CN112329579A - Small sample wireless equipment RF fingerprint identification method and device based on ACGAN-GP - Google Patents
Small sample wireless equipment RF fingerprint identification method and device based on ACGAN-GP Download PDFInfo
- Publication number
- CN112329579A CN112329579A CN202011173288.4A CN202011173288A CN112329579A CN 112329579 A CN112329579 A CN 112329579A CN 202011173288 A CN202011173288 A CN 202011173288A CN 112329579 A CN112329579 A CN 112329579A
- Authority
- CN
- China
- Prior art keywords
- radio frequency
- frequency signal
- acgan
- wireless device
- signal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000012549 training Methods 0.000 claims abstract description 66
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 9
- 238000011478 gradient descent method Methods 0.000 claims description 8
- 238000012847 principal component analysis method Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000004880 explosion Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 18
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1365—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a small sample wireless device RF fingerprint identification method, medium, device and device based on ACGAN-GP, wherein the method comprises the following steps: acquiring a radio frequency signal of wireless equipment, and preprocessing the radio frequency signal to generate a corresponding training signal; training a generation model and a discrimination model according to an ACGAN-GP recognition detection algorithm and the training signal, and determining a final discrimination model according to a training result; acquiring a radio frequency signal to be detected, and inputting the radio frequency signal to be detected into a final discrimination model so as to identify the radio frequency signal to be detected through the final discrimination model; can effectively discern wireless equipment RF fingerprint, simultaneously, need not the manual work and draw fingerprint feature, simplify the fingerprint identification flow, reduce the wireless equipment RF fingerprint identification degree of difficulty.
Description
Technical Field
The invention relates to the technical field of wireless communication, in particular to an ACGAN-GP-based small sample wireless device RF fingerprint identification method, a computer-readable storage medium, computer equipment and an ACGAN-GP-based small sample wireless device RF fingerprint identification device.
Background
Wi-Fi is ubiquitous in our lives due to the continuous development of wireless communication and Internet of things industries. The novel safety belt brings convenience to our life and brings a series of safety risks. The maturity of the 5G technology has promoted the world of everything interconnection, and a large number of products are intelligently integrated into our life in the form of the Internet of things, and smart homes, smart cities, smart medical treatment and the like gradually tend to fall to the ground from the concept for application, so that the privacy information of users is also communicated between equipment through a wireless network. Hackers can further gain control of other devices by connecting to the spatially open wireless network, stealing privacy information such as personal data of users. Therefore, effective Wi-Fi security authentication has become an important topic.
In the related technology, a discrimination classifier based on steady-state spectrum characteristics is mostly adopted, and the difference of phase attributes of demodulated data samples is used as radio frequency fingerprint characteristics for equipment identification; however, these methods require manual extraction of fingerprint features, which is cumbersome and requires a person to understand the type and features of the existing signal before extracting the fingerprint features.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the art described above. Therefore, an object of the present invention is to provide an ACGAN-GP-based small-sample wireless device RF fingerprint identification method, which can effectively identify a wireless device RF fingerprint, and meanwhile, does not need to manually extract fingerprint features, simplifies a fingerprint identification process, and reduces the difficulty of wireless device RF fingerprint identification.
A second object of the invention is to propose a computer-readable storage medium.
A third object of the invention is to propose a computer device.
The fourth purpose of the invention is to provide an ACGAN-GP-based RF fingerprint identification device for small-sample wireless equipment.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides an ACGAN-GP-based small sample wireless device RF fingerprint identification method, including the following steps: acquiring a radio frequency signal of wireless equipment, and preprocessing the radio frequency signal to generate a corresponding training signal; training a generation model and a discrimination model according to an ACGAN-GP recognition detection algorithm and the training signal, and determining a final discrimination model according to a training result; and acquiring a radio frequency signal to be detected, and inputting the radio frequency signal to be detected into a final discrimination model so as to identify the radio frequency signal to be detected through the final discrimination model.
