Block chain data hidden transmission detection method and system based on multi-feature fusion

Abstract

The invention provides a block chain data hidden transmission detection method and system based on multi-feature fusion, and relates to the technical field of block chains, and the method comprises the steps: constructing a block chain data hidden transmission detection model; the block chain data hidden transmission detection model comprises a text feature detection model, an association feature detection model and a fusion feature detection model; the text feature detection model performs text feature classification on the input block chain data to obtain a text feature classification result; the associated feature detection model performs associated feature classification on the input block chain data to obtain an associated feature classification result; carrying out weighted fusion on the fusion feature detection model to obtain a final classification result; training the block chain data hidden transmission detection model to obtain a trained block chain data hidden transmission detection model; and carrying out block chain data hidden transmission detection based on the trained block chain data hidden transmission detection model. According to the invention, the accuracy of block chain data hidden transmission detection is improved.

Description

Technical Field

[0001] The present invention relates to the field of blockchain technology, and in particular to a blockchain data covert transmission detection method and system based on multi-feature fusion. Background Art

[0002] The rapid development and application of computer networks have brought convenience and speed to data transmission, but there are also more and more cases of using the network to build hidden data transmission channels for illegal and criminal activities. By hiding special data in normal network traffic and using obfuscation, encryption and other methods to improve concealment, such data covert transmission behavior can bypass traditional network traffic detection algorithms and achieve data covert transmission with anti-regulatory capabilities.

[0003] The data covert transmission detection method is a method for detecting data covert transmission behavior from network traffic. By collecting and counting the characteristic parameters of normal network traffic, it can be used to detect whether the characteristic values ​​in a specific traffic are abnormal, thereby identifying data covert transmission behavior. However, with the development of network technology, the proportion of encrypted data in network traffic continues to increase. The special characteristics of data covert transmission behavior are hidden in the encryption process and confused in ordinary encrypted traffic, which brings great challenges to data covert transmission detection technology.

[0004] Blockchain is a ledger technology built on a distributed network. It has the properties of data immutability, traffic flooding transmission, and user identity anonymity, making it very suitable for building data covert transmission channels. Data is embedded in the fields of blockchain transactions, and the blockchain network is used to realize data transmission, which has good anti-detection and anti-traceability capabilities. In particular, the large number of encryption parameters inherent in the blockchain transaction fields provide a variety of ciphertext carriers for data covert transmission, which is more conducive to building data covert transmission schemes that resist feature statistical detection algorithms. In order to detect blockchain-based data covert transmission schemes, researchers designed targeted detection algorithms based on blockchain transaction characteristics and constructed a variety of detection schemes using deep learning technology.

[0005] However, most existing solutions face two problems:

[0006] 1) Existing detection algorithms mainly detect special data by counting character statistical features, and cannot detect special data stored in encrypted fields. By embedding the information to be transmitted in the encrypted field, the character features of the special data will be obfuscated during the encryption process, and it is impossible to distinguish between ordinary encrypted data and encrypted data carrying hidden information from the perspective of statistical features. Especially in the blockchain scenario, the inherent multiple types of encrypted fields in blockchain transactions provide a natural shelter for the embedding of hidden information based on encryption algorithms.

[0007] 2) Existing detection algorithms only consider the statistical features of a single blockchain transaction, but ignore the correlation features between multiple blockchain transactions, making it difficult to detect new blockchain data hidden transmission schemes. Summary of the invention

[0008] The purpose of the present invention is to provide a blockchain data covert transmission detection method and system based on multi-feature fusion, so as to improve the accuracy of blockchain data covert transmission detection.

