CN111797386A - Credible user behavior detection method based on Internet of things - Google Patents
Credible user behavior detection method based on Internet of things Download PDFInfo
- Publication number
- CN111797386A CN111797386A CN202010599457.4A CN202010599457A CN111797386A CN 111797386 A CN111797386 A CN 111797386A CN 202010599457 A CN202010599457 A CN 202010599457A CN 111797386 A CN111797386 A CN 111797386A
- Authority
- CN
- China
- Prior art keywords
- data
- behavior
- internet
- things
- credible
- 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
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
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/40—Information sensed or collected by the things relating to personal data, e.g. biometric data, records or preferences
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/50—Safety; Security of things, users, data or systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention discloses a credible detection method for user behaviors based on the Internet of things, which comprises the following steps of: the method comprises the following steps: behavior data of the Internet of things equipment is collected in real time; step two: normalizing the collected operation behavior data, numbering each operation behavior data, and mapping to form behavior sequence data; step three: behavior sequence data is used as training data and is led into an LSTM seq2seq model, and loss function mean square error is adopted to carry out model training; step four: behavior sequence data acquired in real time are input into a trained model, and prediction data at the next moment are generated through an LSTM seq2 seq-based model; step five: calculating to obtain a difference value between a predicted value and actual operation behavior data according to the actually acquired operation behavior data at the next moment; step six: and judging whether the user behavior is credible or not through the difference value. The method and the system can ensure the credibility of the behavior of the equipment of the Internet of things and solve the security risk of being attacked and utilized in the Internet of things.
Description
Technical Field
The invention relates to the technical field of Internet of things safety, in particular to a credible detection method for user behaviors based on the Internet of things.
Background
The popularization and rapid development of the internet of things technology enable more and more devices to be intelligentized, and the intelligent network system is deeply applied to the public field, the intelligent environment (such as intelligent families, intelligent offices and intelligent factories), the personal field, the social field and the like; the working principle of the internet of things is that various devices, goods and basic facilities provided with sensing devices (including sensors, RFID devices and the like) are connected with a communication network, so that the objects can communicate with each other and work together, and meanwhile, the objects can be remotely sensed and controlled through APP, so that the interconnection, integration and interaction of people and people, people and objects and a network system are realized, the resource utilization rate and the productivity level are improved, and the production and the life are managed in a more precise and dynamic mode.
The internet of things interconnects and intercommunicates common equipment and even information, so that convenience is provided, and meanwhile, potential safety hazards are buried, if the equipment can be hijacked remotely, the privacy of a user is easy to leak and attack. In the actual case of camera intrusion, hackers also pass through a plurality of illegal scanning software, then obtain the IP address of the camera by means of the scanning software, and then use weak password passwords to scan in a large range by means of a scanner. Finally, the invasion to the camera is realized through the obtained weak password, so that the personal privacy is leaked. In addition to such port scanning attacks, with the increase of IoT devices, hackers have many attacks such as: botnet (a botnet created by internet of things devices generally is called ThingBots) attacks are one type. ThingBots are composed of different kinds of equipment, all interconnected. Hackers can go through botnet attacks by activating these devices on the web, sending large amounts of spam or information through IoT devices.
At present, the reason for such many security problems of the internet of things equipment mainly includes the following points:
firstly, the cost problem is that in order to save the cost, part of manufacturers use a general-purpose and open-source operating system or a third-party component which is not subjected to security detection, which possibly introduces a vulnerability; also based on cost considerations, most internet of things devices do not protect the debug interface, which gives the attacker a chance to enter while being a false one.
Secondly, many manufacturers lack security consciousness and security capability, and do not make security consideration when developing the intelligent equipment of the internet of things, so that software and hardware security loopholes are generated. Meanwhile, many devices lack a software security update mechanism or the mechanism is unsafe, so that vulnerabilities cannot be repaired, and bad consequences are caused.