According to the small sample wireless device RF fingerprint identification method based on ACGAN-GP, firstly, a radio frequency signal of a wireless device is obtained, and the radio frequency signal is preprocessed to generate a corresponding training signal; secondly, training a generation model and a discrimination model according to an ACGAN-GP recognition detection algorithm and the training signal, and determining a final discrimination model according to a training result; then, acquiring a radio frequency signal to be detected, and inputting the radio frequency signal to be detected into a final discrimination model so as to identify the radio frequency signal to be detected through the final discrimination model; therefore, the RF fingerprint of the wireless equipment is effectively identified, meanwhile, the fingerprint characteristics are not required to be manually extracted, the fingerprint identification process is simplified, and the RF fingerprint identification difficulty of the wireless equipment is reduced.
In addition, the small sample wireless device RF fingerprint identification method based on ACGAN-GP proposed by the above embodiment of the present invention may also have the following additional technical features:
optionally, the preprocessing the radio frequency signal includes: and determining a starting point of the radio frequency signal according to a phase method, extracting envelope information of the radio frequency signal, and reducing the signal dimension of the radio frequency signal by adopting a principal component analysis method.
Optionally, in the ACGAN-GP recognition and detection algorithm, the loss function is a hinge loss function, the optimization algorithm is a gradient descent method, and a gradient penalty is introduced to limit the gradient of the discriminant model.
Optionally, the loss function of the ACGAN-GP recognition detection algorithm is expressed by the following formula:
LS＝Ex～q[max(0,1-D(x,c)]+Ez～p[max(0,1+D(G(z,c),c))]
wherein L isSRepresenting the true and false discrimination loss, D is a discriminator, and G is a generator; q denotes the distribution of the real signal x, c is the corresponding data tag, and p denotes the generator generated signalDistribution of G (z, c); d (x, c) represents the discrimination result of the true signal, and D (G (z, c), c) represents the discrimination result of the generated signal;
Lc＝E[P(C＝c|x)]+E[P(C＝c|G(z,c))]
wherein L iscIndicating a classification loss.
Optionally, the gradient penalty of the discriminant model is expressed by the following formula:
wherein x to q, y to p,
and alpha-y (0,1) can effectively prevent gradient explosion in the training process by combining the real data and the generated data.
Alternatively, the gradient descent method is expressed by the following formula:
the gradient descent method is expressed by the following formula:
Sdw＝βSdw+(1-β)dW2
Sdb＝βSdb+(1-β)db2
wherein S isdwThe cumulative gradient of the weight W of the network, SdbAnd the method comprises the steps of representing the accumulated gradient of a network bias b, representing a gradient accumulated control parameter, W representing the updated weight value after the iteration, b representing the updated bias after the iteration, and alpha representing the updated control parameter of the current iteration gradient.
In order to achieve the above object, a second embodiment of the present invention provides a computer-readable storage medium, on which an ACGAN-GP-based small-sample wireless device RF fingerprinting program is stored, which, when executed by a processor, implements the ACGAN-GP-based small-sample wireless device RF fingerprinting method as described above.
According to the computer-readable storage medium of the embodiment of the invention, the ACGAN-GP-based small sample wireless device RF fingerprint identification program is stored, so that the processor can realize the ACGAN-GP-based small sample wireless device RF fingerprint identification method when executing the ACGAN-GP-based small sample wireless device RF fingerprint identification program, thereby realizing effective identification of the RF fingerprint of the wireless device, simultaneously, the fingerprint characteristics do not need to be extracted manually, the fingerprint identification process is simplified, and the RF fingerprint identification difficulty of the wireless device is reduced.
In order to achieve the above object, a third embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the small-sample wireless device RF fingerprint identification method based on ACGAN-GP as described above.
According to the computer equipment provided by the embodiment of the invention, the ACGAN-GP-based small sample wireless equipment RF fingerprint identification program is stored through the memory, so that the processor realizes the ACGAN-GP-based small sample wireless equipment RF fingerprint identification method when executing the ACGAN-GP-based small sample wireless equipment RF fingerprint identification program, thereby realizing effective identification of the wireless equipment RF fingerprint, simultaneously, the fingerprint characteristics do not need to be extracted manually, the fingerprint identification process is simplified, and the RF fingerprint identification difficulty of the wireless equipment is reduced.
