CN109639479B - Network traffic data enhancement method and device based on generation countermeasure network - Google Patents
Network traffic data enhancement method and device based on generation countermeasure network Download PDFInfo
- Publication number
- CN109639479B CN109639479B CN201811496710.2A CN201811496710A CN109639479B CN 109639479 B CN109639479 B CN 109639479B CN 201811496710 A CN201811496710 A CN 201811496710A CN 109639479 B CN109639479 B CN 109639479B
- Authority
- CN
- China
- Prior art keywords
- data
- network
- data set
- target scene
- generator
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method and a device for enhancing network flow data based on a generation countermeasure network, wherein the method comprises the following steps: acquiring a data set of real network flow in a target scene; training a generative countermeasure network model according to the data set; and acquiring final enhanced flow data based on the trained confrontation network generation model. The embodiment of the invention can be suitable for various scenes, does not need expert experience in the aspect of flow data, adaptively realizes the enhancement of the flow data, expands the data set of network flow and improves the effect of optimizing the network performance by utilizing a machine learning method.
Description
Technical Field
The embodiment of the invention belongs to the technical field of communication networks, and particularly relates to a method and a device for enhancing network traffic data based on a generation countermeasure network.
Background
In recent years, Machine Learning (ML) with network traffic data as a training set is widely applied to traffic classification, traffic anomaly detection, and network performance optimization. To improve the effect of machine learning, a large amount of network traffic data is required.
However, it is difficult to collect effective network traffic data in reality, and the lack of traffic data affects the application effect of machine learning. Therefore, there is a need for synthesizing traffic data using a reasonably efficient network traffic data enhancement method. In the context of current communication networks, a large number of different types of services create a diversity of network traffic data, which requires a high dynamic and flexibility for the synthesis of the network traffic data. The traditional network traffic data synthesis method includes a Fractal Brown Motion (FBM), an M/G/∞ queuing Model, a Wavelet-based Model, and a multi-Fractal Wavelet Model (MWM). These conventional methods need to rely on a large amount of expert experience to build different flow data models and on different expert experiences for different flow scenarios. Due to the strong subjectivity of expert experience, a large difference exists between the flow data synthesized by the expert experience and the real flow data.
In summary, the existing network traffic data synthesis method cannot be applied to all traffic scenes, is poor in universality, relies on expert experience to establish a traffic data model, and has strong subjectivity, so that the synthesized traffic data is lack of authenticity.
Disclosure of Invention
In order to overcome the problems of poor universality and lack of authenticity of synthesized traffic data of the existing network traffic data synthesis method or at least partially solve the problems, the embodiment of the invention provides a network traffic data enhancement method and device based on generation countermeasure network.
According to a first aspect of the embodiments of the present invention, there is provided a method for enhancing network traffic data based on a generation countermeasure network, including:
acquiring a data set of real network flow in a target scene;
training a generative countermeasure network model according to the data set;
and acquiring final enhanced flow data based on the trained confrontation network generation model.
According to a second aspect of the embodiments of the present invention, there is provided a device for enhancing network traffic data based on a spanning countermeasure network, including:
the acquisition module is used for acquiring a data set of real network flow in a target scene;
the training module is used for training a generative countermeasure network model according to the data set;
and the output module is used for acquiring final enhanced flow data based on the trained confrontation network generation model.
According to a third aspect of the embodiments of the present invention, there is also provided an electronic apparatus, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor to invoke the method for enhancing network traffic data based on a generative countermeasure network provided by any of the various possible implementations of the first aspect.
According to a fourth aspect of the embodiments of the present invention, there is also provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method for enhancing network traffic data based on a generative countermeasure network provided in any one of the various possible implementations of the first aspect.