[0009] A blockchain data covert transmission detection method based on multi-feature fusion, comprising:

[0010] Constructing a blockchain data hidden transmission detection model; the blockchain data hidden transmission detection model includes a text feature detection model, an association feature detection model and a fusion feature detection model;

[0011] The text feature detection model includes a first input layer, a first embedding layer, a first convolutional layer, a second convolutional layer, a pooling layer and a fully connected layer;

[0012] The first input layer extracts the input blockchain data to obtain a text feature sequence;

[0013] The first embedding layer performs numerical processing on the text feature sequence to obtain a first numerical index sequence, and converts the first numerical index sequence into a vector space representation to obtain a first embedding matrix;

[0014] The first convolutional layer includes a first convolutional unit, a second convolutional unit and a third convolutional unit;

[0015] The first convolution unit performs convolution processing on the first embedding matrix based on a first convolution kernel to obtain a first convolution feature map; the second convolution unit performs convolution processing on the first embedding matrix based on a second convolution kernel to obtain a second convolution feature map; the third convolution unit performs convolution processing on the first embedding matrix based on a third convolution kernel to obtain a third convolution feature map;

[0016] The second convolutional layer includes a fourth convolutional unit, a fifth convolutional unit and a sixth convolutional unit;

[0017] The fourth convolution unit performs convolution processing on the first convolution feature map based on the fourth convolution kernel to obtain a fourth convolution feature map; the fifth convolution unit performs convolution processing on the second convolution feature map based on the fifth convolution kernel to obtain a fifth convolution feature map; the sixth convolution unit performs convolution processing on the third convolution feature map based on the sixth convolution kernel to obtain a sixth convolution feature map;

[0018] The pooling layer includes a first pooling unit, a second pooling unit and a third pooling unit;

[0019] The first pooling unit performs maximum pooling processing on the fourth convolution feature map to obtain a first pooling feature map; the second pooling unit performs maximum pooling processing on the fifth convolution feature map to obtain a second pooling feature map; the third pooling unit performs maximum pooling processing on the sixth convolution feature map to obtain a third pooling feature map;

[0020] The fully connected layer filters and cascades the first pooled feature map, the second pooled feature map, and the third pooled feature map to obtain a first feature vector, and classifies the first feature vector based on an activation function to obtain a text feature classification result;

[0021] The associated feature detection model is used to perform associated feature classification on the input blockchain data to obtain an associated feature classification result;

[0022] The fusion feature detection model performs weighted fusion on the text feature classification result and the associated feature classification result to obtain a final classification result;

[0023] Training the blockchain data covert transmission detection model to obtain a trained blockchain data covert transmission detection model;

[0024] Blockchain data hidden transmission detection is performed based on the trained blockchain data hidden transmission detection model.

[0025] Optionally, the associated feature detection model includes a second input layer, a second embedding layer, a recurrent layer and an output layer;

[0026] The second input layer extracts the input blockchain data to obtain a correlation feature sequence;

[0027] The second embedding layer performs numerical processing on the associated feature sequence to obtain a second numerical index sequence, and converts the second numerical index sequence into a vector space representation to obtain a second embedding matrix;

[0028] The recurrent layer performs feature extraction on the second embedding matrix to obtain a plurality of associated feature graphs;

[0029] The output layer performs cascade processing on each of the associated feature maps to obtain a second feature vector, and classifies the second feature vector based on an activation function to obtain the associated feature classification result.

[0030] Optionally, the circulation layer adopts a bidirectional long short-term memory network.

[0031] Optionally, the size of the first convolution kernel is 3, the size of the second convolution kernel is 4, the size of the third convolution kernel is 5, the size of the fourth convolution kernel is 6, the size of the fifth convolution kernel is 7, and the size of the sixth convolution kernel is 8.

[0032] Optionally, the fusion feature detection model expression is:

[0033]

[0034] Where: represents the final classification result, f1(X text ) represents the text feature classification result, f2(X related ) represents the classification result of the associated features, f fusion Represents the weighted fusion function.

[0035] Optionally, during the training process, the loss function is a cross entropy loss function.

[0036] Optionally, the cross entropy loss function expression is:

[0037] L=-(ylog(p)+(1-y)log(1-p));

[0038] Where: L is the loss value, y is the true label, and p is the probability that the blockchain data covert transmission detection model predicts the positive class.