In order to achieve the above object, a fourth aspect of the present invention provides an apparatus for small sample wireless device RF fingerprint identification based on ACGAN-GP, including: the wireless device comprises an acquisition module, a transmission module and a control module, wherein the acquisition module is used for acquiring a radio frequency signal of the wireless device and preprocessing the radio frequency signal to generate a corresponding training signal; the training module is used for training a generation model and a discrimination model according to an ACGAN-GP recognition detection algorithm and the training signal and determining a final discrimination model according to a training result; and the identification module is used for acquiring a radio frequency signal to be detected and inputting the radio frequency signal to be detected into a final discrimination model so as to identify the radio frequency signal to be detected through the final discrimination model.
According to the ACGAN-GP-based small sample wireless device RF fingerprint identification device, the acquisition module is arranged for acquiring the radio frequency signal of the wireless device and preprocessing the radio frequency signal to generate a corresponding training signal; the training module is used for training a generation model and a discrimination model according to an ACGAN-GP recognition detection algorithm and the training signal and determining a final discrimination model according to a training result; the identification module is used for acquiring a radio frequency signal to be detected and inputting the radio frequency signal to be detected into a final discrimination model so as to identify the radio frequency signal to be detected through the final discrimination model; therefore, the RF fingerprint of the wireless equipment is effectively identified, meanwhile, the fingerprint characteristics are not required to be manually extracted, the fingerprint identification process is simplified, and the RF fingerprint identification difficulty of the wireless equipment is reduced.
In addition, the apparatus for RF fingerprinting of small sample wireless devices based on ACGAN-GP proposed in the above embodiments of the present invention may also have the following additional technical features:
optionally, the preprocessing the radio frequency signal includes: and determining a starting point of the radio frequency signal according to a phase method, extracting envelope information of the radio frequency signal, and reducing the signal dimension of the radio frequency signal by adopting a principal component analysis method.
Drawings
Fig. 1 is a flowchart illustrating an ACGAN-GP based RF fingerprinting method for a small-sample wireless device according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a radio frequency signal acquisition process of a wireless device according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a process of detecting a starting point of a radio frequency signal according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating envelope information of signals with different SNR according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a signal feature distribution according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating recognition results of a final discriminant model according to an embodiment of the present invention;
fig. 7 is a comparison graph of the recognition result of the small sample wireless device RF fingerprint recognition method based on ACGAN-GP according to the embodiment of the present invention and the recognition result of different algorithms;
fig. 8 is a block diagram of an apparatus for RF fingerprinting of small-sample wireless devices based on ACGAN-GP according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In the related technology, a discrimination classifier based on steady-state spectrum characteristics is mostly adopted, and the difference of phase attributes of demodulated data samples is used as radio frequency fingerprint characteristics for equipment identification; however, these methods all require manual extraction of fingerprint features, which is tedious in process, and the manual method needs to understand the type and features of the existing signal deeply before extracting the fingerprint features; according to the small sample wireless device RF fingerprint identification method based on ACGAN-GP, firstly, a radio frequency signal of a wireless device is obtained, and the radio frequency signal is preprocessed to generate a corresponding training signal; secondly, training a generation model and a discrimination model according to an ACGAN-GP recognition detection algorithm and the training signal, and determining a final discrimination model according to a training result; then, acquiring a radio frequency signal to be detected, and inputting the radio frequency signal to be detected into a final discrimination model so as to identify the radio frequency signal to be detected through the final discrimination model; therefore, the RF fingerprint of the wireless equipment is effectively identified, meanwhile, the fingerprint characteristics are not required to be manually extracted, the fingerprint identification process is simplified, and the RF fingerprint identification difficulty of the wireless equipment is reduced.
In order to better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Fig. 1 is a schematic flowchart of an ACGAN-GP-based small sample wireless device RF fingerprint identification method according to an embodiment of the present invention, and as shown in fig. 1, the ACGAN-GP-based small sample wireless device RF fingerprint identification method includes the following steps:
s101, acquiring a radio frequency signal of the wireless device, and preprocessing the radio frequency signal to generate a corresponding training signal.