Thirdly, the identity authentication and authorization mechanism is weak. The intelligent terminal equipment of the internet of things is large in scale, and equipment working in cooperation possibly belongs to different suppliers, so that identity authentication between terminals is difficult to realize. In addition, a large number of devices are using weak passwords, which allows hackers to easily control the devices.
Therefore, the problem of security risk of being attacked and utilized exists in the internet of things, and the traditional security mechanism can solve the problem that the identity of a user is credible, but cannot ensure that the using behavior and the access behavior of the equipment are credible.
Disclosure of Invention
The invention provides a credible detection method for user behaviors based on the Internet of things, which aims to solve the problem of security risk of being attacked and utilized in the Internet of things in the prior art.
The technical scheme adopted by the invention is as follows: a credible detection method based on Internet of things user behavior is characterized by comprising the following steps:
the method comprises the following steps: acquiring behavior data of the Internet of things equipment in real time, wherein the behavior data comprises use time, an equipment serial number, an equipment hardware model and operation behavior data of the equipment;
step two: using the serial number of the equipment of the Internet of things as an identifier, carrying out normalization processing on the collected operation behavior data, numbering each operation behavior data, and mapping the operation behavior data into numbers to form behavior sequence data;
step three: behavior sequence data is used as training data and is led into an LSTMseq2seq model, and loss function mean square error is adopted to carry out model training;
step four: behavior sequence data acquired in real time are input into a trained model, and prediction data at the next moment are generated based on an LSTMseq2seq model;
step five: calculating to obtain a difference value between the prediction data and the actual operation behavior data according to the actual operation behavior data collected at the next moment;
step six: and D, judging whether the user behavior is credible or not by using the difference value in the step five based on the outlier detection method criterion of normal distribution.
Preferably, in step three, the LSTMseq2seq model includes two submodels: one is a coding model that converts the input sequence into a fixed length vector, and the other is a decoding model that decodes the input fixed length vector and outputs a predicted sequence.
Preferably, in step three, the mean square error value is reduced by optimizing the LSTMseq2seq model parameters.
Preferably, in the sixth step, the 3 σ criterion of the outlier detection method is used to determine whether the user behavior is credible, and if the element v in the E is credibleiSatisfy | vi-u|>Judging the data of the 3 sigma condition to be abnormal, indicating that the user behavior is not credible, otherwise, judging the user behavior to be credible; e is a set of difference values, viIs the element in E, u is the average value of E, and σ is the standard deviation of E.
The invention has the beneficial effects that: the traditional safety mechanism in the Internet of things can solve the problem that the identity of a user is credible, and can carry out user identity authentication, but cannot ensure the credibility of the using behavior and the access behavior of equipment. Therefore, the behavior credibility analysis and detection is added on the basis of the existing security technology, the behavior credibility of the equipment of the Internet of things is ensured, the security risk of being attacked and utilized in the Internet of things is solved, and the security risk problems of privacy disclosure or resource stealing and the like caused by attack invasion of lawbreakers can be effectively prevented.
Drawings
Fig. 1 is a flow chart of a detection method for credible user behavior based on the internet of things disclosed by the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail below with reference to the accompanying drawings, but embodiments of the present invention are not limited thereto.
Example 1:
referring to fig. 1, a method for detecting credible user behavior based on the internet of things includes the following steps:
the method comprises the following steps: behavior data of the Internet of things equipment is collected in real time;
specifically, the behavior data includes usage time, a device serial number (i.e., a device ID), a device hardware model (e.g., an internet of things device such as a camera, a television, a refrigerator, etc.), and operation behavior data of the device; the operation behavior data of the equipment comprises operations of left movement of a camera holder, right movement of the camera holder, zooming in of the camera, zooming out of the camera, equipment access and the like, television startup, channel switching operation, program screening operation, volume adjustment, accessed resources, accessed equipment and the like.
The data content of the acquisition is as follows:
time: 2020.3.1812:00: 00;
a device serial number (ID) for uniquely identifying a character of the device;
hardware model of the device: a camera;
device operation data: the camera holder moves left, the camera holder moves right, the camera is drawn close, and the camera is drawn far.