[0039] The present invention also provides a blockchain data concealed transmission detection system based on multi-feature fusion, which includes:

[0040] A model building module is used to build a blockchain data hidden transmission detection model; the blockchain data hidden transmission detection model includes a text feature detection model, an associated feature detection model and a fusion feature detection model;

[0041] The text feature detection model includes a first input layer, a first embedding layer, a first convolutional layer, a second convolutional layer, a pooling layer and a fully connected layer;

[0042] The first input layer extracts the input blockchain data to obtain a text feature sequence;

[0043] The first embedding layer performs numerical processing on the text feature sequence to obtain a first numerical index sequence, and converts the first numerical index sequence into a vector space representation to obtain a first embedding matrix;

[0044] The first convolutional layer includes a first convolutional unit, a second convolutional unit and a third convolutional unit;

[0045] The first convolution unit performs convolution processing on the first embedding matrix based on a first convolution kernel to obtain a first convolution feature map; the second convolution unit performs convolution processing on the first embedding matrix based on a second convolution kernel to obtain a second convolution feature map; the third convolution unit performs convolution processing on the first embedding matrix based on a third convolution kernel to obtain a third convolution feature map;

[0046] The second convolutional layer includes a fourth convolutional unit, a fifth convolutional unit and a sixth convolutional unit;

[0047] The fourth convolution unit performs convolution processing on the first convolution feature map based on the fourth convolution kernel to obtain a fourth convolution feature map; the fifth convolution unit performs convolution processing on the second convolution feature map based on the fifth convolution kernel to obtain a fifth convolution feature map; the sixth convolution unit performs convolution processing on the third convolution feature map based on the sixth convolution kernel to obtain a sixth convolution feature map;

[0048] The pooling layer includes a first pooling unit, a second pooling unit and a third pooling unit;

[0049] The first pooling unit performs maximum pooling processing on the fourth convolution feature map to obtain a first pooling feature map; the second pooling unit performs maximum pooling processing on the fifth convolution feature map to obtain a second pooling feature map; the third pooling unit performs maximum pooling processing on the sixth convolution feature map to obtain a third pooling feature map;

[0050] The fully connected layer filters and cascades the first pooled feature map, the second pooled feature map, and the third pooled feature map to obtain a first feature vector, and classifies the first feature vector based on an activation function to obtain a text feature classification result;

[0051] The associated feature detection model is used to perform associated feature classification on the input blockchain data to obtain an associated feature classification result;

[0052] The fusion feature detection model performs weighted fusion on the text feature classification result and the associated feature classification result to obtain a final classification result;

[0053] A model training module, used to train the blockchain data covert transmission detection model to obtain a trained blockchain data covert transmission detection model;

[0054] The detection module is used to perform blockchain data covert transmission detection based on the trained blockchain data covert transmission detection model.

[0055] The effects of the present invention are as follows:

[0056] The present invention is based on a blockchain data concealed transmission detection method based on multi-feature fusion, which combines the text feature classification results and the associated feature classification results, and can more effectively capture multiple types of features in the data and improve the detection effect of blockchain concealed transactions. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of the blockchain data concealed transmission detection method based on multi-feature fusion of the present invention;

[0058] Figure 2 It is a structural schematic diagram of the blockchain data hidden transmission detection model of the present invention. DETAILED DESCRIPTION

[0059] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0060] Figure 1 This is a flow chart of the blockchain data hidden transmission detection method based on multi-feature fusion of the present invention. Figure 1 As shown, the present invention provides a blockchain data covert transmission detection method based on multi-feature fusion, which includes:

[0061] S1, build a blockchain data hidden transmission detection model. The blockchain data hidden transmission detection model includes a text feature detection model TextCNN, a correlation feature detection model TextRNN and a fusion feature detection model.

[0062] like Figure 2 As shown, the text feature detection model includes a first input layer, a first embedding layer, a first convolutional layer, a second convolutional layer, a pooling layer, and a fully connected layer.

[0063] The first input layer extracts the input blockchain data to obtain a text feature sequence.

[0064] Specifically, the first input layer extracts the required text features from the input blockchain data. The text feature sequence S is: {total, fees, inputs.addresses, inputs.value, outputs.addresses, outputs.value, outputs.script, outputs.data_string, outputs.number, tx_size, address_repeat}. The feature set is represented as: T = t1, t2, ..., t 11 , where t i represents the i-th feature. The feature subset of text features includes 11 features in total. The actual meaning of each feature is shown in Table 1.

