and storage medium |
| CN114520736B (en) * | 2022-01-24 | 2023-08-22 | 广东工业大学 | Internet of things security detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109547455A (en) | Industrial Internet of Things anomaly detection method, readable storage medium storing program for executing and terminal | |
| CN109688112A (en) | Industrial Internet of Things unusual checking device | |
| WO2020143227A1 (en) | Method for generating malicious sample of industrial control system based on adversarial learning | |
| CN106570513B (en) | The method for diagnosing faults and device of big data network system | |
| CN110909811A (en) | OCSVM (online charging management system) -based power grid abnormal behavior detection and analysis method and system | |
| CN104598813B (en) | Computer intrusion detection method based on integrated study and semi-supervised SVM | |
| CN103905440A (en) | Network security situation awareness analysis method based on log and SNMP information fusion | |
| Liu et al. | A novel intrusion detection algorithm for industrial control systems based on CNN and process state transition | |
| CN109639734B (en) | Abnormal flow detection method with computing resource adaptivity | |
| CN117113262B (en) | Network traffic identification method and system | |
| CN105306463A (en) | Modbus TCP intrusion detection method based on support vector machine | |
| CN105991517B (en) | Vulnerability mining method and apparatus | |
| CN108985061A (en) | A kind of webshell detection method based on Model Fusion | |
| CN103810424A (en) | Method and device for identifying abnormal application programs | |
| CN114338195A (en) | Web traffic anomaly detection method and device based on improved isolated forest algorithm | |
| Liu et al. | Slippage fault diagnosis of dampers for transmission lines based on faster R-CNN and distance constraint | |
| CN105871861B (en) | A kind of intrusion detection method of self study protocol rule | |
| CN103971054A (en) | Detecting method of browser extension loophole based on behavior sequence | |
| CN112333128A (en) | Web attack behavior detection system based on self-encoder | |
| CN110022313A (en) | Polymorphic worm feature extraction and polymorphic worm discrimination method based on machine learning | |
| CN108761250B (en) | Industrial control equipment voltage and current-based intrusion detection method | |
| CN108073803A (en) | For detecting the method and device of malicious application | |
| CN108040067B (en) | Cloud platform intrusion detection method, device and system | |
| Yin et al. | Botnet detection based on genetic neural network | |
| CN114863210A (en) | Method and system for resisting sample attack of bridge structure health monitoring data driving model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190426 |