CN113723358B

CN113723358B - Method and device for detecting countermeasure signal based on generated countermeasure network and electronic equipment

Info

Publication number: CN113723358B
Application number: CN202111080309.2A
Authority: CN
Inventors: 楼财义; 周华吉; 骆振兴; 郑仕链
Original assignee: CETC 36 Research Institute
Current assignee: CETC 36 Research Institute
Filing date: 2021-09-15
Publication date: 2024-07-09
Anticipated expiration: 2041-09-15

Abstract

The application discloses a method and a device for detecting an countermeasure signal based on a generated countermeasure network and electronic equipment. The method comprises the following steps: acquiring a signal training sample; generating a first reconstructed sample corresponding to the signal training sample by using the generated countermeasure network based on the signal training sample; classifying the signal training sample and the first reconstructed sample by using a preset classification model to obtain a classification result of the signal training sample and a classification result of the first reconstructed sample; determining an countermeasure signal detection threshold according to the classification result of the signal training sample and the classification result of the first reconstructed sample; the challenge signal is detected based on a challenge signal detection threshold. The method for detecting the countermeasure signal based on the generated countermeasure network can accurately detect the countermeasure signal, reduces misleading and loss caused by existence of the countermeasure signal in the signal demodulation process, effectively reduces risks brought by the countermeasure signal, and strengthens safety and confidentiality of the signal transmission process.

Description

Method and device for detecting countermeasure signal based on generated countermeasure network and electronic equipment

Technical Field

The present application relates to the field of signal detection technologies, and in particular, to a method and an apparatus for detecting an countermeasure signal based on a generated countermeasure network, and an electronic device.

Background

With the development of scientific progress and hardware technology, topics such as artificial intelligence and machine learning are becoming hot spots in the current discussion. In particular, deep learning models have achieved tremendous success in feature extraction of data in recent years.

Related studies have shown that fine-perturbation, antagonistic samples can be designed for known deep-learning models, such that the model is misidentified and classified, and while these counterfeit samples have no adverse effect on human judgment, they are fatal misleading for deep-learning models, often causing the deep model to produce human unpredictable results. The classification model determines the label of the QAM16 modulated signal as a label of the QAM64 modulated type as in the field of signal modulation type classification. Recently, a series of resistant attacks successfully implemented in the real world have demonstrated that this problem is a safety hazard for all deep learning-based systems. Research into anti-sample detection technology has therefore attracted increasing attention from researchers in the fields of machine learning and security, especially in deep learning, which has a good guiding effect on later applications and practices.

Although deep neural networks (Deep Neural Networks, DNN for short) perform well in terms of speech recognition, signal modulation type classification, and other complex problems, they are susceptible to well-designed perturbations. Typically, these perturbations are imperceptible to humans, but they can give the model a high confidence in the misjudgment. For example, in practical applications, a signal transmitting base station transmits radio signals to a target base station, where the signals have great application value, if the signals are intercepted maliciously and sent again after being carefully adjusted by a machine learning means (such signals are called countermeasure signals), this may pose a huge potential threat to the receiver of the signals, and it is crucial how to detect which signals are countermeasure signals.

Disclosure of Invention

Therefore, a main object of the present application is to provide a method, an apparatus and an electronic device for detecting an countermeasure signal based on a generated countermeasure network, which are used for solving the technical problem that the detection of the countermeasure signal in the prior art is not accurate enough.

According to a first aspect of the present application, there is provided a countermeasure signal detection method based on generation of a countermeasure network, including:

Acquiring a signal training sample;

generating a first reconstructed sample corresponding to the signal training sample by using the generating countermeasure network based on the signal training sample;

Classifying the signal training sample and the first reconstructed sample by using a preset classification model to obtain a classification result of the signal training sample and a classification result of the first reconstructed sample;

determining an countermeasure signal detection threshold according to the classification result of the signal training sample and the classification result of the first reconstructed sample;

and detecting the countermeasure signal according to the countermeasure signal detection threshold.

Optionally, the generating the countermeasure network is trained by:

Acquiring the signal training sample, wherein the signal training sample comprises a training data tag;

Generating a second reconstructed sample with the generator that generates an countermeasure network based on the training data tag and random noise data;

judging the signal training sample and the second reconstruction sample by utilizing a judging device in the generating countermeasure network to obtain a judging result;

And updating the parameters of the generated countermeasure network according to the judging result to obtain the trained generated countermeasure network.

Optionally, the training data tag includes a training data tag of a plurality of signal training samples, and the generating the second reconstructed sample with the generator for generating the countermeasure network based on the training data tag and random noise data includes:

initializing a plurality of random noise values corresponding to a target signal training sample for a training data tag of the target signal training sample, wherein the target signal training sample is any one of the plurality of signal training samples;

Generating a plurality of second reconstructed samples corresponding to the target signal training samples using the generator that generates an antagonism network based on a plurality of random noise values corresponding to the target signal training samples;

And determining a final second reconstruction sample corresponding to the target signal training sample according to the similarity between the target signal training sample and each second reconstruction sample.

Optionally, the classification result of the signal training sample includes predicted values of a plurality of signal training samples, the classification result of the first reconstructed sample includes predicted values of a plurality of first reconstructed samples, and determining the countermeasure signal detection threshold according to the classification result of the signal training sample and the classification result of the first reconstructed sample includes:

respectively determining the error values of the predicted value of each signal training sample and the predicted value of the corresponding first reconstruction sample to obtain a plurality of error values;

An average of the plurality of error values is determined as the challenge signal detection threshold.

Optionally, the detecting the countermeasure signal according to the countermeasure signal detection threshold includes:

acquiring a signal test sample;

Generating a third reconstructed sample from the signal test sample using the generator that generates the countermeasure network;

Classifying the signal test sample and the third reconstruction sample by using the preset classification model to obtain a classification result of the signal test sample and a classification result of the third reconstruction sample;

And detecting the countermeasure signal in the signal test sample by using the countermeasure signal detection threshold according to the classification result of the signal test sample and the classification result of the third reconstructed sample.

Optionally, the classification result of the signal test sample and the classification result of the third reconstructed sample each include a predicted value, and the detecting the challenge signal in the signal test sample according to the classification result of the signal test sample and the classification result of the third reconstructed sample using the challenge signal detection threshold includes:

Determining an error value of the predicted value of the signal test sample and the predicted value of the third reconstructed sample;

Determining that the signal test sample is an countermeasure signal if the error value is greater than the countermeasure signal detection threshold;

and determining that the signal test sample is a non-countermeasure signal if the error value is not greater than the countermeasure signal detection threshold.

According to a second aspect of the present application, there is provided an countermeasure signal detection apparatus based on generation of a countermeasure network, comprising:

The acquisition unit is used for acquiring a signal training sample;

The generation unit is used for generating a first reconstruction sample corresponding to the signal training sample by utilizing the generation countermeasure network based on the signal training sample;

the classification unit is used for classifying the signal training sample and the first reconstructed sample by using a preset classification model to obtain a classification result of the signal training sample and a classification result of the first reconstructed sample;

a determining unit, configured to determine an countermeasure signal detection threshold according to a classification result of the signal training sample and a classification result of the first reconstructed sample;

and the detection unit is used for detecting the countermeasure signal according to the countermeasure signal detection threshold.

Optionally, the classification result of the signal training samples includes predicted values of a plurality of signal training samples, and the determining unit is specifically configured to:

Optionally, the detection unit is specifically configured to:

acquiring a signal test sample;

According to a third aspect of the present application, there is provided an electronic device comprising: a processor, a memory storing computer executable instructions,

The executable instructions, when executed by the processor, implement the aforementioned method of detecting a countermeasure signal based on generating a countermeasure network.

According to a fourth aspect of the present application, there is provided a computer-readable storage medium storing one or more programs which, when executed by a processor, implement the aforementioned method of generating an countermeasure signal based on a countermeasure network.

The beneficial effects of the application are as follows: according to the method for detecting the countermeasure signal based on the generated countermeasure network, a signal training sample is acquired first; then, based on the signal training samples, generating first reconstructed samples corresponding to the signal training samples by using the generation countermeasure network; classifying the signal training sample and the first reconstructed sample by using a preset classification model to obtain a classification result of the signal training sample and a classification result of the first reconstructed sample; then determining an countermeasure signal detection threshold according to the classification result of the signal training sample and the classification result of the first reconstructed sample; and finally detecting the countermeasure signal according to the countermeasure signal detection threshold. According to the method for detecting the countermeasure signal based on the generated countermeasure network, provided by the embodiment of the application, the countermeasure signal can be accurately detected, misleading and loss caused by the existence of the countermeasure signal in the signal demodulation process are reduced, risks brought by the countermeasure signal are effectively reduced, and the safety and the confidentiality of the signal transmission process are enhanced.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:

FIG. 1 is a flow chart of a method for detecting an countermeasure signal based on generating a countermeasure network according to an embodiment of the application;

FIG. 2 is a schematic diagram of an infrastructure of a deep neural network model according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a training process for generating an countermeasure network in accordance with an embodiment of the present application;

FIG. 4 is a schematic diagram of a detecting process of an countermeasure signal according to an embodiment of the application;

FIG. 5 is a block diagram of an countermeasure signal detection apparatus based on a generated countermeasure network in an embodiment of the application;

Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein.

Fig. 1 is a flowchart of a method for detecting an countermeasure signal based on generating a countermeasure network according to an embodiment of the application, referring to fig. 1, the method for detecting an countermeasure signal based on generating a countermeasure network according to the embodiment of the application includes steps S110 to S150 as follows:

Step S110, a signal training sample is obtained.

When the embodiment of the application detects the countermeasure signal, a signal training sample is required to be acquired in advance, wherein the signal training sample refers to signal data which is marked in advance and is used for training and generating the countermeasure network, and the signal can be an electromagnetic signal.

Step S120, based on the signal training samples, generating first reconstructed samples corresponding to the signal training samples by using the generated countermeasure network.

The generation of the countermeasure network (GAN, generative Adversarial Networks) is a deep learning model, and is one of the most promising methods for unsupervised learning on complex distribution in recent years. The model is built up of at least two modules in a frame: the mutual game learning of the generator (GENERATIVE MODEL) and the arbiter (DISCRIMINATIVE MODEL) can produce quite good output, so that the method is widely applied in the aspects of enriching the sample data quantity and the like.

The aim of the embodiment of the application is to minimize the difference between the reconstructed sample and the training sample distribution by generating the reconstructed sample data of the countermeasure network, and simultaneously the discriminator can accurately discriminate the reconstructed sample and the training sample. Therefore, the embodiment of the application inputs the obtained signal training samples into the pre-trained generation countermeasure network, so that the first reconstructed samples with little difference with the signal training samples can be generated.

Step S130, classifying the signal training sample and the first reconstructed sample by using a preset classification model to obtain a classification result of the signal training sample and a classification result of the first reconstructed sample.

After the first reconstructed sample corresponding to the signal training sample is obtained, the signal training sample and the first reconstructed sample are respectively subjected to classification prediction by utilizing a classification model trained in advance, so that a classification result of the signal training sample and a classification result of the first reconstructed sample are obtained. The classification model here can be trained as follows:

Training a deep neural network model using signal training samples x= { X ₁,x₂,…,x_n } and class labels z= { Z ₁,z₂,…,z_n } of X, defining a deep neural network model function and a loss function as:

z_i＝argmax(F(x_i)),i＝1,2,…,n (1)

L_m＝-(z_ilog(max(F(x_i)))+(1-z_i)log(1-max(F(x_i)))),i＝1,2,…,n (2)

Wherein, F (-) represents the deep neural network model, F (x _i) represents the output vector of the model pair x _i, x _i represents the ith sample, z _i represents the label corresponding to the ith sample, and L _m represents the loss value between the predicted value and the true value of the deep neural network model pair sample.

The classification model can be obtained based on the infrastructure training of the deep neural network model, as shown in fig. 2, and provides an infrastructure schematic diagram of the deep neural network model in the embodiment of the application, including an input layer, a hidden layer, an output layer, and the like.

Of course, which kind of deep neural network model is specifically adopted, those skilled in the art can flexibly select according to actual requirements, and the method is not specifically limited herein.

Step S140, determining the countermeasure signal detection threshold according to the classification result of the signal training sample and the classification result of the first reconstructed sample.

Step S150, detecting the countermeasure signal according to the countermeasure signal detection threshold.

After the classification structure of the signal training sample and the classification result of the first reconstructed sample are obtained, it is necessary to compare the deviation between the classification results of the signal training sample and the corresponding first reconstructed sample, and the deviation between the classification results of the signal training sample and the corresponding first reconstructed sample should be very small for a normal signal, i.e. a non-countermeasure signal, and relatively large for a countermeasure signal.

The challenge signal detection threshold may thus be determined based on a comparison of the classification results of the signal training samples and the first reconstructed samples, which may be used as a basis for a subsequent detection of the challenge signal.

According to the method for detecting the countermeasure signal based on the generated countermeasure network, provided by the embodiment of the application, the countermeasure signal can be accurately detected, misleading and loss caused by the existence of the countermeasure signal in the signal demodulation process are reduced, risks brought by the countermeasure signal are effectively reduced, and the safety and the confidentiality of the signal transmission process are enhanced.

In one embodiment of the application, the generation of the antagonism network is trained by: acquiring a signal training sample, wherein the signal training sample comprises a training data tag; generating a second reconstructed sample with a generator that generates an countermeasure network based on the training data tag and the random noise data; judging the signal training sample and the second reconstruction sample by using a discriminator in the generated countermeasure network to obtain a judging result; and updating parameters of the generated countermeasure network according to the judging result to obtain the trained generated countermeasure network.

As shown in fig. 3, a training flow diagram of generating an countermeasure network in an embodiment of the present application is provided. When the embodiment of the application is used for training and generating the countermeasure network, the signal training sample can be acquired first, wherein the signal training sample is the same as the signal training sample of the embodiment and comprises the training sample and the corresponding training data label.

For each class of training samples, randomly initializing a plurality of random noise data, generating a second reconstruction sample corresponding to each training sample through a generator G for generating an countermeasure network, and then respectively judging each training sample and the corresponding second reconstruction sample by a discriminator D for generating the countermeasure network to obtain a judging result, and determining the generation Loss G-Loss of the generator G and the judging Loss D-Loss of the discriminator D according to the judging result.

Based on the generation Loss G-Loss of the generator G, the generator G is updated by a gradient descent method, and the formula can be expressed as follows:

Where G (-) represents the model parameters of the generator, θ _g, and r _i ^(j) is the j-th random noise value of the i-th sample.

Based on the discrimination Loss D-Loss of the discriminator D, updating the discriminator D by gradient ascent, and the formula can be expressed as follows:

Where D (-) is the arbiter, θ _d represents the model parameters of the arbiter, x _i represents the ith sample, and r _i ^(j) is the jth random noise value of the ith sample.

Through the iterative training of the process, the generated countermeasure network with better output effect is finally obtained.

In one embodiment of the application, the training data tag comprises a training data tag of a plurality of signal training samples, and generating the second reconstructed sample with the generator that generates the challenge network based on the training data tag and the random noise data comprises: initializing a plurality of random noise values corresponding to a target signal training sample for a training data tag of the target signal training sample, wherein the target signal training sample is any one of the plurality of signal training samples; generating a plurality of second reconstructed samples corresponding to the target signal training samples using a generator that generates an antagonism network based on the plurality of random noise values corresponding to the target signal training samples; and determining a final second reconstruction sample corresponding to the target signal training sample according to the similarity between the target signal training sample and each second reconstruction sample.

In actual training, the signal training samples include a plurality of signal training samples and corresponding training data labels, when generating the second reconstructed samples by using the generator for generating the countermeasure network based on the training data labels and the random noise data, m random values r _i ⁽¹⁾,…,r_i ^(m) can be initialized randomly for each target signal training sample, and then a plurality of second reconstructed samples corresponding to the target signal training samples are generated by using the generator for generating the countermeasure network, and one reconstructed sample closest to the original signal training sample x _i is selected as the second reconstructed sample of the target signal training sample. Specifically, the similarity between samples can be measured by the distance d _i between samples, and the similarity calculation formula is as follows:

Where x _i represents the ith training sample, r _i ^(j) represents the jth sample generated for the x _i tag, and d _i represents the similarity between the two samples.

In one embodiment of the present application, the classification result of the signal training sample includes a plurality of predicted values of the signal training sample, the classification result of the first reconstructed sample includes a plurality of predicted values of the first reconstructed sample, and determining the challenge signal detection threshold based on the classification result of the signal training sample and the classification result of the first reconstructed sample includes: respectively determining the error values of the predicted value of each signal training sample and the predicted value of the corresponding first reconstruction sample to obtain a plurality of error values; an average of the plurality of error values is determined as an countermeasure signal detection threshold.

The classification result of the signal training samples obtained by the embodiment of the application comprises the predicted values of a plurality of signal training samples, the classification result of the first reconstructed samples comprises the predicted values of a plurality of first reconstructed samples, and when the countermeasure signal detection threshold is determined, the classification result can be obtained by the following steps:

Wherein T represents the challenge signal detection threshold, F (r _i ^(j)) represents the predicted value of the preset classification model for the first reconstructed sample r _i ^(j), and F (x _i) represents the predicted value of the model for the signal training sample x _i.

According to the embodiment of the application, the absolute error values between the predicted values of the plurality of signal training samples and the predicted values of the corresponding first reconstructed samples are averaged to serve as the standard for detecting the countermeasure signals subsequently, so that the accuracy of detecting the countermeasure signals can be further improved.

In one embodiment of the present application, detecting an countermeasure signal from a countermeasure signal detection threshold includes: acquiring a signal test sample; generating a third reconstructed sample from the signal test sample using a generator that generates an countermeasure network; classifying the signal test sample and the third reconstructed sample by using a preset classification model to obtain a classification result of the signal test sample and a classification result of the third reconstructed sample; and detecting the countermeasure signal in the signal test sample by using the countermeasure signal detection threshold according to the classification result of the signal test sample and the classification result of the third reconstruction sample.

As shown in fig. 4, a schematic diagram of an antagonistic signal detection flow in an embodiment of the application is provided. When the countermeasure signal detection threshold is used for detecting the countermeasure signal, the embodiment of the application can firstly obtain the signal test sample X _t＝{x_t1,x_t2,…,x_tn, then generate the third reconstructed sample R _t＝{r_t1,r_t2,…,r_tn corresponding to the signal test sample by using the generator for generating the countermeasure network trained by the embodiment, and then respectively carry out classification detection on the signal test sample and the third reconstructed sample by using the preset classification model, thereby obtaining the classification result of the signal test sample and the classification result of the third reconstructed sample.

By comparing the error between the classification result of the signal test sample and the classification result of the third reconstructed sample, it is detected whether the signal test sample is an countermeasure signal using the countermeasure signal detection threshold determined in the foregoing embodiment.

In one embodiment of the present application, the classification result of the signal test sample and the classification result of the third reconstructed sample each include a predicted value, and detecting the challenge signal in the signal test sample using the challenge signal detection threshold according to the classification result of the signal test sample and the classification result of the third reconstructed sample includes: determining an error value of the predicted value of the signal test sample and the predicted value of the third reconstructed sample; determining that the signal test sample is an countermeasure signal if the error value is greater than the countermeasure signal detection threshold; and determining that the signal test sample is a non-countermeasure signal if the error value is not greater than the countermeasure signal detection threshold.

The classification result of the signal test sample and the classification result of the third reconstructed sample in the embodiment of the present application also both include predicted values, and when detecting the countermeasure signal, the absolute error value E between the predicted value of the signal test sample and the predicted value of the third reconstructed sample may be calculated by:

E＝|max(F(x_ti))-max(F(r_ti))|,i＝1,2,…,n (7)

Wherein E represents an absolute error, F (r _ti) represents a predicted value of the preset classification model pair generated data r _ti, and F (x _ti) represents a predicted value of the model pair x _ti.

After the absolute error value E between the predicted value of the signal test sample and the predicted value of the third reconstructed sample is calculated, the absolute error value E may be compared with the challenge signal detection threshold T, if the absolute error value E is greater than the challenge signal detection threshold T, it is indicated that the class deviation between the signal test sample and its reconstructed sample is greater, and thus the signal test sample may be determined to be a challenge signal, whereas if the absolute error value E is not greater than the challenge signal detection threshold T, it is indicated that the class deviation between the signal test sample and its reconstructed sample is very small, and thus it may be determined that the signal test sample is not a challenge signal, i.e., a normal signal.

To further illustrate the training method and training effect of the present application for generating an countermeasure network, the signal training samples of the present application may specifically include 12 sub-categories of phase shift keying modulation, frequency shift keying modulation, quadrature amplitude modulation, pulse amplitude modulation: BPSK, QPSK, 8PSK, OQPSK, 2FSK, 4FSK, 8FSK, 16QAM, 32QAM, 64QAM, 4PAM, and 8PAM. The original signal data is randomly generated to ensure equal probability of transmitting bits. The pulse shaping filter uses a raised cosine filter and roll coefficients to extract a random value in the range of 0.2,0.7. The phase offset is randomly selected within the range [ -pi, pi ], and the normalized carrier frequency offset is randomly selected within the range [ -0.1,0.1 ]. The signal-to-noise ratio for each modulation class is evenly distributed from-20 dB to 30dB. Each data sample is an IQ signal comprising 64 symbols, the number of samples per symbol being 8, and thus the number of samples per sample being 512. The training set and the testing set are 312,000 and 156,000 respectively, and the sample size of each type of modulation signal is the same.

Obtaining an countermeasure sample based on a gradient attack method, obtaining a final countermeasure sample detection result by using the method, and finally using an ACC (Accuracy) index as a basis for judging the training effect.

Table 1 shows ACC indexes of an embodiment of the present application based on a Method for detecting an countermeasure signal by generating a countermeasure network, which adopts Alexnet network architecture and FGSM attack algorithm (FAST GRADIENT SIGN Method, rapid gradient notation). As can be seen from table 1, the accuracy of the method for detecting the countermeasure signal based on generating the countermeasure network according to the embodiment of the application can reach 88.68%, so that the countermeasure sample can be effectively detected.

TABLE 1

Model	Attack	ACC
			Alexnet	FGSM	88.68％

Table 2 shows the comparison of ACC indexes based on the local intrinsic dimension method (Local Intrinsic Dimensionality, abbreviated as LID) of the method for detecting the antagonism signal (Detect-GAN) and the method for detecting the uncertainty of bayesian (Bayesian Uncertainty, abbreviated as BUE), the method for detecting the kernel density (KERNEL DENSITY Estimation, abbreviated as KDE) according to the embodiment of the present application.

TABLE 2

Method	Detect-GAN	LID	KDE	BUE
					ACC	88.68％	87.20％	61.31％	54.08％

As can be seen from tables 1 and 2, the method for detecting an countermeasure signal based on generating a countermeasure network of the present application has a better detection effect than the existing detection method.

The method belongs to the same technical concept as the method for detecting the countermeasure signal based on the generated countermeasure network, and the embodiment of the application also provides a device for detecting the countermeasure signal based on the generated countermeasure network. Fig. 5 shows a block diagram of a countermeasure signal detection apparatus based on generating a countermeasure network in an embodiment of the application, referring to fig. 5, a countermeasure signal detection apparatus 500 based on generating a countermeasure network includes: an acquisition unit 510, a generation unit 520, a classification unit 530, a determination unit 540, and a detection unit 550. Wherein,

An obtaining unit 510, configured to obtain a signal training sample;

A generating unit 520, configured to generate a first reconstructed sample corresponding to the signal training sample by using the generated antagonism network based on the signal training sample;

the classifying unit 530 is configured to classify the signal training sample and the first reconstructed sample by using a preset classifying model, so as to obtain a classification result of the signal training sample and a classification result of the first reconstructed sample;

a determining unit 540, configured to determine an countermeasure signal detection threshold according to the classification result of the signal training sample and the classification result of the first reconstructed sample;

and a detection unit 550 for detecting the countermeasure signal according to the countermeasure signal detection threshold.

In one embodiment of the present application, the training data tag comprises a plurality of training data tags of signal training samples, and the generated countermeasure network is trained by: initializing a plurality of random noise values corresponding to a target signal training sample for a training data tag of the target signal training sample, wherein the target signal training sample is any one of the plurality of signal training samples; generating a plurality of second reconstructed samples corresponding to the target signal training samples using a generator that generates an antagonism network based on the plurality of random noise values corresponding to the target signal training samples; and determining a final second reconstruction sample corresponding to the target signal training sample according to the similarity between the target signal training sample and each second reconstruction sample.

In one embodiment of the present application, the classification result of the signal training samples includes predicted values of a plurality of signal training samples, and the determining unit 540 is specifically configured to: respectively determining the error values of the predicted value of each signal training sample and the predicted value of the corresponding first reconstruction sample to obtain a plurality of error values; an average of the plurality of error values is determined as an countermeasure signal detection threshold.

In one embodiment of the present application, the detection unit 550 is specifically configured to: acquiring a signal test sample; generating a third reconstructed sample from the signal test sample using a generator that generates an countermeasure network; classifying the signal test sample and the third reconstructed sample by using a preset classification model to obtain a classification result of the signal test sample and a classification result of the third reconstructed sample; and detecting the countermeasure signal in the signal test sample by using the countermeasure signal detection threshold according to the classification result of the signal test sample and the classification result of the third reconstruction sample.

In one embodiment of the present application, the classification result of the signal test sample and the classification result of the third reconstructed sample each include a predicted value, and the detection unit 550 is specifically configured to: determining an error value of the predicted value of the signal test sample and the predicted value of the third reconstructed sample; determining that the signal test sample is an countermeasure signal if the error value is greater than the countermeasure signal detection threshold; and determining that the signal test sample is a non-countermeasure signal if the error value is not greater than the countermeasure signal detection threshold.

It should be noted that:

Fig. 6 illustrates a schematic structure of an electronic device. Referring to fig. 6, at a hardware level, the electronic device includes a memory and a processor, and optionally includes an interface module, a communication module, and the like. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory, and the like. Of course, the electronic device may also include hardware required for other services.

The processor, interface module, communication module, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (PERIPHERAL COMPONENT INTERCONNECT, peripheral component interconnect standard) bus, or an EISA (Extended Industry Standard Architecture ) bus, etc. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 6, but not only one bus or type of bus.

And a memory for storing computer executable instructions. The memory provides computer-executable instructions to the processor via the internal bus.

A processor executing computer executable instructions stored in the memory and specifically configured to perform the following operations:

Acquiring a signal training sample;

Generating a first reconstructed sample corresponding to the signal training sample by using the generated countermeasure network based on the signal training sample;

The challenge signal is detected based on a challenge signal detection threshold.

The functions performed by the countermeasure signal detection apparatus based on generating the countermeasure network as disclosed in the embodiment of fig. 5 of the present application described above may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

The electronic device may further execute the steps executed by the method for detecting an countermeasure signal based on generating the countermeasure network in fig. 1, and implement the functions of the embodiment shown in fig. 1 of the method for detecting an countermeasure signal based on generating the countermeasure network, which are not described herein.

The embodiment of the present application also proposes a computer-readable storage medium storing one or more programs that, when executed by a processor, implement the aforementioned method for detecting a countermeasure signal based on generating a countermeasure network, and is specifically configured to perform:

Acquiring a signal training sample;

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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) containing computer-usable program code.

The present application is described in terms of flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims

1. A countermeasure signal detection method based on generation of a countermeasure network, comprising:

Acquiring a signal training sample;

detecting an countermeasure signal according to the countermeasure signal detection threshold;

The generated countermeasure network is trained by the following steps:

updating parameters of the generated countermeasure network according to the discrimination result to obtain a trained generated countermeasure network;

The training data tag comprises a training data tag of a plurality of signal training samples, and the generating a second reconstructed sample with the generator for generating an countermeasure network based on the training data tag and random noise data comprises:

2. The method of claim 1, wherein the classification result of the signal training samples comprises a plurality of predicted values of the signal training samples, the classification result of the first reconstructed sample comprises a plurality of predicted values of the first reconstructed sample, and wherein determining the challenge signal detection threshold based on the classification result of the signal training sample and the classification result of the first reconstructed sample comprises:

3. The method of claim 1, wherein the detecting an countermeasure signal according to the countermeasure signal detection threshold comprises:

acquiring a signal test sample;

4. The method of claim 3, wherein the classification of the signal test sample and the classification of the third reconstructed sample each comprise a predicted value, and wherein detecting the challenge signal in the signal test sample using the challenge signal detection threshold based on the classification of the signal test sample and the classification of the third reconstructed sample comprises:

5. An countermeasure signal detection apparatus based on a generated countermeasure network, comprising:

The acquisition unit is used for acquiring a signal training sample;

A detection unit configured to detect an countermeasure signal according to the countermeasure signal detection threshold;

The generated countermeasure network is trained by the following steps:

the training data label comprises a plurality of training data labels of signal training samples, and the generated countermeasure network is trained by the following modes:

6. The apparatus according to claim 5, wherein the classification result of the signal training samples comprises predicted values of a plurality of signal training samples, and the determining unit is specifically configured to:

7. The device according to claim 5, wherein the detection unit is specifically configured to:

acquiring a signal test sample;

8. An electronic device, comprising: a processor, a memory storing computer executable instructions,

The executable instructions, when executed by the processor, implement the method of generating an countermeasure signal detection based on a countermeasure network of any of claims 1 to 4.