CN110417755A - Based on the industry control protocol bug excavation method for generating confrontation network - Google Patents
Based on the industry control protocol bug excavation method for generating confrontation network Download PDFInfo
- Publication number
- CN110417755A CN110417755A CN201910626439.8A CN201910626439A CN110417755A CN 110417755 A CN110417755 A CN 110417755A CN 201910626439 A CN201910626439 A CN 201910626439A CN 110417755 A CN110417755 A CN 110417755A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- training
- depth
- study
- 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
-
- 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
-
- 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
-
- 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
- H04L63/1433—Vulnerability analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Debugging And Monitoring (AREA)
Abstract
It is the present invention relates to industrial control system, depth confrontation study, fuzz testing field, in particular to a kind of based on the industry control protocol bug excavation method for generating confrontation network.Include: depth confrontation study, generates fuzz testing data；Depth is fought the fuzz testing data that study generates and is injected into system by attack test, and records the abnormal feedback of system, excavates the loophole of the system.The present invention is combined by the way that fuzz testing technology is fought learning art with depth, it realizes efficiently, the format of autonomous study communication data, and generates the fuzz testing data with variation, this technology accomplishes the very big burden for mitigating people in bug excavation efficient and intelligent.
Description
Technical field
It is the present invention relates to industrial control system, depth confrontation study, fuzz testing field, in particular to a kind of based on generation
Fight the industry control protocol bug excavation method of network.
Background technique
In traditional industry control protocol system fuzz testing bug excavation technology, the design of fuzz testing data generates excessive
By artificial analysis and design, and this analysis design very time and effort consuming, and be easy error, while can not have effect
Test data generation is carried out to the system of the agreement of proprietary protocol or unknown format, so that the loophole of industry control protocol system
Excavate not efficient enough, intelligence.
Summary of the invention
The embodiment of the invention provides a kind of based on the industry control protocol bug excavation method for generating confrontation network, constructs one
It intelligently can quickly learn the frame lattice of communication data in industry control work system, and the loophole for generating correct format fuzz testing data is dug
Pick system is combined by the way that fuzz testing technology is fought learning art with depth, is realized efficiently, autonomous study communication data
Format, and generate with variation fuzz testing data, this technology will greatly mitigate bug excavation in people burden, accomplish
It is efficiently and intelligent.
According to a first aspect of the embodiments of the present invention, a kind of based on the industry control protocol bug excavation side for generating confrontation network
Method, comprising:
Depth confrontation study, generates fuzz testing data；
Depth is fought the fuzz testing data that study generates and is injected into system, and records the different of system by attack test
Often feedback, excavates the loophole of the system.
Further include Frame processes, grabs the communication data in communication process, and pre-process to data.
The depth confrontation study, including parameter setting, model training and model verifying,
Parameter setting selects the structure of neural network for data characteristics in industry control method；
Model training uses pretreated communication data as training dataset, and using confrontation neural network, training is generated
Model and discrimination model；
Model verifying uses the pretreated communication data of remainder to handle as data set, and verifying generates model and sentences
Other model.
Attack test includes re -training, is recorded to the system exception behavior of discovery, and records and cause the exception
Specific data frame data, will specific data frame data duplication after be used as training dataset, using confrontation neural network, training described in
Generate model and the discrimination model.
The generation model activation primitive is Relu activation primitive.
It in the generation model, is cut using weight, reaches and model training is kept to stablize.
The evaluation index of Wasserstein distance instruction model training.
Sigmoid activation primitive is eliminated in discrimination model.
Frame processes include that data frame crawl and data frame pre-process,
The characteristics of data frame crawl is for the industry control means of communication, grab the communication data in communication process；
Data frame pretreatment pre-processes communication data to be analyzed.
The pretreatment includes that data frame expands, data frame cluster, encoding operation.
Technical solution provided in an embodiment of the present invention can include the following benefits:
Industry control protocol bug excavation method proposed by the present invention based on generation confrontation network, realizes depth fighting study
Technical application, can be in the case where no mankind's Analysis of Intelligence be put into the bug excavation of industrial control system, intelligent study work
Data frame pattern in control system, and generate the variation data of icotype.Meanwhile the simple parameter adjustment of system can needle
The generation of fuzz testing data is carried out to different industrial control systems, loophole is excavated to do pressure test, greatly alleviates artificial point
The burden of analysis design test data, improves the degree of intelligence of system.