The embodiment of the invention provides a network flow data enhancement method and device based on a generated countermeasure network, the method inputs a data set of real network flow in a target scene into a generated countermeasure network model for training, and enhanced flow data generated by the countermeasure network model when convergence is achieved is used as final enhanced flow data.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic overall flow chart of a network traffic data enhancement method based on a generative countermeasure network according to an embodiment of the present invention;
fig. 2 is a schematic overall flowchart of a network traffic data enhancement method based on a generative countermeasure network according to another embodiment of the present invention;
fig. 3 is a schematic overall structure diagram of a network traffic data enhancement device based on a spanning countermeasure network according to an embodiment of the present invention;
fig. 4 is a schematic view of an overall structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In an embodiment of the present invention, a method for enhancing network traffic data based on a generative countermeasure network is provided, and fig. 1 is a schematic overall flow chart of the method for enhancing network traffic data based on a generative countermeasure network provided in an embodiment of the present invention, where the method includes: s101, acquiring a data set of real network traffic in a target scene;
the target scene is a scene in which network traffic data enhancement is required, and can be various scenes such as residential areas, school areas, business areas and the like. And taking the network traffic data directly acquired from the target scene as real network traffic data. And combining the plurality of samples of the real network traffic data to serve as a data set of the real network traffic.
S102, generating a countermeasure network model according to the data set;
the generation of confrontation networks (GANs) is a core algorithm in the field of deep learning, is widely applied to the fields of image processing, video generation and the like, benefits from the idea of zero sum game, and the principle of the GANs is that effective data enhancement is realized through the confrontation training of two neural networks. The actual network traffic data in the dataset is pre-processed, such as normalized, before the dataset is used to train the generation of the countermeasure network model. And inputting the preprocessed data set into the constructed GANS model, and training the GANS model to make the GANs model converge. The GANs model includes a generator and a discriminator. The generator is used for enhancing the random noise, and the enhanced processing result is used as intermediate enhanced flow data. The discriminator is used for distinguishing the intermediate enhanced flow data from the real flow data.
S103, acquiring final enhanced flow data based on the trained generation confrontation network model.
And taking the intermediate enhanced data traffic output by the generator after the generated antagonistic network model converges as final enhanced traffic data.
The embodiment inputs the data set of the real network traffic in the target scene to generate the confrontation network model for training, and takes the enhanced traffic data generated by the confrontation network model when convergence is achieved as the final enhanced traffic data.
On the basis of the foregoing embodiment, the step of acquiring the data set of the real network traffic in the target scene in this embodiment specifically includes: acquiring real network flow data of a preset granularity of a target scene in a preset historical time period; dividing the preset historical time period into a plurality of sub time periods, and taking real network traffic data of each preset granularity in each sub time period as a sample; and taking the set of all the samples as a data set of real network traffic in the target scene.
Specifically, the real traffic data in a target scene in a preset historical time period is collected, such as one of a residential area, a school area and a business area as the target scene. According to the preset granularity of the real flow data, such as millisecond, second, minute or hour, the real flow data of each day, each week or each month is selected as a sample, and all the real flow data samples are combined into a data set. And carrying out normalization processing on the real flow data in each sample in the target scene. In order to better train the generation of the countermeasure network to make the network converge quickly, the data set in the target scene is subjected to maximum and minimum normalization processing. For example, the duration of the preset historical time period is 44 days, the duration of each sub-time period is one day, the total real flow data per hour is taken as one granularity, the real flow data per day, that is, per hour in 24 hours is taken as one sample, and the data set of the target scene has 44 samples in total.
On the basis of the foregoing embodiment, in this embodiment, the step of generating a training of a countermeasure network model according to the data set specifically includes: enhancing random noise based on a generator in the generated countermeasure network model to obtain intermediate enhanced flow data; judging the intermediate enhanced flow data and the samples in the preprocessed data set based on a discriminator in the generated confrontation network model; and adjusting the parameters of the generator and the discriminator according to the discrimination result until the generation confrontation network model converges.