That is, as shown in fig. 2, a radio frequency signal of the wireless device is collected, and the collected radio frequency signal is preprocessed to generate a training signal suitable for training.
There are various ways to preprocess the rf signal.
In some embodiments, pre-processing the radio frequency signal comprises:
and determining a starting point of the radio frequency signal according to a phase method, extracting envelope information of the radio frequency signal, and reducing the signal dimension of the radio frequency signal by adopting a principal component analysis method.
As an example, as shown in fig. 3, fig. 3 is a schematic diagram of a process of detecting a starting point of a radio frequency signal according to an embodiment of the present invention; FIG. 4 is a diagram illustrating envelope information of signals with different SNR according to an embodiment of the present invention; fig. 5 is a schematic diagram of signal characteristic distribution according to an embodiment of the invention.
S102, training a generation model and a discrimination model according to the ACGAN-GP recognition detection algorithm and the training signal, and determining a final discrimination model according to a training result.
In other words, according to the ACGAN-GP recognition detection algorithm, training of the generation model and the discrimination model is performed by using the acquired training signals, and the final discrimination model is determined according to the training result. The generation model is used for generating a simulation signal corresponding to the training signal according to the random noise, and the simulation signal and the training signal are input into the discrimination model so as to be recognized by the discrimination model; thus forming game training, and respectively training the generated model and the discrimination model; and finally, determining a final discrimination model according to the identification accuracy of the discrimination model.
In some embodiments, in the ACGAN-GP recognition detection algorithm, the loss function is a hinge loss function, the optimization algorithm is a gradient descent method, and a gradient penalty is introduced to define the gradient of the discriminant model.
As an example, the loss function of the ACGAN-GP recognition detection algorithm is expressed by the following formula:
LS＝Ex～q[max(0,1-D(x,c)]+Ez～p[max(0,1+D(G(z,c),c))]
wherein L isSRepresenting the true and false discrimination loss, D is a discriminator, and G is a generator; q represents the distribution of the real signal x, c is the corresponding data tag, and p represents the distribution of the generator generated signal G (z, c); d (x, c) represents the discrimination result of the true signal, and D (G (z, c), c) represents the discrimination result of the generated signal;
Lc＝E[P(C＝c|x)]+E[P(C＝c|G(z,c))]
wherein L iscIndicating a classification loss.
It can be understood that the hinge loss function is introduced into the loss function, which is realized by fitting the statistical distribution of the data, and has strong robustness.
As another example, the gradient descent method is expressed by the following formula:
Sdw＝βSdw+(1-β)dW2
Sdb＝βSdb+(1-β)db2
wherein S isdwThe cumulative gradient of the weight W of the network, SdbAnd the method comprises the steps of representing the accumulated gradient of a network bias b, representing a gradient accumulated control parameter, W representing the updated weight value after the iteration, b representing the updated bias after the iteration, and alpha representing the updated control parameter of the current iteration gradient.
It can be understood that the optimization algorithm adopts a gradient descent method, which is beneficial to solving the problem that the loss function has overlarge swing amplitude in the updating process so as to avoid the instability of the loss function.
As yet another example, the penalty function of the discriminant model is expressed by the following equation:
the gradient penalty of the discriminant model is expressed by the following formula:
wherein x to q, y to p,
and alpha-y (0,1) can effectively prevent gradient explosion in the training process by combining the real data and the generated data.
It can be understood that introducing a gradient penalty into the loss function can help the discriminant model to distribute its capacity more evenly among the spatial regions, finding invisible regions of the target distribution; thereby significantly improving the diversity of the generated samples. Meanwhile, by introducing gradient punishment, mode collapse can be effectively prevented, and generalization capability and convergence are improved.
S103, acquiring a radio frequency signal to be detected, inputting the radio frequency signal to be detected into the final discrimination model, and identifying the radio frequency signal to be detected through the final discrimination model.
That is, after the final discrimination model is determined, the radio frequency signal to be detected is obtained, the obtained radio frequency signal to be detected is input to the final discrimination model, the final discrimination model identifies the radio frequency signal to be detected, and an identification result is output.