Network is fought based on generating, system will directly do unsupervised learning from industrial control system to be tested, generate a large amount of
Test data, the analysis for effectively mitigating the mankind design burden, reduce the throw in intelligence of the mankind.
Network is fought based on generating, system, which can facilitate, adapts to different industrial control systems, in the industry control system in face of not standardizing
It when system or proprietary protocol system, can intelligently be learnt from communication data, accomplish that height is intelligent.
Detailed description of the invention
The drawings herein are incorporated into the specification and constitutes a module of this specification, shows and meets implementation of the invention
Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is the embodiment of the present invention one based on the industry control protocol bug excavation method module map for generating confrontation network；
Fig. 2 is the embodiment of the present invention two based on the industry control protocol bug excavation method module map for generating confrontation network；
Fig. 3 is the place of data frame of the embodiment of the present invention two based on the industry control protocol bug excavation method for generating confrontation network
Manage schematic diagram.
Specific embodiment
The present invention, which constructs one, can intelligently learn to generate the technical method that test data does industrial control system bug excavation,
By the way that based on existing communication data frame, training generates confrontation neural network, specific Maker model and arbiter are obtained
Model, Maker model excavate system with these data using the data for generating a large amount of icotypes as test data
Test is fought the combination of learning art by fuzz testing technology and depth, realizes the intelligent excavating of industrial control system loophole.
Embodiment one
As shown in Figure 1, the present invention provides a kind of based on the industry control protocol bug excavation method for generating confrontation network, packet
It includes:
Depth confrontation study, generates fuzz testing data；Mould can be generated by neural rivalry training in depth confrontation study
Paste test data.
Depth is fought the fuzz testing data that study generates and is injected into system, and records the different of system by attack test
Often feedback, excavates the loophole of the system.
Embodiment two
As shown in Figure 2 and Figure 3, the present invention provides it is a kind of based on generate confrontation network industry control protocol bug excavation method,
It specifically includes:
Frame processes cluster the raw data in source, are aligned, format is converted using statistics and machine learning techniques
Operation；Since handled data are the communication data in industrial control system, feature is list type, there is unified mode, length
It is different；Communication data has fixed protocol format, and with the presence of pattern information, the characteristics of being directed to industry control communication system, crawl is logical
Communication data during news, and hexadecimal data are converted into decimal format, it is then stored into specific file or number
According to library；
Data frame crawl includes data frame crawl and data frame pretreatment；
The characteristics of data frame crawl is for industry control communication system, grabs the communication data in communication process；
Data frame pretreatment pre-processes communication data to be analyzed, such as: data frame amplification, data frame cluster etc.；
And the communication data caught is performed the encoding operation, such as: one-hot coding；Convenient for the processing of further part.
Depth confrontation study is based on confrontation network (WGAN) is generated, with the pretreated normal communication data of primary collection
Training dataset is used as after processing, training obtains generating model, and trained generation model will generate and normal data has phase
With format but sequence data that content has differences, while training discrimination model carries out true and false differentiation to the sequence data of generation,
Such dual training, which constantly adjusts, generates model and discrimination model, finally obtains two stable models；Net is fought based on generating
The depth of network fights study, fights network using generating, introduces Maker model and arbiter model, does confrontation study, reaches
The effect of unsupervised learning.
Depth confrontation study includes parameter setting, model training and model verifying；
Parameter setting reasonably selects the structure of neural network, improves model training for data characteristics in industrial control system
Speed；It is high according to the accuracy of the format of data frame, select convolutional neural networks；Data frame has sequential relationship, selection circulation mind
Through network.
Model training uses pretreated communication data processing as training dataset, and training obtains generating model, training
The sequence data that good generation model will generate and there is normal data same format but content to have differences, while training differentiates
Model carries out true and false differentiation to the sequence data of generation, and such dual training, which constantly adjusts, generates model and discrimination model, finally
Obtain two stable models.