As shown in fig. 2, the generative countermeasure network mainly includes a generator and an arbiter. The generator and the arbiter are both Deep Neural Networks (DNN) structures that include an input layer, one or more hidden layers, and an output layer. And taking the preprocessed real network traffic data set as the input of a discriminator, taking the input of a generator as random noise, and taking the enhancement result of the generator on the random noise as intermediate enhancement traffic data. In the initial training stage, the enhancement capability of the generator is poor, and the enhanced flow data does not conform to the distribution of the real flow data. After the random noise passes through the generator, the output enhanced flow data and the real flow data are input into the discriminator, and the discriminator can easily discriminate the enhanced flow data and the real flow data. And adjusting parameters of the generator and the discriminator according to the discrimination result, iterating the generator based on the adjusted parameters to enhance the random noise, and discriminating the enhanced flow data and the real flow data based on the discriminator. With the continuous training, the strengthening capability of the generator is stronger, the generated middle strengthened flow data is more consistent with the distribution of the real flow data, and the discriminator is difficult to distinguish the strengthened flow data from the real flow data. When the GANS model converges, the discriminator judges that the input probability of the GANs model belongs to the real flow data and the enhanced flow data is 0.5. The final enhanced traffic data distribution output by the generator at convergence approximates the distribution of the true traffic data.
On the basis of the foregoing embodiment, in this embodiment, the step of obtaining intermediate enhanced traffic data based on the random noise enhancement processing performed by the generator in the generated countermeasure network model specifically includes: inputting random noise into an input layer of the generator; enhancing the random noise based on one or more hidden layers of the generator to obtain intermediate enhanced flow data; inputting the intermediate enhanced traffic data into the discriminator based on an output layer of the generator.
In particular, the generator includes an input layer, one or more hidden layers, and an output layer. Inputting the preprocessed real flow data into a discriminator, wherein the input of an input layer of a generator is random noise, after calculation and transmission of a hidden layer, an output layer outputs enhanced flow data and inputs the enhanced flow data into the discriminator, and the discriminator distinguishes the enhanced flow data from the real flow data. The hidden layer of the generator may be a full connection layer, such as m full connection layers, an input layer of the generator is connected to the full connection layer, the full connection layers are sequentially connected through the m full connection layers, a last full connection layer is fully connected to an output layer of the generator, and an activation function of the full connection layer is a Rectified Linear Unit (ReLU). The output layer of the generator outputs enhanced traffic data, i.e. intermediate enhanced traffic data. The output layer of the discriminator outputs the probability that its input belongs to the real traffic data and the enhanced traffic data. And taking the intermediate enhanced data traffic output by the generator after the generated antagonistic network model converges as final enhanced traffic data.
According to the common statistical characteristics of the flow data, such as mean, variance and Hurst index (Hurst exponents), the enhanced data flow and the real flow data are compared, and the effectiveness of the enhanced data flow and the enhanced adaptability of the flow data under different scenes are verified and analyzed. As shown in table 1, the mean, variance, and Hurst index of the enhanced flow data are very close to the real flow data in three different scenarios, which indicates that the enhanced flow data distribution is close to the real flow data distribution, and can be applied to various different scenarios.
TABLE 1 enhanced flow data Effect under different scenarios
In another embodiment of the present invention, a device for enhancing network traffic data based on generation of a countermeasure network is provided, and the device is used for implementing the methods in the foregoing embodiments. Therefore, the description and definition in the foregoing embodiments of the network traffic data enhancement method based on generation of the countermeasure network can be used for understanding of each execution module in the embodiments of the present invention. Fig. 3 is a schematic diagram of an overall structure of a network traffic data enhancement device based on a spanning tree network according to an embodiment of the present invention, where the device includes an obtaining module 301, a training module 302, and an output module 303; wherein:
the obtaining module 301 is configured to obtain a data set of real network traffic in a target scene;
the target scene is a scene in which network traffic data enhancement is required, and can be various scenes such as residential areas, school areas, business areas and the like. The obtaining module 301 takes the network traffic data directly obtained from the target scene as real network traffic data. And combining the plurality of samples of the real network traffic data to serve as a data set of the real network traffic.
The training module 302 is configured to train a generative countermeasure network model according to the data set;
the GANs model is a core algorithm in the field of deep learning, is widely applied to the fields of image processing, video generation and the like, benefits from the thought of zero sum games, and realizes effective data enhancement through the countermeasure training of two neural networks. The actual network traffic data in the dataset is pre-processed, such as normalized, before the dataset is used to train the generation of the countermeasure network model. The training module 302 then inputs the preprocessed data set into the constructed GANs model, and trains the GANs model to converge. The GANs model includes a generator and a discriminator. The generator is used for enhancing the random noise, and the enhanced processing result is used as intermediate enhanced flow data. The discriminator is used for distinguishing the intermediate enhanced flow data from the real flow data.