To better illustrate the identification effect of the small sample wireless device RF fingerprint identification method based on ACGAN-GP proposed in the embodiment of the present invention, as shown in fig. 6, fig. 6 is a schematic diagram of the identification result of the final discriminant model according to the embodiment of the present invention; as can be seen from FIG. 6, the accuracy of the identification according to the final discrimination model is greatly improved; as shown in fig. 7, fig. 7 is a comparison graph of the identification result of the small sample wireless device RF fingerprint identification method based on ACGAN-GP according to the embodiment of the present invention and the identification result of different algorithms; therefore, under the condition of a small sample, the accuracy of the method is greatly improved compared with other algorithms.
In summary, according to the small sample wireless device RF fingerprint identification method based on ACGAN-GP of the embodiment of the present invention, first, a radio frequency signal of a wireless device is obtained, and the radio frequency signal is preprocessed to generate a corresponding training signal; secondly, training a generation model and a discrimination model according to an ACGAN-GP recognition detection algorithm and the training signal, and determining a final discrimination model according to a training result; then, acquiring a radio frequency signal to be detected, and inputting the radio frequency signal to be detected into a final discrimination model so as to identify the radio frequency signal to be detected through the final discrimination model; therefore, the RF fingerprint of the wireless equipment is effectively identified, meanwhile, the fingerprint characteristics are not required to be manually extracted, the fingerprint identification process is simplified, and the RF fingerprint identification difficulty of the wireless equipment is reduced.
In order to implement the foregoing embodiments, an embodiment of the present invention further provides a computer-readable storage medium, on which an ACGAN-GP-based small-sample wireless device RF fingerprint identification program is stored, where the ACGAN-GP-based small-sample wireless device RF fingerprint identification program, when executed by a processor, implements the ACGAN-GP-based small-sample wireless device RF fingerprint identification method as described above.
According to the computer-readable storage medium of the embodiment of the invention, the ACGAN-GP-based small sample wireless device RF fingerprint identification program is stored, so that the processor can realize the ACGAN-GP-based small sample wireless device RF fingerprint identification method when executing the ACGAN-GP-based small sample wireless device RF fingerprint identification program, thereby realizing effective identification of the RF fingerprint of the wireless device, simultaneously, the fingerprint characteristics do not need to be extracted manually, the fingerprint identification process is simplified, and the RF fingerprint identification difficulty of the wireless device is reduced.
In order to implement the foregoing embodiments, an embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method for RF fingerprinting of the small-sample wireless device based on ACGAN-GP as described above is implemented.
According to the computer equipment provided by the embodiment of the invention, the ACGAN-GP-based small sample wireless equipment RF fingerprint identification program is stored through the memory, so that the processor realizes the ACGAN-GP-based small sample wireless equipment RF fingerprint identification method when executing the ACGAN-GP-based small sample wireless equipment RF fingerprint identification program, thereby realizing effective identification of the wireless equipment RF fingerprint, simultaneously, the fingerprint characteristics do not need to be extracted manually, the fingerprint identification process is simplified, and the RF fingerprint identification difficulty of the wireless equipment is reduced.
In order to implement the foregoing embodiments, an embodiment of the present invention provides an apparatus for identifying an RF fingerprint of a small sample wireless device based on ACGAN-GP, where as shown in fig. 6, the apparatus for identifying an RF fingerprint of a small sample wireless device based on ACGAN-GP includes: acquisition module 10, training module 20, and recognition module 30.
The acquisition module 10 is configured to acquire a radio frequency signal of the wireless device, and preprocess the radio frequency signal to generate a corresponding training signal;
the training module 20 is used for training a generation model and a discrimination model according to the ACGAN-GP recognition detection algorithm and the training signal, and determining a final discrimination model according to a training result;
the identification module 30 is configured to obtain a radio frequency signal to be detected, and input the radio frequency signal to be detected into the final discrimination model, so as to identify the radio frequency signal to be detected through the final discrimination model.