[0065] Table 1 Blockchain transaction text features

[0066] type feature describe Text Features total Total transaction amount Text Features fees Transaction Fees Text Features inputs.addresses Enter address Text Features inputs.value Enter amount Text Features outputs.addresses Output Address Text Features outputs.Value Output amount Text Features outputs.script Output Script Text Features outputs.data_string OP_RETURN output data Text Features outputs.number Output quantity Text Features tx_size Transaction size Text Features address_repeat Number of duplicate addresses

[0067] The first embedding layer performs numerical processing on the text feature sequence to obtain a first numerical index sequence, and converts the first numerical index sequence into a vector space representation to obtain a first embedding matrix. Specifically, the first embedding layer uses a vocabulary building technology to convert the text feature sequence into a numerical feature representation that can be understood by the model. The present invention adopts a character-level text processing method to segment a long text sequence character by character, and uses a character dictionary to map each character to a numerical index, thereby realizing the numerical conversion of text data and obtaining a first numerical index sequence.

[0068] The output dimension k=128. In order to maintain the consistency of the vector length, padding is performed on the original text sentence. The first embedding matrix is ​​an n*k matrix, where n is the number of characters in a data, the length range is 1000-1400, k is the dimension of the word vector corresponding to each character, and each row is the 128-dimensional word vector corresponding to a data. The word vector of the i-th character in a row is expressed as: Text data of length n is represented as: in, is the concatenation operator.

[0069] The first convolutional layer includes a first convolutional unit, a second convolutional unit, and a third convolutional unit. The first convolutional layer captures word order information and local patterns through local perception to extract phrase patterns and local context information.

[0070] The first convolution unit performs convolution processing on the first embedding matrix based on the first convolution kernel to obtain a first convolution feature map; the second convolution unit performs convolution processing on the first embedding matrix based on the second convolution kernel to obtain a second convolution feature map; the third convolution unit performs convolution processing on the first embedding matrix based on the third convolution kernel to obtain a third convolution feature map. Preferably, the size of the first convolution kernel is 3, the size of the second convolution kernel is 4, and the size of the third convolution kernel is 5.

[0071] Specifically, the feature map after each convolution is expressed as:

[0072] c i =f(ω·x i:i+h-1 + b);

[0073] Among them, f represents a nonlinear function, the Relu activation function is selected, b is the bias term, h refers to the convolution window size, and the convolution kernel is an h×k weight matrix.

[0074] The first convolutional feature map is expressed as:

[0075] C={c1,c2,…,c n-h+1}.

[0076] The second convolutional layer includes a fourth convolutional unit, a fifth convolutional unit, and a sixth convolutional unit.

[0077] The fourth convolution unit performs convolution processing on the first convolution feature map based on the fourth convolution kernel to obtain a fourth convolution feature map; the fifth convolution unit performs convolution processing on the second convolution feature map based on the fifth convolution kernel to obtain a fifth convolution feature map; the sixth convolution unit performs convolution processing on the third convolution feature map based on the sixth convolution kernel to obtain a sixth convolution feature map. Preferably, the size of the fourth convolution kernel is 6, the size of the fifth convolution kernel is 7, and the size of the sixth convolution kernel is 8.

[0078] The pooling layer includes a first pooling unit, a second pooling unit and a third pooling unit.

[0079] The first pooling unit performs maximum pooling on the fourth convolution feature map to obtain a first pooling feature map; the second pooling unit performs maximum pooling on the fifth convolution feature map to obtain a second pooling feature map; the third pooling unit performs maximum pooling on the sixth convolution feature map to obtain a third pooling feature map.

[0080] The fully connected layer filters and cascades the first pooling feature map, the second pooling feature map, and the third pooling feature map to obtain a first feature vector, and classifies the first feature vector based on the activation function to obtain a text feature classification result.