Step two: and using the equipment ID of the Internet of things as an identifier, normalizing the collected operation behavior data, numbering each operation behavior data, and mapping the operation behavior data into numbers to form behavior sequence data.
Specifically, the device ID is used as the user identifier, and the operation behavior data is numbered as follows:
the camera pan-tilt moves to the left: x1
The camera holder moves to the right: x2
Zooming in the focal length: x3
Zooming out: x4
Focal length reduction: x5
After each behavior data is numbered, behavior sequence data X is formed (X1, X2, X3, X4, X5 … Xn), and data in the behavior sequence data is mapped to a number by performing numerical encoding processing, such as X (1,2,3, … n).
Step three: behavior sequence data is led into an LSTMseq2seq model as training data, loss function mean square error is adopted to carry out model training, and the smaller the error is, the closer the predicted value of the model is to the true value is; if the mean square error value is larger, the mean square error value can be reduced by optimizing the model parameters. The mean square error formula is as follows:
Specifically, the LSTMseq2 seq-based model includes two submodels: one is a coding model that converts the input sequence into a fixed-length vector, and the other is a decoding model that decodes the input fixed-length vector and outputs a predicted sequence.
The LSTM (Long-short term memory) Long-short term memory network is a gate-controlled recurrent neural network structure, each unit is a cell, and the LSTM cell has two states: implicit and cellular states, by which the LSTM facilitates the flow of information between cells of the same network layer, different network layers and different time steps. LSEM cells have 3 control gates: the cell state control circuit comprises a forgetting gate, an input gate and an output gate, wherein the forgetting gate, the input gate and the output gate are composed of an addition operation, a multiplication operation and an activation function, and the three gates are used for controlling cell output, a cell state and a hidden state together.
Forget the door: the method is used for learning how long information is stored in a memory unit, and simultaneously determining whether what information needs to be forgotten from the previously stored information currently, reading input information and information of a previous layer is processed by a sigmoid function, wherein 0 represents complete discarding, and 1 represents complete retaining, according to the formula:
ft＝σ(Wf·[ht-1,xt]+bf)
an input gate: for determining what new information is needed for learning, updated input values are determined by the sigmoid layer, and a tanh layer creates a new candidate value vector to be added to the state, as shown in the formula:
it＝σ(Wi·[ht-1,xt]+bi)
finally, multiplying the state of the previous layer by ft to determine the discarded information, and adding a new candidate value, as shown in the formula:
an output gate: for determining a final output value, firstly, determining an output state through sigmoid, and then mapping output information through tanh function to obtain an output value, as shown in the formula:
ot＝σ(Wo·[ht-1,xt]+bo)
ht＝ot×tanh(Ct)
inputting the preprocessed time series data in an LSTMseq2seq prediction model, entering into an encoding layer with an LSTM structure, obtaining a vector through encoding, entering the vector into a decoding model with the LSTM structure, decoding, and finally sequentially and circularly predicting to obtain an output prediction data sequence.
Inputting: sequence containing behavior signature x ═ (x1, x2, …, xn)
And (3) outputting: predicted data sequence y ═ (y1, y2, …, yn)
Step four: and performing corresponding data prediction on the trained model, inputting the behavior sequence data X acquired in real time into the model (X1, X2, X3, X, xn), and generating prediction data at the next moment, such as h (Y1, Y2, Y3, Y, Yn) based on the LSTMseq2seq model.
Step five: calculating a difference value between the predicted value and the actual operation behavior data according to the actually acquired actual operation behavior data m at the next moment (X1, X2, X3, v · Xn), wherein E ═ h-m | (v1, v2, v3, ·, vn), according to a formula:
according to the formula:
the standard deviation σ of E is calculated.