The output module 303 is configured to obtain final enhanced traffic data based on the trained generated confrontation network model.
The output module 303 takes the intermediate enhanced data traffic output by the generator after the generation of the confrontation network model convergence as final enhanced traffic data.
The embodiment inputs the data set of the real network traffic in the target scene to generate the confrontation network model for training, and takes the enhanced traffic data generated by the confrontation network model when convergence is achieved as the final enhanced traffic data.
On the basis of the foregoing embodiment, the obtaining module in this embodiment is specifically configured to: acquiring real network flow data of a preset granularity of a target scene in a preset historical time period; dividing the preset historical time period into a plurality of sub time periods, and taking real network traffic data of each preset granularity in each sub time period as a sample; and taking the set of all the samples as a data set of real network traffic in the target scene.
On the basis of the above embodiment, the present embodiment further includes a preprocessing module, configured to perform preprocessing on the data set, where the preprocessing includes maximum and minimum normalization processing.
On the basis of the above embodiment, the training module in this embodiment is specifically configured to: enhancing random noise based on a generator in the generated countermeasure network model to obtain intermediate enhanced flow data; judging the intermediate enhanced flow data and the samples in the preprocessed data set based on a discriminator in the generated confrontation network model; and adjusting the sum discriminator parameter of the generator according to the discrimination result until the generation confrontation network model converges.
On the basis of the foregoing embodiment, the training module in this embodiment is further configured to: inputting random noise into an input layer of the generator; enhancing the random noise based on one or more hidden layers of the generator to obtain intermediate enhanced flow data; inputting the intermediate enhanced traffic data into the discriminator based on an output layer of the generator.
On the basis of the above embodiments, in this embodiment, the hidden layer is a fully-connected layer, and the activation function of the fully-connected layer is a linear rectification function.
On the basis of the foregoing embodiment, the output module in this embodiment is specifically configured to: and taking the intermediate enhanced data traffic output by the generator after the generated antagonistic network model is converged as final enhanced traffic data.
The embodiment provides an electronic device, and fig. 4 is a schematic view of an overall structure of the electronic device according to the embodiment of the present invention, where the electronic device includes: at least one processor 401, at least one memory 402, and a bus 403; wherein the content of the first and second substances,
the processor 401 and the memory 402 communicate with each other via a bus 403;
the memory 402 stores program instructions executable by the processor 401, and the processor calls the program instructions to perform the methods provided by the above method embodiments, for example, the methods include: acquiring a data set of real network flow in a target scene; training a generative countermeasure network model according to the data set; and acquiring final enhanced flow data based on the trained confrontation network generation model.
The present embodiments provide a non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the methods provided by the above method embodiments, for example, including: acquiring a data set of real network flow in a target scene; training a generative countermeasure network model according to the data set; and acquiring final enhanced flow data based on the trained confrontation network generation model.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill 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 (9)
1. A network traffic data enhancement method based on a generation countermeasure network is characterized by comprising the following steps:
acquiring a data set of real network flow in a target scene; the target scene is one of a residential area, a school area and a business area;
training a generative countermeasure network model according to the data set;
acquiring final enhanced flow data based on the trained confrontation network model;
the step of acquiring the data set of the real network traffic in the target scene specifically includes:
acquiring real network flow data of a preset granularity of a target scene in a preset historical time period;
dividing the preset historical time period into a plurality of sub time periods, and taking real network traffic data of each preset granularity in each sub time period as a sample;
and taking the set of all the samples as a data set of real network traffic in the target scene.
2. The method of claim 1, wherein the step of training the generative countermeasure network model from the data set further comprises:
preprocessing the data set, the preprocessing including a maximum-minimum normalization process.
3. The method according to claim 1, characterized in that the step of generating a training of a reactive network model from said data set comprises in particular:
enhancing random noise based on a generator in the generated countermeasure network model to obtain intermediate enhanced flow data;
judging the intermediate enhanced flow data and the samples in the preprocessed data set based on a discriminator in the generated confrontation network model;
and adjusting the parameters of the generator and the discriminator according to the discrimination result until the generation confrontation network model converges.