[0081] The correlation feature detection model is used to classify the input blockchain data by correlation features to obtain the correlation feature classification results.

[0082] Specifically, Figure 2 As shown, the associated feature detection model includes a second input layer, a second embedding layer, a recurrent layer and an output layer.

[0083] The second input layer extracts the input blockchain data to obtain the associated feature sequence. The associated feature sequence S2 is: {art_num, total_received, total_sent, final_balance, input_proportion, output_proportion}. The feature set is represented as: T = t1, t2, ..., t6, where t i The feature subset representing the i-th feature includes 6 features in total. The actual meaning of each feature is shown in Table 2.

[0084] Table 2. Blockchain transaction correlation characteristics

[0085]

[0086] The second embedding layer digitizes the associated feature sequence to obtain a second numerical index sequence, and converts the second numerical index sequence into a vector space representation to obtain a second embedding matrix. In order to handle text sequences of different lengths, padding and truncation strategies are adopted.

[0087] The recurrent layer performs feature extraction on the second embedding matrix to obtain a plurality of associated feature maps. Preferably, the recurrent layer uses a bidirectional long short-term memory network BiLSTM.

[0088] The output layer performs cascade processing on each associated feature map to obtain a second feature vector, and classifies the second feature vector based on the activation function to obtain an associated feature classification result.

[0089] The fusion feature detection model performs weighted fusion on the text feature classification results and the associated feature classification results to obtain the final classification results.

[0090] The fusion feature detection model expression is:

[0091]

[0092] Where: represents the final classification result, f1(X text ) represents the text feature classification result, f2(X related ) represents the classification result of the associated features, f fusion Preferably, the weighted fusion function is a weighted average fusion function.

[0093] S2, training the blockchain data hidden transmission detection model to obtain a trained blockchain data hidden transmission detection model.

[0094] Specifically, during the training process, the loss function uses the cross entropy loss function. The cross entropy loss function is expressed as:

[0095] L=-(ylog(p)+(1-y)log(1-p));

[0096] Where: L is the loss value, y is the true label, and p is the probability that the blockchain data covert transmission detection model predicts the positive class.

[0097] S3, performs blockchain data covert transmission detection based on the trained blockchain data covert transmission detection model.

[0098] The present invention also provides a blockchain data concealed transmission detection system based on multi-feature fusion, which includes:

[0099] The model building module is used to build a blockchain data hidden transmission detection model. The blockchain data hidden transmission detection model includes a text feature detection model, an associated feature detection model, and a fusion feature detection model.

[0100] The text feature detection model includes the first input layer, the first embedding layer, the first convolutional layer, the second convolutional layer, the pooling layer and the fully connected layer.

[0101] The first input layer extracts the input blockchain data to obtain a text feature sequence.

[0102] The first embedding layer performs numerical processing on the text feature sequence to obtain a first numerical index sequence, and converts the first numerical index sequence into a vector space representation to obtain a first embedding matrix.

[0103] The first convolutional layer includes a first convolutional unit, a second convolutional unit, and a third convolutional unit.

[0104] The first convolution unit performs convolution processing on the first embedding matrix based on the first convolution kernel to obtain a first convolution feature map; the second convolution unit performs convolution processing on the first embedding matrix based on the second convolution kernel to obtain a second convolution feature map; the third convolution unit performs convolution processing on the first embedding matrix based on the third convolution kernel to obtain a third convolution feature map.

[0105] The second convolutional layer includes a fourth convolutional unit, a fifth convolutional unit, and a sixth convolutional unit.

[0106] The fourth convolution unit performs convolution processing on the first convolution feature map based on the fourth convolution kernel to obtain a fourth convolution feature map; the fifth convolution unit performs convolution processing on the second convolution feature map based on the fifth convolution kernel to obtain a fifth convolution feature map; the sixth convolution unit performs convolution processing on the third convolution feature map based on the sixth convolution kernel to obtain a sixth convolution feature map.

[0107] The pooling layer includes a first pooling unit, a second pooling unit and a third pooling unit.