In some embodiments, pre-processing the radio frequency signal comprises: and determining a starting point of the radio frequency signal according to a phase method, extracting envelope information of the radio frequency signal, and reducing the signal dimension of the radio frequency signal by adopting a principal component analysis method.
It should be noted that the above description about the ACGAN-GP-based small sample wireless device RF fingerprint identification method in fig. 1 is also applicable to the ACGAN-GP-based small sample wireless device RF fingerprint identification apparatus, and is not repeated herein.
In summary, according to the small-sample wireless device RF fingerprint identification apparatus based on ACGAN-GP of the embodiment of the present invention, the acquisition module is configured to acquire the radio frequency signal of the wireless device, and preprocess the radio frequency signal to generate the corresponding training signal; the training module is used for training a generation model and a discrimination model according to an ACGAN-GP recognition detection algorithm and the training signal and determining a final discrimination model according to a training result; the identification module is used for acquiring a radio frequency signal to be detected and inputting the radio frequency signal to be detected into a final discrimination model so as to identify the radio frequency signal to be detected through the final discrimination model; therefore, the RF fingerprint of the wireless equipment is effectively identified, meanwhile, the fingerprint characteristics are not required to be manually extracted, the fingerprint identification process is simplified, and the RF fingerprint identification difficulty of the wireless equipment is reduced.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
In the description of the present invention, it is to be understood that the terms "first", "second" and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above should not be understood to necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A small sample wireless device RF fingerprint identification method based on ACGAN-GP is characterized by comprising the following steps:
acquiring a radio frequency signal of wireless equipment, and preprocessing the radio frequency signal to generate a corresponding training signal;
training a generation model and a discrimination model according to an ACGAN-GP recognition detection algorithm and the training signal, and determining a final discrimination model according to a training result;
and acquiring a radio frequency signal to be detected, and inputting the radio frequency signal to be detected into a final discrimination model so as to identify the radio frequency signal to be detected through the final discrimination model.
2. The ACGAN-GP based small-sample wireless device RF fingerprinting method of claim 1, wherein pre-processing the radio frequency signal comprises:
and determining a starting point of the radio frequency signal according to a phase method, extracting envelope information of the radio frequency signal, and reducing the signal dimension of the radio frequency signal by adopting a principal component analysis method.
3. The ACGAN-GP-based small sample wireless device RF fingerprint identification method as claimed in claim 1, wherein in the ACGAN-GP identification detection algorithm, the loss function is a hinge loss function, the optimization algorithm is a gradient descent method, and a gradient penalty is introduced to define the gradient of the discriminant model.
4. The ACGAN-GP based small sample wireless device RF fingerprinting method according to any of the claims 1 to 4, characterized in that the ACGAN-GP identification detection algorithm's loss function is expressed by the following formula:
LS＝Ex～q[max(0,1-D(x,c)]+Ez～p[max(0,1+D(G(z,c),c))]
wherein L isSRepresenting the true and false discrimination loss, D is a discriminator, and G is a generator; q represents the distribution of the real signal x, c is the corresponding data tag, and p represents the distribution of the generator generated signal G (z, c); d (x, c) represents the discrimination result of the true signal, and D (G (z, c), c) represents the discrimination result of the generated signal;
Lc＝E[P(C＝c|x)]+E[P(C＝c|G(z,c))]
wherein L iscIndicating a classification loss.
5. The ACGAN-GP based small sample wireless device RF fingerprinting method according to any of the claims 1-3, characterized in that the discriminating model's gradient penalty is expressed by the following formula:
wherein x to q, y to p,
and alpha-y (0,1) can effectively prevent gradient explosion in the training process by combining the real data and the generated data.
6. The ACGAN-GP-based small sample wireless device RF fingerprinting method according to claim 3, characterized in that the gradient descent method is expressed by the following formula:
Sdw＝βSdw+(1-β)dW2
Sdb＝βSdb+(1-β)db2
wherein S isdwThe cumulative gradient of the weight W of the network, SdbAnd the method comprises the steps of representing the accumulated gradient of a network bias b, representing a gradient accumulated control parameter, W representing the updated weight value after the iteration, b representing the updated bias after the iteration, and alpha representing the updated control parameter of the current iteration gradient.