Model verifying uses the pretreated normal communication data processing of remainder as data set, and verifying generates model
And discrimination model；
It is described that study is fought based on the depth for generating confrontation network (WGAN), Wasserstein distance is introduced to measure two
Difference between a distribution, the measurement can effectively indicate the quality of model training, provide preferable model-evaluation index；
Wasserstein distance is called Earth-Mover distance (EM distance), for measuring the difference between two distributions.
Data after processed will enter into arbiter model, arbiter model be based on the neural network connected entirely,
Gaussian noise is input in Maker model and is handled and is exported, which is also used as the input of arbiter to go judgement true
Vacation, generates dual training, and the model parameter that two models constantly adjust oneself in the training process forms stable model；
Preferably, for the unstable feature of confrontation network training is generated, make in the selection for generating model activation primitive
With Relu activation primitive, the unstability of model training is reduced；
It is described that study is fought based on the depth for generating confrontation network (WGAN), sigmoid is eliminated in discrimination model to be swashed
Function living, and the parameter of model is adjusted using weight cutting in training, avoid the model during model training from collapsing
It bursts, keeps the diversity of the test data generated；
Study is fought based on the depth for generating confrontation network, to generating in model, using weight method of cutting out, reaches holding
The stable effect of model training, avoids model from not restraining, model collapse；
The data transmission of generation is injected into goal systems, digging system loophole, and records initiation by attack test
Abnormal behaviour and corresponding transmitting and receiving process.
Study is fought based on the depth for generating confrontation network (WGAN), is used to carry out pattern information to the data of crawl
Study, the generation of test data is instructed with the mode learnt；Network is fought using generating, introduces and generates model and confrontation model
Unsupervised learning is carried out, for solving the difficult point of data pattern excavation, different protocol systems is successfully managed, is learnt；
The characteristics of for communication system data frame, reasonably selects full link neural network framework as each model base
Plinth carries out modelling；
Attack test is injected into corresponding system for depth to be fought the fuzz testing data that study generates, and remembers
The abnormal feedback of recording system, to excavate the loophole of the system；
Depth is fought into the mass data frame that study generates and is sent to specific system progress pressure test, record sends and connects
The process of receipts, to find the abnormal behaviour of system；
Preferably, attack test further includes re -training, and re -training records the system exception behavior of discovery, and
Record causes the specific data frame data of the exception, training dataset will be used as after the duplication of specific data frame data, using confrontation
Neural network, training generate model and discrimination model.
The present invention is based on generate confrontation network industry control protocol bug excavation method, realize by depth confrontation learning art and
Fuzz testing technology is applied in the bug excavation of industrial control system, can intelligently learn in the case where prosthetic is analyzed and put into
Practise the data frame pattern excavated in communication system.Meanwhile being adjusted by simple parameter, which is adapted to other a variety of works
The bug excavation of control system.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (10)
1. a kind of based on the industry control protocol bug excavation method for generating confrontation network characterized by comprising
Depth confrontation study, generates fuzz testing data；
Depth is fought the fuzz testing data that study generates and is injected into system by attack test, and records the abnormal anti-of system
Feedback, excavates the loophole of the system.
2. the method as described in claim 1, which is characterized in that it further include Frame processes before depth confrontation study,
The communication data in communication process is grabbed, and data are pre-processed.
3. method according to claim 2, which is characterized in that the depth confrontation study, including parameter setting, model training
It is verified with model, in which:
Parameter setting selects the structure of neural network for data characteristics in industry control method；
Model training uses pretreated communication data as training dataset, and using confrontation neural network, training generates model
And discrimination model；
Model verifying uses the pretreated communication data of remainder to handle as data set, and verifying generates model and differentiates mould
Type.
4. method as claimed in claim 3, which is characterized in that attack test includes re -training, re -training, to discovery
System exception behavior is recorded, and records the specific data frame data for causing the exception, after the duplication of specific data frame data
As training dataset, using confrontation neural network, the training generation model and the discrimination model.
5. method as claimed in claim 3, which is characterized in that the generation model activation primitive is Relu activation primitive.
6. method as claimed in claim 3, which is characterized in that in the generation model, cut using weight, keep model instruction
Practice and stablizes.
