CN110110525A - A kind of bug excavation method based on machine learning and deep learning - Google Patents
A kind of bug excavation method based on machine learning and deep learning Download PDFInfo
- Publication number
- CN110110525A CN110110525A CN201910342954.3A CN201910342954A CN110110525A CN 110110525 A CN110110525 A CN 110110525A CN 201910342954 A CN201910342954 A CN 201910342954A CN 110110525 A CN110110525 A CN 110110525A
- Authority
- CN
- China
- Prior art keywords
- bug excavation
- excavation method
- loophole
- code
- machine learning
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/52—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems during program execution, e.g. stack integrity ; Preventing unwanted data erasure; Buffer overflow
- G06F21/53—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems during program execution, e.g. stack integrity ; Preventing unwanted data erasure; Buffer overflow by executing in a restricted environment, e.g. sandbox or secure virtual machine
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/55—Detecting local intrusion or implementing counter-measures
- G06F21/56—Computer malware detection or handling, e.g. anti-virus arrangements
- G06F21/562—Static detection
- G06F21/563—Static detection by source code analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/57—Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
- G06F21/577—Assessing vulnerabilities and evaluating computer system security
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Virology (AREA)
- Computing Systems (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a kind of bug excavation method based on machine learning and deep learning, the bug excavation method is the following steps are included: step 1: carrying out automation code pattern identification to source code data；Step 2: determining source code data type according to identifying；Step 3: being associated analysis and heuristic search；Step 4: homologous threat problem of the same clan is found out from code vulnerabilities library；Step 5: implementing attack, and attack effect returns, if attacking unsuccessful return step 3, if success attack executes step 6；Step 6: vulnerability exploit is presented, and general strike scheme is exported to code vulnerabilities library.
Description
Technical field
The present invention relates to technical field of network information safety, more particularly to the loophole based on machine learning and deep learning
Method for digging.
Background technique
System vulnerability refers to that there are weakness or defects in system, because of the presence of loophole, system can passively be generated to specific
The sensibility of attack or hazard event is threatened, or there is a possibility that threat effect attacked.Loophole may be from applying
The mistake generated when defect or coding when software or operating system design, it is also possible to from business in iterative process
Unreasonable place in design defect or logic flow.These defects, mistake or unreasonable place may be by either intentionally or unintentionally
It utilizes, so that the assets or operation organized to one adversely affect, or even ruins paralysed event.So needing a kind of continue
Efficient bug excavation method carrys out continuous output loophole, it is ensured that the safety of all types of information systems.
Excavating loophole is a long-term process, but since the types such as equipment, system, agreement, application, network, signal are numerous
More, the bug excavation in these fields just becomes very many and diverse, difficult problem, and lasting height is also hardly formed to loophole even if excavating
The excavation and defence ecology of effect.
Thus, it is desirable to have a kind of bug excavation method based on machine learning and deep learning can overcome or at least mitigate
Bug excavation technology relies primarily on manually in the prior art, the low problem of digging efficiency.
Summary of the invention
The invention discloses a kind of bug excavation method based on machine learning and deep learning, the bug excavation method
The following steps are included:
Step 1: automation code pattern identification is carried out to source code data；
Step 2: determining source code data type according to identifying；
Step 3: being associated analysis and heuristic search；
Step 4: homologous threat problem of the same clan is found out from code vulnerabilities library；
Step 5: implementing attack, and attack effect returns, if unsuccessful return step 3 is attacked, if success attack is held
Row step 6；
Step 6: vulnerability exploit is presented, and general strike scheme is exported to code vulnerabilities library.
Preferably, the association analysis of the step 3 and heuristic search include from the mode of writing, frame structure, module resource
Threat problem is verified with the multiple dimensions of same source code.
Preferably, the association analysis of the step 3 and heuristic search include from the mode of writing, frame structure, module resource
Threat problem is verified with the multiple dimensions of same source code.
It is disclosed by the invention that machine learning and depth are based on based on the research of the bug excavation method of machine learning and deep learning
The intelligent bug excavation technology of study is spent, the identification of automation code pattern, association analysis and heuristic search are realized, in conjunction with warp
The loophole of overfitting is dominant, recessive character, improves the automation and scale ability of bug excavation.