Step six: judging whether the user behavior is credible or not by using the 3 sigma criterion of the outlier detection method based on normal distribution of the difference values in the step five, and if so, judging whether the user behavior is credible by using the element v in the element EiSatisfy | vi-u|>And judging the data of the 3 sigma condition as abnormal data, indicating that the user behavior is not credible, otherwise, judging the user behavior to be credible.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (4)
1. A credible detection method based on Internet of things user behavior is characterized by comprising the following steps:
the method comprises the following steps: acquiring behavior data of the Internet of things equipment in real time, wherein the behavior data comprises use time, an equipment serial number, an equipment hardware model and operation behavior data of the equipment;
step two: using the serial number of the equipment of the Internet of things as an identifier, carrying out normalization processing on the collected operation behavior data, numbering each operation behavior data, and mapping the operation behavior data into numbers to form behavior sequence data;
step three: behavior sequence data is used as training data and is led into an LSTM seq2seq model, and loss function mean square error is adopted to carry out model training;
step four: behavior sequence data acquired in real time are input into a trained model, and prediction data at the next moment are generated through an LSTM seq2 seq-based model;
step five: calculating to obtain a difference value between the prediction data and the actual operation behavior data according to the actual operation behavior data collected at the next moment;
step six: and D, judging whether the user behavior is credible or not by using the difference value in the step five based on the outlier detection method criterion of normal distribution.
2. The internet of things user behavior credible detection method as claimed in claim 1, wherein: in step three, the LSTM seq2seq model includes two submodels: one is a coding model that converts the input sequence into a fixed length vector, and the other is a decoding model that decodes the input fixed length vector and outputs a predicted sequence.
3. The internet of things user behavior credible detection method as claimed in claim 1, wherein: in the third step, the mean square error value is reduced by optimizing LSTM seq2seq model parameters.
4. The internet of things user behavior credible detection method as claimed in claim 1, wherein: in the sixth step, the 3 sigma criterion of the outlier detection method is used for judging whether the user behavior is credible, if the element v in the E isiSatisfy | vi-u|>Judging the data of the 3 sigma condition to be abnormal, indicating that the user behavior is not credible, otherwise, judging the user behavior to be credible; e is a set of difference values, viIs the element in E, u is the average value of E, and σ is the standard deviation of E.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010599457.4A CN111797386A (en) | 2020-06-28 | 2020-06-28 | Credible user behavior detection method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010599457.4A CN111797386A (en) | 2020-06-28 | 2020-06-28 | Credible user behavior detection method based on Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111797386A true CN111797386A (en) | 2020-10-20 |
Family
ID=72804710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010599457.4A Pending CN111797386A (en) | 2020-06-28 | 2020-06-28 | Credible user behavior detection method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111797386A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114580852A (en) * | 2022-01-30 | 2022-06-03 | 江苏苏华泵业有限公司 | Water pump breakwater clearance real-time warning system based on industry big data |
| CN115795484A (en) * | 2023-02-06 | 2023-03-14 | 北京长亭未来科技有限公司 | Vulnerability detection method and device for Internet of things equipment and equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086912A (en) * | 2018-07-11 | 2018-12-25 | 东北大学 | A kind of intelligent appliance user's behavior prediction method and apparatus based on LSTM |
| CN109685290A (en) * | 2019-02-11 | 2019-04-26 | 南方电网科学研究院有限责任公司 | A kind of electricity demand forecasting method, device and equipment based on deep learning |
| CN109698836A (en) * | 2019-02-01 | 2019-04-30 | 重庆邮电大学 | A kind of method for wireless lan intrusion detection and system based on deep learning |