7. method as claimed in claim 3, which is characterized in that use the evaluation of Wasserstein distance instruction model training
Index.
8. method as claimed in claim 3, which is characterized in that eliminate sigmoid activation primitive in discrimination model.
9. the method as described in claim 2-8 any one claim, which is characterized in that Frame processes include data frame
Crawl and data frame pretreatment,
The characteristics of data frame crawl is for the industry control means of communication, grab the communication data in communication process；
Data frame pretreatment pre-processes communication data to be analyzed.
10. method as claimed in claim 9, which is characterized in that the pretreatment includes that data frame expands, data frame cluster,
Encoding operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910626439.8A CN110417755A (en) | 2019-07-11 | 2019-07-11 | Based on the industry control protocol bug excavation method for generating confrontation network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910626439.8A CN110417755A (en) | 2019-07-11 | 2019-07-11 | Based on the industry control protocol bug excavation method for generating confrontation network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110417755A true CN110417755A (en) | 2019-11-05 |
Family
ID=68361142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910626439.8A Pending CN110417755A (en) | 2019-07-11 | 2019-07-11 | Based on the industry control protocol bug excavation method for generating confrontation network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110417755A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110855654A (en) * | 2019-11-06 | 2020-02-28 | 中国移动通信集团广东有限公司 | Vulnerability risk quantitative management method and system based on flow mutual access relation |
| CN111026012A (en) * | 2019-11-29 | 2020-04-17 | 哈尔滨安天科技集团股份有限公司 | Method and device for detecting PLC firmware level bugs, electronic equipment and storage medium |
| CN112073242A (en) * | 2020-09-08 | 2020-12-11 | 中国人民解放军陆军工程大学 | Method for generating and applying network protocol fuzzy test case |
| CN113312891A (en) * | 2021-04-22 | 2021-08-27 | 北京墨云科技有限公司 | Automatic payload generation method, device and system based on generative model |
| CN113468071A (en) * | 2021-07-23 | 2021-10-01 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Fuzzy test case generation method, system, computer equipment and storage medium |
| CN114117450A (en) * | 2021-12-01 | 2022-03-01 | 湖南大学 | Seed generation method for trusted computing environment fuzzy test |
| CN115174194A (en) * | 2022-06-30 | 2022-10-11 | 浙江极氪智能科技有限公司 | System vulnerability mining method, device, equipment and storage medium |
| CN116016297A (en) * | 2022-12-27 | 2023-04-25 | 中国联合网络通信集团有限公司 | Communication monitoring system and method based on artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170169357A1 (en) * | 2015-12-15 | 2017-06-15 | Deep Instinct Ltd. | Methods and systems for data traffic analysis |
| CN108520504A (en) * | 2018-04-16 | 2018-09-11 | 湘潭大学 | A kind of blurred picture blind restoration method based on generation confrontation network end-to-end |
| CN108549597A (en) * | 2018-03-05 | 2018-09-18 | 浙江大学 | A kind of fuzzy detection seed set generation method and generator based on WGAN models |
| CN109218134A (en) * | 2018-09-27 | 2019-01-15 | 华东师范大学 | A kind of Test cases technology system based on neural Style Transfer |
-
2019
- 2019-07-11 CN CN201910626439.8A patent/CN110417755A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170169357A1 (en) * | 2015-12-15 | 2017-06-15 | Deep Instinct Ltd. | Methods and systems for data traffic analysis |
| CN108549597A (en) * | 2018-03-05 | 2018-09-18 | 浙江大学 | A kind of fuzzy detection seed set generation method and generator based on WGAN models |
| CN108520504A (en) * | 2018-04-16 | 2018-09-11 | 湘潭大学 | A kind of blurred picture blind restoration method based on generation confrontation network end-to-end |
| CN109218134A (en) * | 2018-09-27 | 2019-01-15 | 华东师范大学 | A kind of Test cases technology system based on neural Style Transfer |
Non-Patent Citations (1)
| Title |
|---|
| ZHIHUI LI: "An Intelligent Fuzzing Data Generation Method Based on Deep Adversarial Learning", 《IEEE ACCESS》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110855654A (en) * | 2019-11-06 | 2020-02-28 | 中国移动通信集团广东有限公司 | Vulnerability risk quantitative management method and system based on flow mutual access relation |