Detailed description of the invention
Fig. 1 is the flow chart of the bug excavation method based on machine learning and deep learning.
Fig. 2 is the work-based logic schematic diagram of Exploit developing intellectual resource.
Fig. 3 is the flow chart of malicious code origin cause of formation movement verifying.
Specific embodiment
To keep the purposes, technical schemes and advantages of the invention implemented clearer, below in conjunction in the embodiment of the present invention
Attached drawing, technical solution in the embodiment of the present invention is further described in more detail.In the accompanying drawings, identical from beginning to end or class
As label indicate same or similar element or element with the same or similar functions.Described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.The embodiments described below with reference to the accompanying drawings are exemplary, it is intended to use
It is of the invention in explaining, and be not considered as limiting the invention.Based on the embodiments of the present invention, ordinary skill people
Member's every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
As shown in Figure 1, the bug excavation method based on machine learning and deep learning the following steps are included:
Step 1: automation code pattern identification is carried out to source code data；
Automate code pattern identification: the code under various compiler languages has self-characteristic and general character, quickly reads generation
Code simultaneously analyzes the basis that its code pattern is bug excavation；
Step 2: determining source code data type according to identifying；
Step 3: being associated analysis and heuristic search；
Association analysis and heuristic search: it analyzes after code pattern classified, according to finding out in code vulnerabilities library
Homologous threat problem of the same clan goes verifying to threaten from the mode of writing, frame structure, module resource, same to source code, the multiple dimensions of interface
Problem solves the problems, such as that single dominant threat can not accomplish intelligent association, to excavate dominant, recessive character, more on a large scale
Rapid output loophole resource and strike scheme；
Step 4: homologous threat problem of the same clan is found out from code vulnerabilities library；
Step 5: implementing attack, and attack effect returns, if unsuccessful return step 3 is attacked, if success attack is held
Row step 6；
Step 6: vulnerability exploit is presented, and general strike scheme is exported to code vulnerabilities library.
1. being mined environment and homologous design, cross-platform excavation is realized
Towards different computing environments such as general purpose computer, mobile intelligent terminal, industrial control systems, researches and develops serial loophole and dig
Platform is dug, the digging efficiency to different computing platforms software and system vulnerability is improved；Towards a certain loophole, can find rapidly same
Homologous loophole in one computing platform and different computing platforms forms cross-platform bug excavation ability, improves the needle of bug excavation
To property and digging efficiency.
2. using distributed computing technology and fuzz testing engine
Discovering software vulnerabilities system eliminates the test rate bottleneck of fuzz testing using distributed computing technology, and platform is simultaneously
It obtains the various sample files on internet extensively using search engine technique, and is screened according to the demand of fuzz testing,
Obtain the optimal test sample for being directed to tested program.The fuzz testing engine of platform will also integrate and improve existing fuzz testing
Technology and achievement, the integration that these technologies and resource carry out system is encapsulated, and complicated sport technique segment is packaged into simple number
According to interface, user, which carries out operation by web console, can be realized the deployment installation of tested program, test assignment initiation, distribution
Formula detects execution, test assignment monitoring, a series of activities such as mechanized classification of exception catching, test result.
3. enabling genetic algorithm
Genetic algorithm is calculated for solving optimized searching algorithm in mathematics, is one kind of evolution algorithm.Heredity is calculated
Method carries out Fuzzy processing to the key bytes in sample input data, and calculates the fitness of sample input data, determines
Which input data should be retained, which input data should be abandoned.
Application of the genetic algorithm in the fuzzy variation of sample is studied, is become by the continuous evolution of input sample data, intersection
It is different, enable the test case generated to cover more execution routes, while obtained outstanding " offspring " is added to input
During sample is lined up.
4. solving the judgement of leak analysis mechanism to extract
For software in system vulnerability Analysis on Mechanism loophole Identifying Outliers, be associated with that input data is determining, key refers to
The problems such as enabling sequential extraction procedures, the data-flow analysis of software-oriented leak analysis, path constraint analysis, the loophole towards attack traffic
The analysis methods such as Analysis on Mechanism improve leak analysis in the process to the quick analysis extractability of key element；Research is based on leakage
The utilizability determination method that hole utilizes path to construct automatically quickly judges the utilizability of loophole, improves to the quick of loophole
Using verifying and risk assessment ability, corresponding loophole risk assessment system is researched and developed.