7. A computer-readable storage medium, on which an ACGAN-GP-based small-sample wireless device RF fingerprinting program is stored, which, when executed by a processor, implements the ACGAN-GP-based small-sample wireless device RF fingerprinting method as claimed in any one of claims 1 to 6.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, implements the ACGAN-GP based small sample wireless device RF fingerprinting method as claimed in any of claims 1 to 6.
9. An ACGAN-GP-based small sample wireless device RF fingerprint identification device is characterized by comprising:
the wireless device comprises an acquisition module, a transmission module and a control module, wherein the acquisition module is used for acquiring a radio frequency signal of the wireless device and preprocessing the radio frequency signal to generate a corresponding training signal;
the training module is used for training a generation model and a discrimination model according to an ACGAN-GP recognition detection algorithm and the training signal and determining a final discrimination model according to a training result;
and the identification module is used for acquiring a radio frequency signal to be detected and inputting the radio frequency signal to be detected into a final discrimination model so as to identify the radio frequency signal to be detected through the final discrimination model.
10. The ACGAN-GP based small-sample wireless device RF fingerprinting apparatus of claim 9, wherein pre-processing the radio frequency signal includes:
and determining a starting point of the radio frequency signal according to a phase method, extracting envelope information of the radio frequency signal, and reducing the signal dimension of the radio frequency signal by adopting a principal component analysis method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011173288.4A CN112329579A (en) | 2020-10-28 | 2020-10-28 | Small sample wireless equipment RF fingerprint identification method and device based on ACGAN-GP |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011173288.4A CN112329579A (en) | 2020-10-28 | 2020-10-28 | Small sample wireless equipment RF fingerprint identification method and device based on ACGAN-GP |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112329579A true CN112329579A (en) | 2021-02-05 |
Family
ID=74296547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011173288.4A Pending CN112329579A (en) | 2020-10-28 | 2020-10-28 | Small sample wireless equipment RF fingerprint identification method and device based on ACGAN-GP |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112329579A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113347637A (en) * | 2021-04-19 | 2021-09-03 | 厦门大学 | Embedded wireless device based RF fingerprint identification method and device |
| CN114387627A (en) * | 2022-01-11 | 2022-04-22 | 厦门大学 | Small sample wireless device radio frequency fingerprint identification method and device based on depth measurement learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197581A (en) * | 2018-01-10 | 2018-06-22 | 厦门大学 | A kind of unmanned plane signal identification detection algorithm based on improvement AC-WGANs |
| CN109711452A (en) * | 2018-12-20 | 2019-05-03 | 四川新网银行股份有限公司 | It is a kind of based on WGAN-GP model to the uneven classification method of user behavior |
| CN109918999A (en) * | 2019-01-22 | 2019-06-21 | 西安交通大学 | Based on the mechanical equipment fault intelligent diagnosing method for generating model under a kind of Small Sample Database |
| CN110348330A (en) * | 2019-06-24 | 2019-10-18 | 电子科技大学 | Human face posture virtual view generation method based on VAE-ACGAN |
| CN110472699A (en) * | 2019-08-24 | 2019-11-19 | 福州大学 | A kind of harmful biological motion blurred picture detection method of field of electric force institute based on GAN |
| CN111652827A (en) * | 2020-04-24 | 2020-09-11 | 山东大学 | Front face synthesis method and system based on generation countermeasure network |
-
2020
- 2020-10-28 CN CN202011173288.4A patent/CN112329579A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197581A (en) * | 2018-01-10 | 2018-06-22 | 厦门大学 | A kind of unmanned plane signal identification detection algorithm based on improvement AC-WGANs |
| CN109711452A (en) * | 2018-12-20 | 2019-05-03 | 四川新网银行股份有限公司 | It is a kind of based on WGAN-GP model to the uneven classification method of user behavior |
| CN109918999A (en) * | 2019-01-22 | 2019-06-21 | 西安交通大学 | Based on the mechanical equipment fault intelligent diagnosing method for generating model under a kind of Small Sample Database |
| CN110348330A (en) * | 2019-06-24 | 2019-10-18 | 电子科技大学 | Human face posture virtual view generation method based on VAE-ACGAN |
| CN110472699A (en) * | 2019-08-24 | 2019-11-19 | 福州大学 | A kind of harmful biological motion blurred picture detection method of field of electric force institute based on GAN |
| CN111652827A (en) * | 2020-04-24 | 2020-09-11 | 山东大学 | Front face synthesis method and system based on generation countermeasure network |
Non-Patent Citations (5)
| Title |
|---|
| C.ZHAO ET AL.: "Classification of Small UAVs based on Auxiliary Classifier Wasserstein GANs", 《2018 IEEE GLOBAL COMMUNICATIONS CONFERENCE（GLOBECOM）》, pages 206 - 212 * |
| HOANG THANH-TUNG ET AL.: "Improving Generalization and Stability of Generative Adversarial Networks", 《ARXIV》, 11 February 2019 (2019-02-11), pages 1 - 18 * |
| KAVALEROV ET AL.: "cGANs with Multi-Hinge Loss", 《ARXIV》, pages 1 - 18 * |
| 张丹丹: "《基于深度神经网络技术的高分遥感图像处理及应用》", 31 August 2020, 《中国宇航出版社》, pages: 98 * |
| 钟跃崎: "《人工智能技术原理与应用》", 30 September 2020, 《东华大学出版社》, pages: 83 - 85 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113347637A (en) * | 2021-04-19 | 2021-09-03 | 厦门大学 | Embedded wireless device based RF fingerprint identification method and device |
| CN113347637B (en) * | 2021-04-19 | 2023-07-18 | 厦门大学 | Radio Frequency (RF) fingerprint identification method and device based on embedded wireless equipment |
| CN114387627A (en) * | 2022-01-11 | 2022-04-22 | 厦门大学 | Small sample wireless device radio frequency fingerprint identification method and device based on depth measurement learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105740707B (en) | The recognition methods of malicious file and device | |
| CN111444826B (en) | Video detection method, device, storage medium and computer equipment | |
| CN112699808B (en) | Dense target detection method, electronic equipment and related products | |
| CN112329579A (en) | Small sample wireless equipment RF fingerprint identification method and device based on ACGAN-GP | |
| CN112668519A (en) | Abnormal face recognition living body detection method and system based on MCCAE network and Deep SVDD network | |
| CN110741387B (en) | Face recognition method and device, storage medium and electronic equipment | |
| CN110102051B (en) | Method and device for detecting game plug-in | |
| CN107451455A (en) | Solve lock control method and Related product | |
| CN107169334B (en) | The user authen method based on straight punch motion detection for hand wearable device | |
| CN111814148A (en) | Android malicious software family clustering method based on method call graph | |
| CN103279744A (en) | Multi-scale tri-mode texture feature-based method and system for detecting counterfeit fingerprints | |
| CN114387627A (en) | Small sample wireless device radio frequency fingerprint identification method and device based on depth measurement learning | |
| CN109671055A (en) | Pulmonary nodule detection method and device | |
| CN116738278A (en) | Automatic modulation classification method based on wavelet transformation and multi-mode feature fusion | |
| CN110008987B (en) | Method and device for testing robustness of classifier, terminal and storage medium | |
| CN115577357A (en) | Android malicious software detection method based on stacking integration technology | |
| CN117095254A (en) | Open set radio frequency fingerprint identification method based on layered self-encoder | |
| CN112350790A (en) | Deep learning-based spectrum sensing detection method, device and equipment | |
| CN114745155B (en) | Network abnormal flow detection method, device and storage medium | |
| Szymkowski et al. | A novel approach to fingerprint identification using method of sectorization | |
| CN114841340A (en) | Deep forgery algorithm identification method and device, electronic equipment and storage medium | |
| CN115098864A (en) | Evaluation method and device of image recognition model, medium and electronic equipment | |
| CN112201270B (en) | Voice noise processing method and device, computer equipment and storage medium | |
| CN115035608A (en) | Living body detection method, device, equipment and system | |
| CN114626412A (en) | Multi-class target identification method and system for unattended sensor 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 |