| CN110855654B (en) * | 2019-11-06 | 2021-10-08 | 中国移动通信集团广东有限公司 | Vulnerability risk quantitative management method and system based on flow mutual access relation |
| CN111026012A (en) * | 2019-11-29 | 2020-04-17 | 哈尔滨安天科技集团股份有限公司 | Method and device for detecting PLC firmware level bugs, electronic equipment and storage medium |
| CN112073242A (en) * | 2020-09-08 | 2020-12-11 | 中国人民解放军陆军工程大学 | Method for generating and applying network protocol fuzzy test case |
| CN113312891A (en) * | 2021-04-22 | 2021-08-27 | 北京墨云科技有限公司 | Automatic payload generation method, device and system based on generative model |
| CN113312891B (en) * | 2021-04-22 | 2022-08-26 | 北京墨云科技有限公司 | Automatic payload generation method, device and system based on generative model |
| CN113468071A (en) * | 2021-07-23 | 2021-10-01 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Fuzzy test case generation method, system, computer equipment and storage medium |
| CN113468071B (en) * | 2021-07-23 | 2023-10-03 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Fuzzy test case generation method, system, computer equipment and storage medium |
| CN114117450A (en) * | 2021-12-01 | 2022-03-01 | 湖南大学 | Seed generation method for trusted computing environment fuzzy test |
| CN115174194A (en) * | 2022-06-30 | 2022-10-11 | 浙江极氪智能科技有限公司 | System vulnerability mining method, device, equipment and storage medium |
| CN116016297A (en) * | 2022-12-27 | 2023-04-25 | 中国联合网络通信集团有限公司 | Communication monitoring system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110417755A (en) | Based on the industry control protocol bug excavation method for generating confrontation network | |
| CN110532778A (en) | Based on the industry control protocol bug excavation system for generating confrontation network | |
| CN108776683B (en) | Electric power operation and maintenance data cleaning method based on isolated forest algorithm and neural network | |
| Aldosari et al. | Fusion in sensor networks with communication constraints | |
| CN111488577B (en) | Model building method and risk assessment method and device based on artificial intelligence | |
| CN105024877B (en) | A kind of Hadoop malicious node detecting systems based on user's behaviors analysis | |
| US11699278B2 (en) | Mapper component for a neuro-linguistic behavior recognition system | |
| CN107423217B (en) | Black box fuzzy test method and system based on variation tree | |
| CN112073242A (en) | Method for generating and applying network protocol fuzzy test case | |
| CN110991871A (en) | Risk monitoring method, device, equipment and computer readable storage medium | |
| CN110190909B (en) | Signal equalization method and device for optical communication | |
| CN110334105B (en) | Stream data abnormity detection method based on Storm | |
| CN117435506B (en) | Fuzzy test method, electronic device and computer readable storage medium | |
| KR20190001501A (en) | Artificial intelligence operations system of telecommunication network, and operating method thereof | |
| CN113114581A (en) | TCP congestion control method and device based on multi-agent deep reinforcement learning | |
| CN111553806A (en) | Self-adaptive crop management system and method based on low-power-consumption sensor and Boost model | |
| Woźniak et al. | Active learning classification of drifted streaming data | |
| CN113726545A (en) | Network traffic generation method and device for generating countermeasure network based on knowledge enhancement | |
| KR102254522B1 (en) | Control method, device and program of parametric equalizing sound tuning system using artificial intelligence | |
| Stamatakis et al. | Autonomous maintenance in IoT networks via aoi-driven deep reinforcement learning | |
| KR20190028880A (en) | Method and appratus for generating machine learning data for botnet detection system | |
| CN111475358A (en) | Automatic testing method and device for controller interface | |
| CN106846080A (en) | The real-time monitoring system and method placed an order in line service | |
| CN113987980B (en) | Popular simulation implementation method for physical PHD (graphical user device) | |
| CN107579871A (en) | The generation method of distributed testing script based on model inspection and generation system |
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 |
Application publication date: 20191105 |
|
| RJ01 | Rejection of invention patent application after publication |