5. using virtualization technology
Virtualization technology mainly improves the efficiency of entire leak analysis platform in terms of two.It is in physics on one side
Virtual a hundred or so a virtual nodes in node are calculated, due to this hundred or so a dummy node environment having the same, by memory, task
The resources such as memory, CPU can be reduced after schedulingization optimization, to substantially increase the speed of loophole fuzz testing.Another
A small amount of code is added after virtualization in aspect in the code of virtual opetrating system, can be from bottom layer realization to operating system
The software of upper layer operation carries out the record of the information such as path, exception.The recording mode of this information and traditional pitching pile, debugging etc.
Mode is compared, and is undoubtedly greatly improved the efficiency, to make the intelligence of software test state feedback guidance samples selection and generation
Fuzzy mutation obtains functionization, and being capable of a large amount of output loopholes.
6. establishing infix notation
By establishing the intermediate representation method towards safety analysis, research includes control and data analysis, parallelization symbol
It executes, the intelligent bug excavation technology including discovery etc. of the triggering of loophole guiding and loophole, in General Promotion analysis precision, accuracy
On the basis of, to quickly approach sensitive spot, it is accurately positioned and identifies loophole.
In an embodiment of the present invention:
(1) using safeguard detect vulnerability exploit, determine that safeguard can stop the loophole to be utilized, and by pair
After the fuzzy variation of loophole (homologous loophole), safeguard can not stop loophole to be utilized, and carry out the verifying of homologous loophole, it was demonstrated that
The shortcoming of bug excavation technology；
(2) preventing mechanism utilizes bring challenge to software vulnerability, seriously reduces vulnerability exploit for security technic system
The problem of efficiency, studies software and security system mechanism and bypasses method, improves vulnerability exploit success rate；For loophole benefit
It is confined to scatteredization technology and objectives with method, lacks Systematization method, it is difficult to the problems such as forming scale ability, research
Aims of systems system (general purpose computer, mobile intelligent terminal and industrial control system etc.) vulnerability exploit technology mechanism extracts altogether
Property technology and architectural framework feature, expand the range and adaptability of vulnerability exploit mode.It is kidnapped for control stream, memory spilling,
Object such as obscures at the particular vulnerabilities type, and the method for automatically constructing that research software vulnerability utilizes studies DEP, ASLR, ROP
The preventing mechanisms such as Mitigation bypass method, form the method for automatically constructing utilized to software vulnerability, and for specific
A variety of different utilization ways building methods of loophole；Research and development utilize tool, shape for the software vulnerability of particular vulnerability type automatically
The automatic construction ability of vulnerability exploit of pairs of particular vulnerability type, to promote software vulnerability Utilization ability and utilization efficiency.
For the technical need of the links such as loophole discovery, loophole Analysis on Mechanism, loophole risk assessment, scale is studied
The leak analysis and digging technology for changing team's collaboration, research and develop, are integrated to form leak analysis, using unified platform, realize each ring
The unification of interface and the linkage of partial function are saved, to improve software vulnerability analysis efficiency, utilization and ability of discovery.
Exploit developing intellectual resourceization mainly includes following components: input information parsing, Payload classification storage,
Payload comparison inquiry, Payload consolidation process, Payload output, loophole too development template, intelligence assembling, safety are soft
Part detection, advanced escape utilize, output forms, and main work-based logic is as shown in Figure 2.
Payload is the part data that recite information, that is, the successful data of code Inhaul operation.Usually passing
When transmission of data, in order to make data transmission it is more reliable, initial data batchwise transfer, and the head and tail of every batch of data all
In addition certain auxiliary information, such as the size of this batch of data amount, check bit etc., it is equivalent in this way in batches original
Data add some housings, these housings play marked effect, so that initial data is not easy to lose.Batch of data is plus the " outer of it
Set ", is formed transmission unit basic in transmission channel, is called data frame or data packet.
Payload data packet is to carry out the basis of loophole too development, source code data (I after code pattern identifies
Be known as parsing data), the comparison-of-pair sorting of the data packet that impends (loophole resource), the heuristic inquiry of stroke, carry out payload
Consolidation process (purpose is to allow the loophole resource having had that can not again identify that comparison is still threat to the data packet) is large quantities of
It measures the new loophole of quick output and is ready work.Data packet after reinforcing is assembled, and carries out the detection of advanced escape, together
When export vulnerability exploit tool, which is not detected by the detections of various security softwares, then processing success, can be with
Export formal tool.
Exploit developing intellectual resource beggar module receives the packed data of format in the initial stage, includes
Loophole POC data, loophole type information, loophole control flow information, simple Construct Tool, the multinomial number of exploitation demand etc.
According to the input data of meaning.
Input data can be carried out further data first and returned by the analytical algorithm of Exploit developing intellectual resource beggar's module
Receive parsing, to facilitate the next work of entire submodule, information parses final presentation model can be according to next work
It is specifically designed customization, this relatively large important work simplification exploitation loophole is facilitated to work at a series of atom.
In an alternative embodiment of the invention:
Intelligent bug excavation method based on machine learning and deep learning the following steps are included:
(1) it as shown in figure 3, using malicious software code file, builds virtual environment and runs logical malicious code, and obtain final
Malicious file MD5, analysis malicious code origin cause of formation movement verifying
(2) according to malicious code feature, the detection of homologous loophole, batch output loophole are carried out.
As shown in Fig. 2, Exploit developing intellectual resourceization mainly includes following components: the parsing of input information, Payload
Classification storage, Payload comparison inquiry, Payload consolidation process, Payload output, loophole too development template, smart group
Dress, security software detection, advanced escape are utilized, are exported, and form batch output.
Finally it is noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations.To the greatest extent
Present invention has been described in detail with reference to the aforementioned embodiments for pipe, those skilled in the art should understand that: it is still
It is possible to modify the technical solutions described in the foregoing embodiments, or part of technical characteristic is equally replaced
It changes；And these are modified or replaceed, the essence for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution
Mind and range.
Claims (3)
1. a kind of bug excavation method based on machine learning and deep learning, which is characterized in that the bug excavation method packet
Include following steps:
Step 1: automation code pattern identification is carried out to source code data；
Step 2: determining source code data type according to identifying；
Step 3: being associated analysis and heuristic search；
Step 4: homologous threat problem of the same clan is found out from code vulnerabilities library；
Step 5: implementing attack, and attack effect returns, if unsuccessful return step 3 is attacked, if success attack executes step
Rapid 6；
Step 6: vulnerability exploit is presented, and general strike scheme is exported to code vulnerabilities library.
2. the bug excavation method according to claim 1 based on machine learning and deep learning, it is characterised in that: described
The association analysis of step 3 and heuristic search include testing from the mode of writing, frame structure, module resource and with the multiple dimensions of source code
Demonstrate,prove threat problem.
3. the bug excavation method according to claim 2 based on machine learning and deep learning, it is characterised in that: described
It includes the dominant and recessive character for excavating loophole that the vulnerability exploit of step 6, which is presented,.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910342954.3A CN110110525A (en) | 2019-04-26 | 2019-04-26 | A kind of bug excavation method based on machine learning and deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910342954.3A CN110110525A (en) | 2019-04-26 | 2019-04-26 | A kind of bug excavation method based on machine learning and deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110110525A true CN110110525A (en) | 2019-08-09 |
Family
ID=67486703
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910342954.3A Pending CN110110525A (en) | 2019-04-26 | 2019-04-26 | A kind of bug excavation method based on machine learning and deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110110525A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110493226A (en) * | 2019-08-20 | 2019-11-22 | 北京大学 | It is a kind of to captured memory destroy loophole attack traffic carry out vulnerability exploit generation method and system |