[0108] The first pooling unit performs maximum pooling on the fourth convolution feature map to obtain a first pooling feature map; the second pooling unit performs maximum pooling on the fifth convolution feature map to obtain a second pooling feature map; the third pooling unit performs maximum pooling on the sixth convolution feature map to obtain a third pooling feature map.

[0109] The fully connected layer filters and cascades the first pooling feature map, the second pooling feature map, and the third pooling feature map to obtain a first feature vector, and classifies the first feature vector based on the activation function to obtain a text feature classification result.

[0110] The correlation feature detection model is used to classify the input blockchain data by correlation features to obtain the correlation feature classification results.

[0111] The fusion feature detection model performs weighted fusion on the text feature classification results and the associated feature classification results to obtain the final classification results.

[0112] The model training module is used to train the blockchain data hidden transmission detection model to obtain a trained blockchain data hidden transmission detection model.

[0113] The detection module is used to detect the hidden transmission of blockchain data based on the trained blockchain data hidden transmission detection model.

[0114] The embodiments described above are only descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A blockchain data covert transmission detection method based on multi-feature fusion, characterized in that: It includes: Constructing a blockchain data hidden transmission detection model; the blockchain data hidden transmission detection model includes a text feature detection model, an association feature detection model and a fusion feature detection model; The text feature detection model includes a first input layer, a first embedding layer, a first convolutional layer, a second convolutional layer, a pooling layer and a fully connected layer; The first input layer extracts the input blockchain data to obtain a text feature sequence; The first embedding layer performs numerical processing on the text feature sequence to obtain a first numerical index sequence, and converts the first numerical index sequence into a vector space representation to obtain a first embedding matrix; The first convolutional layer includes a first convolutional unit, a second convolutional unit and a third convolutional unit; The first convolution unit performs convolution processing on the first embedding matrix based on a first convolution kernel to obtain a first convolution feature map; the second convolution unit performs convolution processing on the first embedding matrix based on a second convolution kernel to obtain a second convolution feature map; the third convolution unit performs convolution processing on the first embedding matrix based on a third convolution kernel to obtain a third convolution feature map; The second convolutional layer includes a fourth convolutional unit, a fifth convolutional unit and a sixth convolutional unit; The fourth convolution unit performs convolution processing on the first convolution feature map based on the fourth convolution kernel to obtain a fourth convolution feature map; the fifth convolution unit performs convolution processing on the second convolution feature map based on the fifth convolution kernel to obtain a fifth convolution feature map; the sixth convolution unit performs convolution processing on the third convolution feature map based on the sixth convolution kernel to obtain a sixth convolution feature map; The pooling layer includes a first pooling unit, a second pooling unit and a third pooling unit; The first pooling unit performs maximum pooling processing on the fourth convolution feature map to obtain a first pooling feature map; the second pooling unit performs maximum pooling processing on the fifth convolution feature map to obtain a second pooling feature map; the third pooling unit performs maximum pooling processing on the sixth convolution feature map to obtain a third pooling feature map; The fully connected layer filters and cascades the first pooled feature map, the second pooled feature map, and the third pooled feature map to obtain a first feature vector, and classifies the first feature vector based on an activation function to obtain a text feature classification result; The associated feature detection model is used to perform associated feature classification on the input blockchain data to obtain an associated feature classification result; The fusion feature detection model performs weighted fusion on the text feature classification result and the associated feature classification result to obtain a final classification result; Training the blockchain data covert transmission detection model to obtain a trained blockchain data covert transmission detection model; Blockchain data hidden transmission detection is performed based on the trained blockchain data hidden transmission detection model.

2. The blockchain data covert transmission detection method based on multi-feature fusion according to claim 1 is characterized in that: The associated feature detection model includes a second input layer, a second embedding layer, a circulation layer and an output layer; The second input layer extracts the input blockchain data to obtain a correlation feature sequence; The second embedding layer performs numerical processing on the associated feature sequence to obtain a second numerical index sequence, and converts the second numerical index sequence into a vector space representation to obtain a second embedding matrix; The recurrent layer performs feature extraction on the second embedding matrix to obtain a plurality of associated feature graphs; The output layer performs cascade processing on each of the associated feature maps to obtain a second feature vector, and classifies the second feature vector based on an activation function to obtain the associated feature classification result.