4. The method according to claim 3, wherein the step of obtaining the intermediate enhanced traffic data based on the enhancement processing of the random noise by the generator in the generated countermeasure network model specifically includes:
inputting random noise into an input layer of the generator;
enhancing the random noise based on one or more hidden layers of the generator to obtain intermediate enhanced flow data;
inputting the intermediate enhanced traffic data into the discriminator based on an output layer of the generator.
5. The method of claim 4, wherein the hidden layer is a fully connected layer and the activation function of the fully connected layer is a linear rectification function.
6. The method according to claim 3, wherein the step of obtaining the final enhanced traffic data based on the trained generative confrontation network model specifically comprises:
and taking the intermediate enhanced traffic data output by the generator after the generated antagonistic network model is converged as final enhanced traffic data.
7. A device for enhancing network traffic data based on a spanning countermeasure network, comprising:
the acquisition module is used for acquiring a data set of real network flow in a target scene; the target scene is one of a residential area, a school area and a business area; the step of acquiring the data set of the real network traffic in the target scene specifically includes:
acquiring real network flow data of a preset granularity of a target scene in a preset historical time period;
dividing the preset historical time period into a plurality of sub time periods, and taking real network traffic data of each preset granularity in each sub time period as a sample;
taking the set of all the samples as a data set of real network traffic in the target scene;
the training module is used for training a generative countermeasure network model according to the data set;
and the output module is used for acquiring final enhanced flow data based on the trained confrontation network generation model.
8. An electronic device, comprising:
at least one processor, at least one memory, and a bus; wherein the content of the first and second substances,
the processor and the memory complete mutual communication through the bus;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 6.
9. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811496710.2A CN109639479B (en) | 2018-12-07 | 2018-12-07 | Network traffic data enhancement method and device based on generation countermeasure network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811496710.2A CN109639479B (en) | 2018-12-07 | 2018-12-07 | Network traffic data enhancement method and device based on generation countermeasure network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109639479A CN109639479A (en) | 2019-04-16 |
| CN109639479B true CN109639479B (en) | 2020-10-20 |
Family
ID=66072037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811496710.2A Active CN109639479B (en) | 2018-12-07 | 2018-12-07 | Network traffic data enhancement method and device based on generation countermeasure network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109639479B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112398674B (en) * | 2019-08-16 | 2022-08-23 | 中国移动通信集团浙江有限公司 | Method and device for generating VNFD configuration template for describing virtual network functions |
| CN110602078B (en) * | 2019-09-04 | 2022-12-20 | 南京邮电大学 | Application encryption traffic generation method and system based on generation countermeasure network |
| CN113379045B (en) * | 2020-02-25 | 2022-08-09 | 华为技术有限公司 | Data enhancement method and device |
| CN112688928A (en) * | 2020-12-18 | 2021-04-20 | 中国科学院信息工程研究所 | Network attack flow data enhancement method and system combining self-encoder and WGAN |
| CN112884121A (en) * | 2021-02-05 | 2021-06-01 | 武汉纺织大学 | Traffic identification method based on generation of confrontation deep convolutional network |
| CN112884075A (en) * | 2021-03-23 | 2021-06-01 | 北京天融信网络安全技术有限公司 | Traffic data enhancement method, traffic data classification method and related device |
| CN113158390B (en) * | 2021-04-29 | 2023-03-24 | 北京邮电大学 | Network attack traffic generation method for generating countermeasure network based on auxiliary classification |
| CN113726545B (en) * | 2021-06-23 | 2022-12-23 | 清华大学 | Network traffic generation method and device for generating countermeasure network based on knowledge enhancement |
| CN116737793A (en) * | 2023-05-29 | 2023-09-12 | 南方电网能源发展研究院有限责任公司 | Carbon emission stream generation method, model training method, device and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104796416A (en) * | 2015-04-08 | 2015-07-22 | 中国科学院信息工程研究所 | Botnet simulation method and botnet simulation system |