| 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 |
| CN112257077A (en) * | 2020-11-11 | 2021-01-22 | 福建奇点时空数字科技有限公司 | Automatic vulnerability mining method based on deep learning |
| CN113162892A (en) * | 2020-01-23 | 2021-07-23 | 北京华顺信安科技有限公司 | POC verification environment rapid generation method, readable medium and equipment |
| 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 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108347430A (en) * | 2018-01-05 | 2018-07-31 | 国网山东省电力公司济宁供电公司 | Network invasion monitoring based on deep learning and vulnerability scanning method and device |
| CN108763928A (en) * | 2018-05-03 | 2018-11-06 | 北京邮电大学 | A kind of open source software leak analysis method, apparatus and storage medium |
-
2019
- 2019-04-26 CN CN201910342954.3A patent/CN110110525A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108347430A (en) * | 2018-01-05 | 2018-07-31 | 国网山东省电力公司济宁供电公司 | Network invasion monitoring based on deep learning and vulnerability scanning method and device |
| CN108763928A (en) * | 2018-05-03 | 2018-11-06 | 北京邮电大学 | A kind of open source software leak analysis method, apparatus and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 刘鹏睿: "针对恶意JavaScript识别的降维方法", 《计算机工程与应用》 * |
| 贾蕴哲: "基于静态特征的Android恶意代码检测", 《通信技术》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110493226A (en) * | 2019-08-20 | 2019-11-22 | 北京大学 | It is a kind of to captured memory destroy loophole attack traffic carry out vulnerability exploit generation method and system |
| CN110493226B (en) * | 2019-08-20 | 2020-10-20 | 北京大学 | Method and system for generating flow vulnerability utilization aiming at memory corruption vulnerability attack |
| 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 |
| CN111026012B (en) * | 2019-11-29 | 2023-01-31 | 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 |
| CN113162892A (en) * | 2020-01-23 | 2021-07-23 | 北京华顺信安科技有限公司 | POC verification environment rapid generation method, readable medium and equipment |
| CN113162892B (en) * | 2020-01-23 | 2022-12-06 | 北京华顺信安科技有限公司 | POC verification environment rapid generation method, readable medium and equipment |
| CN112257077A (en) * | 2020-11-11 | 2021-01-22 | 福建奇点时空数字科技有限公司 | Automatic vulnerability mining method based on deep learning |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110525A (en) | A kind of bug excavation method based on machine learning and deep learning | |
| Momeni et al. | Machine learning model for smart contracts security analysis | |
| Le et al. | Deep specification mining | |
| CN110046089B (en) | Intelligent contract testing method based on path coverage sufficiency criterion | |
| CN109933991A (en) | A kind of method, apparatus of intelligence contract Hole Detection | |
| Liang et al. | Deepfuzzer: Accelerated deep greybox fuzzing | |
| CN102034042A (en) | Novel unwanted code detecting method based on characteristics of function call relationship graph | |
| CN111240991B (en) | Dynamic stain detection method and system for resisting implicit stain propagation | |
| CN115270131A (en) | Java anti-serialization vulnerability detection method and system | |
| CN116361810A (en) | Intelligent contract vulnerability detection method based on symbol execution | |
| CN115906092A (en) | Symbolic execution method for detecting intelligent contract vulnerability across contracts | |
| CN111859380A (en) | Zero false alarm detection method for Android App vulnerability | |
| CN110362485A (en) | A kind of fuzz testing method for excavating Windows core A PI loophole | |
| CN105487983A (en) | Sensitive point approximation method based on intelligent route guidance | |
| Lin et al. | A priority based path searching method for improving hybrid fuzzing | |
| Shokri et al. | Arcode: Facilitating the use of application frameworks to implement tactics and patterns | |
| Kang et al. | Scaling javascript abstract interpretation to detect and exploit node. js taint-style vulnerability | |
| CN113836009A (en) | Intelligent contract fuzzy test method and system based on reinforcement learning | |
| Aho et al. | Automated extraction of GUI models for testing | |
| Gao et al. | Deep Learning-Based Hybrid Fuzz Testing. | |
| Saumya et al. | Xstressor: Automatic generation of large-scale worst-case test inputs by inferring path conditions | |
| CN109784048A (en) | A kind of stack buffer spilling vulnerability checking method based on programme diagram | |
| CN113553593B (en) | Semantic analysis-based method and system for mining loopholes of firmware kernel of Internet of things | |
| CN111190813B (en) | Android application network behavior information extraction system and method based on automatic testing | |
| Jiang et al. | An exploitability analysis technique for binary vulnerability based on automatic exception suppression |
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: 20190809 |
|
| RJ01 | Rejection of invention patent application after publication |