3. The blockchain data covert transmission detection method based on multi-feature fusion according to claim 2 is characterized in that: The circulation layer adopts a bidirectional long short-term memory network.

4. The blockchain data concealed transmission detection method based on multi-feature fusion according to claim 1 is characterized in that: The size of the first convolution kernel is 3, the size of the second convolution kernel is 4, the size of the third convolution kernel is 5, the size of the fourth convolution kernel is 6, the size of the fifth convolution kernel is 7, and the size of the sixth convolution kernel is 8.

5. The blockchain data concealed transmission detection method based on multi-feature fusion according to claim 1 is characterized in that: The fusion feature detection model expression is: Where: represents the final classification result, f1(X text ) represents the text feature classification result, f2(X related ) represents the classification result of the associated features, f fusion Represents the weighted fusion function.

6. The blockchain data concealed transmission detection method based on multi-feature fusion according to claim 1 is characterized in that: During the training process, the cross entropy loss function is used as the loss function.

7. The method for detecting hidden transmission of blockchain data based on multi-feature fusion according to claim 6 is characterized in that: The cross entropy loss function expression is: L=-(ylog(p)+(1-y)log(1-p)); Where: L is the loss value, y is the true label, and p is the probability that the blockchain data covert transmission detection model predicts the positive class.

8. A blockchain data hidden transmission detection system based on multi-feature fusion, characterized in that: It includes: A model building module is used to build a blockchain data hidden transmission detection model; the blockchain data hidden transmission detection model includes a text feature detection model, an associated feature detection model and a fusion feature detection model; The text feature detection model includes a first input layer, a first embedding layer, a first convolutional layer, a second convolutional layer, a pooling layer and a fully connected layer; The first input layer extracts the input blockchain data to obtain a text feature sequence; The first embedding layer performs numerical processing on the text feature sequence to obtain a first numerical index sequence, and converts the first numerical index sequence into a vector space representation to obtain a first embedding matrix; The first convolutional layer includes a first convolutional unit, a second convolutional unit and a third convolutional unit; The first convolution unit performs convolution processing on the first embedding matrix based on a first convolution kernel to obtain a first convolution feature map; the second convolution unit performs convolution processing on the first embedding matrix based on a second convolution kernel to obtain a second convolution feature map; the third convolution unit performs convolution processing on the first embedding matrix based on a third convolution kernel to obtain a third convolution feature map; The second convolutional layer includes a fourth convolutional unit, a fifth convolutional unit and a sixth convolutional unit; The fourth convolution unit performs convolution processing on the first convolution feature map based on the fourth convolution kernel to obtain a fourth convolution feature map; the fifth convolution unit performs convolution processing on the second convolution feature map based on the fifth convolution kernel to obtain a fifth convolution feature map; the sixth convolution unit performs convolution processing on the third convolution feature map based on the sixth convolution kernel to obtain a sixth convolution feature map; The pooling layer includes a first pooling unit, a second pooling unit and a third pooling unit; The first pooling unit performs maximum pooling processing on the fourth convolution feature map to obtain a first pooling feature map; the second pooling unit performs maximum pooling processing on the fifth convolution feature map to obtain a second pooling feature map; the third pooling unit performs maximum pooling processing on the sixth convolution feature map to obtain a third pooling feature map; The fully connected layer filters and cascades the first pooled feature map, the second pooled feature map, and the third pooled feature map to obtain a first feature vector, and classifies the first feature vector based on an activation function to obtain a text feature classification result; The associated feature detection model is used to perform associated feature classification on the input blockchain data to obtain an associated feature classification result; The fusion feature detection model performs weighted fusion on the text feature classification result and the associated feature classification result to obtain a final classification result; A model training module, used to train the blockchain data covert transmission detection model to obtain a trained blockchain data covert transmission detection model; The detection module is used to perform blockchain data covert transmission detection based on the trained blockchain data covert transmission detection model.

Images