| CN110232082A (en) * | 2019-06-13 | 2019-09-13 | 中国科学院新疆理化技术研究所 | Method for detecting abnormality towards continuous space-time oil-filling data |
| CN110378392A (en) * | 2019-06-26 | 2019-10-25 | 华东师范大学 | A kind of indoor geriatric state's monitoring method based on LSTM-AE |
| US20200125992A1 (en) * | 2018-10-19 | 2020-04-23 | Tata Consultancy Services Limited | Systems and methods for conversational based ticket logging |
-
2020
- 2020-06-28 CN CN202010599457.4A patent/CN111797386A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086912A (en) * | 2018-07-11 | 2018-12-25 | 东北大学 | A kind of intelligent appliance user's behavior prediction method and apparatus based on LSTM |
| US20200125992A1 (en) * | 2018-10-19 | 2020-04-23 | Tata Consultancy Services Limited | Systems and methods for conversational based ticket logging |
| CN109698836A (en) * | 2019-02-01 | 2019-04-30 | 重庆邮电大学 | A kind of method for wireless lan intrusion detection and system based on deep learning |
| CN109685290A (en) * | 2019-02-11 | 2019-04-26 | 南方电网科学研究院有限责任公司 | A kind of electricity demand forecasting method, device and equipment based on deep learning |
| CN110232082A (en) * | 2019-06-13 | 2019-09-13 | 中国科学院新疆理化技术研究所 | Method for detecting abnormality towards continuous space-time oil-filling data |
| CN110378392A (en) * | 2019-06-26 | 2019-10-25 | 华东师范大学 | A kind of indoor geriatric state's monitoring method based on LSTM-AE |
Non-Patent Citations (1)
| Title |
|---|
| 陶涛 等: "基于双向LSTM的Seq2Seq模型在加油站时序数据异常检测中的应用", 《计算机应用》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114580852A (en) * | 2022-01-30 | 2022-06-03 | 江苏苏华泵业有限公司 | Water pump breakwater clearance real-time warning system based on industry big data |
| CN114580852B (en) * | 2022-01-30 | 2022-11-29 | 江苏苏华泵业有限公司 | Water pump breakwater clearance real-time warning system based on industry big data |
| CN115795484A (en) * | 2023-02-06 | 2023-03-14 | 北京长亭未来科技有限公司 | Vulnerability detection method and device for Internet of things equipment and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Network security situation awareness based on semantic ontology and user-defined rules for Internet of Things | |
| Jacobsson et al. | A risk analysis of a smart home automation system | |
| CN105376255B (en) | A kind of Android platform intrusion detection method based on K-means cluster | |
| Yin et al. | A subgrid-oriented privacy-preserving microservice framework based on deep neural network for false data injection attack detection in smart grids | |
| CN107346388A (en) | Web attack detection methods and device | |
| CN111797386A (en) | Credible user behavior detection method based on Internet of things | |
| US9491186B2 (en) | Method and apparatus for providing hierarchical pattern recognition of communication network data | |
| CN112464295A (en) | Communication maintenance safety device based on electric power edge gateway equipment | |
| Bai et al. | Intrusion detection algorithm based on change rates of multiple attributes for WSN | |
| Ahmed et al. | Internet of things: Security threats and proposed solutions | |
| Shafiq et al. | Analyzing IoT attack feature association with threat actors | |
| CN113992437B (en) | Access control management method, device and system for Modbus equipment | |
| Shi et al. | An immunity-based IOT environment security situation awareness model | |
| CN109670339A (en) | The access control method and device towards secret protection based on ontology | |
| Rakas et al. | Intrusion detection systems in smart grid | |
| Mankodiya et al. | Deep Learning-based Secure Machine-to-Machine Communication in Edge-Enabled Industrial IoT | |
| US20220116783A1 (en) | System that provides cybersecurity in a home or office by interacting with Internet of Things devices and other devices | |
| CN114357449A (en) | Abnormal process detection method and device, electronic equipment and storage medium | |
| Eid et al. | IIoT network intrusion detection using machine learning | |
| Din et al. | Challenges in IoT Technology Adoption into Information System Security Management of Smart Cities: A Review | |
| Umsonst et al. | Sample-based anomaly detector tuning with finite sample guarantees | |
| Poongodi et al. | Intrusion detection system using distributed multilevel discriminator in GAN for IoT system | |
| Shaikh et al. | Anomaly Based Intrusion Detection System Using Deep Learning Methods | |
| Hu et al. | Security operation center design based on ds evidence theory | |
| Robles Durazno | Industrial control systems cybersecurity analysis and countermeasures |
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: 20201020 |