| CN107451619A (en) * | 2017-08-11 | 2017-12-08 | 深圳市唯特视科技有限公司 | A kind of small target detecting method that confrontation network is generated based on perception |
| CN108446667A (en) * | 2018-04-04 | 2018-08-24 | 北京航空航天大学 | Based on the facial expression recognizing method and device for generating confrontation network data enhancing |
| CN108805418A (en) * | 2018-05-22 | 2018-11-13 | 福州大学 | A kind of traffic data fill method fighting network based on production |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103023927B (en) * | 2013-01-10 | 2016-03-16 | 西南大学 | The intrusion detection method based on Non-negative Matrix Factorization under a kind of sparse expression and system |
| CN108322349B (en) * | 2018-02-11 | 2021-04-06 | 浙江工业大学 | Deep learning adversity attack defense method based on adversity type generation network |
-
2018
- 2018-12-07 CN CN201811496710.2A patent/CN109639479B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104796416A (en) * | 2015-04-08 | 2015-07-22 | 中国科学院信息工程研究所 | Botnet simulation method and botnet simulation system |
| CN107451619A (en) * | 2017-08-11 | 2017-12-08 | 深圳市唯特视科技有限公司 | A kind of small target detecting method that confrontation network is generated based on perception |
| CN108446667A (en) * | 2018-04-04 | 2018-08-24 | 北京航空航天大学 | Based on the facial expression recognizing method and device for generating confrontation network data enhancing |
| CN108805418A (en) * | 2018-05-22 | 2018-11-13 | 福州大学 | A kind of traffic data fill method fighting network based on production |
Non-Patent Citations (2)
| Title |
|---|
| 基于分形的网络流量分析及异常检测技术研究;夏正敏;《中国博士学位论文全文数据库信息科技辑》;20130415;全文 * |
| 基于条件生成式对抗网络的数据增强方法;陈文兵等;《计算机应用》;20181110;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109639479A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109639479B (en) | Network traffic data enhancement method and device based on generation countermeasure network | |
| CN108537743B (en) | Face image enhancement method based on generation countermeasure network | |
| CN114913565B (en) | Face image detection method, model training method, device and storage medium | |
| CN108629413B (en) | Neural network model training and transaction behavior risk identification method and device | |
| CN108846323A (en) | A kind of convolutional neural networks optimization method towards Underwater Targets Recognition | |
| CN108573243A (en) | A kind of comparison method of the low quality face based on depth convolutional neural networks | |
| CN113762138B (en) | Identification method, device, computer equipment and storage medium for fake face pictures | |
| CN111681154B (en) | Color image steganography distortion function design method based on generation countermeasure network | |
| CN107680077A (en) | A kind of non-reference picture quality appraisement method based on multistage Gradient Features | |
| CN114841364A (en) | Federal learning method capable of meeting personalized local differential privacy requirements | |
| CN107483473A (en) | A kind of low speed Denial of Service attack data-flow detection method of cloud environment | |
| CN110102051A (en) | The plug-in detection method and device of game | |
| CN112633234A (en) | Method, device, equipment and medium for training and applying face glasses-removing model | |
| CN114663685A (en) | Method, device and equipment for training pedestrian re-recognition model | |
| CN110633735B (en) | Progressive depth convolution network image identification method and device based on wavelet transformation | |
| CN115953317A (en) | Image enhancement method and device, electronic equipment and storage medium | |
| CN111354367B (en) | Voice processing method and device and computer storage medium | |
| CN113657272B (en) | Micro video classification method and system based on missing data completion | |
| CN110570375A (en) | image processing method, image processing device, electronic device and storage medium | |
| CN116186629B (en) | Financial customer classification and prediction method and device based on personalized federal learning | |
| CN115953821A (en) | Virtual face image generation method and device and electronic equipment | |
| CN111597847A (en) | Two-dimensional code identification method, device and equipment and readable storage medium | |
| CN113205044B (en) | Deep fake video detection method based on characterization contrast prediction learning | |
| Li et al. | Research on Image Denoising and Super‐Resolution Reconstruction Technology of Multiscale‐Fusion Images | |
| CN115311152A (en) | Image processing method, image processing apparatus, electronic device, and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |