Traffic integrity verification methods, apparatus, computer equipment and their storage media
By extracting and fusing features from the encryption key and combining it with a traffic discrimination model, the problem of low accuracy in encrypted traffic integrity verification in existing technologies is solved, and more accurate integrity verification is achieved.
Patent Information
- Application Number
- CN202311313386.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-11
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-10-11
AI Technical Summary
Existing technologies have low accuracy in verifying the integrity of encrypted transmission traffic and cannot accurately determine whether the traffic has been corrupted.
By extracting features from the encryption key, key features are obtained and fused with the encrypted traffic to be verified. The key fusion features are then used to input the traffic discrimination model for integrity verification.
It improves the accuracy of encrypted traffic integrity verification, ensuring that the verification results accurately reflect whether the integrity of the traffic is missing.
Smart Images

Figure CN117240578B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of network security technology, and in particular to a traffic integrity verification method, apparatus, computer device and its storage medium. Background Technology
[0002] With the continuous development of network security technology, more and more users are paying attention to network security and encrypting traffic during transmission to improve the security of traffic transmission. To determine whether traffic has been corrupted during transmission, it is necessary to verify the integrity of the encrypted traffic.
[0003] However, existing technologies only verify the integrity of encrypted transmission traffic based on its encrypted characteristics, resulting in low accuracy in verifying the integrity of encrypted transmission traffic. Summary of the Invention
[0004] Therefore, it is necessary to provide a traffic integrity verification method, apparatus, computer equipment, and storage medium that can accurately verify the integrity of encrypted transmitted traffic in response to the above-mentioned technical problems.
[0005] Firstly, this application provides a method for verifying traffic integrity. The method includes:
[0006] Based on the key feature extraction model, the encryption key of the encrypted traffic to be verified is extracted to obtain key features;
[0007] Determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified;
[0008] The key fusion features are input into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0009] In one embodiment, determining key fusion characteristics based on key characteristics and the encrypted traffic to be verified includes:
[0010] Determine the traffic characteristics corresponding to the encrypted traffic to be verified;
[0011] The key features and traffic features are fused to obtain the key fused features.
[0012] In one embodiment, determining the traffic characteristics corresponding to the encrypted traffic to be verified includes:
[0013] The encrypted traffic to be verified is input into the traffic feature extraction model to obtain the traffic features output by the traffic feature extraction model.
[0014] In one embodiment, the encryption key of the encrypted traffic to be verified is extracted using a key feature extraction model to obtain key features, including:
[0015] The encryption key is normalized to obtain the processed encryption key;
[0016] The processed encryption key is input into the key feature extraction model to obtain the key features output by the key feature extraction model.
[0017] In one embodiment, the training process for the key feature extraction model and the traffic discrimination model includes:
[0018] Input the sample key corresponding to the encrypted traffic into the key feature extraction model to obtain the sample key features output by the key feature extraction model;
[0019] Based on the sample key characteristics and sample encryption traffic, sample fusion characteristics are obtained;
[0020] The sample fusion features are input into the traffic discrimination model to obtain the sample verification results output by the traffic discrimination model;
[0021] Based on the sample verification results and sample encrypted traffic, the key feature extraction model and traffic discrimination model are trained.
[0022] In one embodiment, the key feature extraction model and the traffic discrimination model are trained based on the sample verification results and the sample encrypted traffic, including:
[0023] Based on the sample verification results and sample encryption traffic, determine the sample fusion feature error and sample encryption traffic error;
[0024] The key feature extraction model is trained based on the sample fusion feature error.
[0025] The traffic discrimination model is trained based on the sample fusion feature error and the sample encryption traffic error.
[0026] In one embodiment, the method further includes:
[0027] The traffic identifier of the encrypted traffic to be verified is sent to the server so that the server can determine the encryption key of the encrypted traffic to be verified based on the traffic identifier and provide feedback.
[0028] Receive the encryption key from the server.
[0029] Secondly, this application also provides a traffic integrity verification device. The device includes:
[0030] The extraction module is used to extract features from the encryption key of the encrypted traffic to be verified according to the key feature extraction model, so as to obtain key features;
[0031] The first determining module is used to determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified;
[0032] The second determining module is used to input the key fusion features into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0033] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:
[0034] Based on the key feature extraction model, the encryption key of the encrypted traffic to be verified is extracted to obtain key features;
[0035] Determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified;
[0036] The key fusion features are input into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0037] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:
[0038] Based on the key feature extraction model, the encryption key of the encrypted traffic to be verified is extracted to obtain key features;
[0039] Determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified;
[0040] The key fusion features are input into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0041] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:
[0042] Based on the key feature extraction model, the encryption key of the encrypted traffic to be verified is extracted to obtain key features;
[0043] Determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified;
[0044] The key fusion features are input into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0045] The aforementioned traffic integrity verification method, apparatus, computer equipment, and storage medium extract key features from the encryption key, determine key fusion features based on the key features and the encrypted traffic to be verified, and then obtain the integrity verification result output by the traffic discrimination model based on the key fusion features. Since the above process does not directly verify the integrity of the encrypted traffic to be verified, but rather verifies the integrity through the key fusion features obtained by fusing the encrypted traffic to be verified with the key features, compared to existing methods that directly verify the integrity of the encrypted traffic to be verified, this application introduces key features of the encryption key when verifying the integrity of the encrypted traffic to be verified. By establishing a correspondence between the encrypted traffic to be verified and the key features, the accuracy of the integrity verification of the encrypted traffic to be verified is improved, ensuring that the integrity verification result of the encrypted traffic to be verified accurately reflects whether the integrity of the encrypted traffic to be verified is missing. Attached Figure Description
[0046] Figure 1 An application environment diagram for a traffic integrity verification method provided in this application embodiment;
[0047] Figure 2 A flowchart illustrating a traffic integrity verification method provided in an embodiment of this application;
[0048] Figure 3 A flowchart illustrating the process of determining key fusion features provided in an embodiment of this application;
[0049] Figure 4 A flowchart illustrating the process of determining key characteristics provided in an embodiment of this application;
[0050] Figure 5 A schematic diagram illustrating the training process of the key feature extraction model and the traffic discrimination model provided in the embodiments of this application;
[0051] Figure 6 An interaction signaling diagram of an encrypted traffic sender and an encrypted traffic receiver provided in an embodiment of this application;
[0052] Figure 7 A flowchart illustrating another traffic integrity verification method provided in this application embodiment;
[0053] Figure 8 A structural block diagram of the first flow integrity verification device provided in the embodiments of this application;
[0054] Figure 9 This is a structural block diagram of the second type of flow integrity verification device provided in the embodiments of this application;
[0055] Figure 10A structural block diagram of the third flow integrity verification device provided in the embodiments of this application;
[0056] Figure 11 A structural block diagram of the fourth flow integrity verification device provided in the embodiments of this application;
[0057] Figure 12 A structural block diagram of the fifth flow integrity verification device provided in the embodiments of this application;
[0058] Figure 13 A structural block diagram of the sixth flow integrity verification device provided in the embodiments of this application;
[0059] Figure 14 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0061] The traffic integrity verification method provided in this application can be applied to, for example... Figure 1 In the application environment shown, both the encrypted traffic receiver 101 and the encrypted traffic sender 102 communicate with the server 103 via a network. A data storage system can store the data that the server 103 needs to process. The data storage system can be integrated onto the server 103 or placed on a cloud or other network server. This application extracts features from the encryption key to obtain key features, and determines key fusion features based on the key features and the encrypted traffic to be verified. Then, based on the key fusion features, the integrity verification result output by the traffic discrimination model is obtained. The encrypted traffic receiver 101 and the encrypted traffic sender 102 can be, but are not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. The server 103 can be implemented using a standalone server or a server cluster composed of multiple servers.
[0062] In one embodiment, such as Figure 2 As shown, a traffic integrity verification method is provided, which is applied to... Figure 1 Taking the encrypted traffic receiver 101 as an example, the following steps are included:
[0063] Step 201: Extract features from the encryption key of the encrypted traffic to be verified using the key feature extraction model to obtain key features.
[0064] Among them, the key feature extraction model is a model with ResNet-34 (a 34-layer convolutional neural network) as the backbone network.
[0065] It should be noted that, in order to ensure that the correspondence between the encryption key and the encrypted traffic to be verified can be considered in the subsequent process of obtaining the integrity verification result of the encrypted traffic to be verified, the encryption key needs to be input into the key feature extraction model first to extract the features of the encryption key of the encrypted traffic to be verified, and obtain the output result of the key feature extraction model, which is the key feature.
[0066] To further explain, since the encryption methods of different encrypted traffic to be verified may be different, the key format of the encryption key may also be different. Therefore, in order to ensure that the key feature extraction model can extract features for the encryption keys of different encrypted traffic to be verified, the encryption keys of the encrypted traffic to be verified can be normalized to ensure that the encryption keys of different encrypted traffic to be verified have the same key format when input into the key feature extraction model.
[0067] Step 202: Determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified.
[0068] It should be noted that, in order to ensure the integrity verification result of the encrypted traffic to be verified is obtained in the subsequent process, the key features of the encryption key are introduced. This allows the integrity verification result of the encrypted traffic to be verified to be obtained by the correspondence between the encrypted traffic to be verified and the key features. Therefore, the key features and the encrypted traffic to be verified can be fused to obtain the key fusion features.
[0069] To further explain, in order to ensure the smooth fusion of key features and encrypted traffic to be verified, it is necessary to extract features from the encrypted traffic to be verified to obtain the traffic features corresponding to the encrypted traffic to be verified. Then, the traffic features corresponding to the encrypted traffic to be verified and the key features are fused to obtain the key fusion features.
[0070] Among them, feature addition fusion or feature concatenation fusion methods can be used to fuse the traffic features and key features corresponding to the encrypted traffic to be verified. It can be understood that there are many methods to fuse the traffic features and key features corresponding to the encrypted traffic to be verified, and no fusion method is limited here.
[0071] Step 203: Input the key fusion features into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0072] The integrity verification result includes integrity verification passed and integrity verification failed. Furthermore, integrity verification passed means that the key fusion characteristics determine that there is no missing traffic in the encrypted traffic to be verified; integrity verification failed means that the key fusion characteristics determine that there is missing traffic in the encrypted traffic to be verified.
[0073] The backbone network of the traffic discrimination model is a ResNet-18 (18-layer convolutional neural network).
[0074] In one embodiment of this application, if the integrity verification result output by the traffic discrimination model is that the integrity verification fails, the integrity verification result is fed back to the encrypted traffic sender so that the encrypted traffic sender can send the encrypted traffic to be verified to the encrypted traffic receiver again.
[0075] The aforementioned traffic integrity verification method extracts key features from the encryption key to obtain key features, determines key fusion features based on the key features and the encrypted traffic to be verified, and then obtains the integrity verification result output by the traffic discrimination model based on the key fusion features. Since the above process does not directly verify the integrity of the encrypted traffic to be verified, but rather verifies the integrity through the key fusion features obtained by fusing the encrypted traffic to be verified with the key features, compared to existing methods that directly verify the integrity of the encrypted traffic to be verified, this application introduces key features of the encryption key when verifying the integrity of the encrypted traffic to be verified. By establishing a correspondence between the encrypted traffic to be verified and the key features, the accuracy of the integrity verification of the encrypted traffic to be verified is improved, ensuring that the integrity verification result of the encrypted traffic to be verified accurately reflects whether the integrity of the encrypted traffic to be verified is missing.
[0076] In one embodiment, because existing technologies only verify the integrity of encrypted transmission traffic based on its encrypted characteristics, the accuracy of integrity verification for encrypted transmission traffic is relatively low. To prevent this problem, the following can be done: Figure 3 As shown, based on key characteristics and the encrypted traffic to be verified, key fusion characteristics are determined, which may specifically include the following:
[0077] Step 301: Determine the traffic characteristics corresponding to the encrypted traffic to be verified.
[0078] Among them, the traffic features corresponding to the encrypted traffic to be verified refer to the features that can reflect the encrypted traffic content of the encrypted traffic to be verified. The traffic features corresponding to the encrypted traffic to be verified refer to at least one of the five-tuple of the encrypted traffic to be verified and the information entropy. Here, there is no limitation on the traffic features corresponding to the encrypted traffic to be verified.
[0079] It should be noted that when it is necessary to determine traffic characteristics, the following steps may be included: inputting the encrypted traffic to be verified into the traffic characteristic extraction model to obtain the traffic characteristics output by the traffic characteristic extraction model.
[0080] To further explain, the training process of the traffic feature extraction model includes: pre-acquiring sample encrypted traffic, manually labeling the sample encrypted traffic with traffic features, and training the traffic feature extraction model based on the sample encrypted traffic with labeled traffic features to obtain the trained traffic feature extraction model.
[0081] Step 302: Perform feature fusion on key features and traffic features to obtain key fusion features.
[0082] In one embodiment of this application, when it is necessary to perform feature fusion on key features and traffic features, the key features and traffic features can be added together to obtain the fused key fusion features.
[0083] In another embodiment of this application, when it is necessary to perform feature fusion on key features and traffic features, the key features and traffic features can be concatenated to obtain the fused key fusion features.
[0084] The aforementioned traffic integrity verification method, by determining the traffic characteristics corresponding to the encrypted traffic to be verified, ensures that the traffic characteristics corresponding to the encrypted traffic to be verified can be successfully fused with the key characteristics in the subsequent process. This achieves the accuracy of the integrity verification of the encrypted traffic to be verified by realizing the correspondence between the encrypted traffic to be verified and the key characteristics, and ensures that the integrity verification result of the encrypted traffic to be verified can accurately reflect whether there is any missing integrity in the encrypted traffic to be verified.
[0085] In one embodiment, such as Figure 4 As shown, when it is necessary to extract features from the encryption key of the encrypted traffic to be verified according to the key feature extraction model to obtain key features, the specific features may include the following:
[0086] Step 401: Normalize the encryption key to obtain the processed encryption key.
[0087] It should be noted that when it is necessary to normalize the encryption key, the following can be included: perform decimal calculation on the encryption key in units of eight bits to obtain the decimal representation of the encryption key, and then divide the decimal representation of the encryption key by 255 to obtain the processed encryption key.
[0088] To further explain, if the result of dividing the decimal representation of the encryption key by 255 is not a multiple of 8, then the result is padded with zeros until it is a multiple of 8, thus obtaining the processed encryption key.
[0089] The processed encryption key is a key vector consisting of multiple 0s and 1s.
[0090] To further explain, before normalizing the encryption key, the encryption key can be obtained by: sending the traffic identifier of the encrypted traffic to be verified to the server, so that the server can determine the encryption key of the encrypted traffic to be verified based on the traffic identifier and provide feedback; and receiving the encryption key provided by the server.
[0091] Specifically, the server determines the target identifier that is the same as the traffic identifier from the candidate identifiers pre-stored in the server. The server also stores the encryption key corresponding to each candidate identifier. Therefore, the encryption key corresponding to the target identifier is used as the encryption key of the traffic identifier, which is the encryption key of the encrypted traffic to be verified.
[0092] Step 402: Input the processed encryption key into the key feature extraction model to obtain the key features output by the key feature extraction model.
[0093] The above-mentioned traffic integrity verification method normalizes the encryption key to prevent the key feature output by the key feature extraction model from being inaccurate due to different encryption key formats, thus ensuring that the integrity verification results can be obtained smoothly in subsequent processes.
[0094] In one embodiment, such as Figure 5 As shown, the training process of the key feature extraction model and the traffic discrimination model may specifically include the following:
[0095] Step 501: Input the sample key corresponding to the sample encrypted traffic into the key feature extraction model to obtain the sample key features output by the key feature extraction model.
[0096] The sample key can be a historical key or reference key pre-set by the staff. Furthermore, there are many ways to obtain the sample key, and the process of obtaining the sample key is not limited here.
[0097] Among them, sample key features refer to the output of the key feature extraction model after extracting features from the sample key.
[0098] Step 502: Obtain sample fusion characteristics based on sample key characteristics and sample encryption traffic.
[0099] In one embodiment of this application, when it is necessary to obtain sample fusion features, the sample traffic features corresponding to the sample encrypted traffic can be determined; then, the sample key features and sample traffic features are fused by feature addition to obtain the fused sample fusion features.
[0100] Among them, sample traffic characteristics refer to at least one of the sample encrypted traffic quintuple and information entropy.
[0101] Furthermore, the sample traffic features corresponding to the encrypted sample traffic can be determined through a traffic feature extraction model; specifically, the encrypted sample traffic is input into the traffic feature extraction model to obtain the sample traffic features output by the traffic feature extraction model.
[0102] Step 503: Input the sample fusion features into the traffic discrimination model to obtain the sample verification results output by the traffic discrimination model.
[0103] Step 504: Train the key feature extraction model and the traffic discrimination model based on the sample verification results and sample encrypted traffic.
[0104] It should be noted that the specific process of training the key feature extraction model and the traffic discrimination model includes: determining the sample fusion feature error and the sample encrypted traffic error based on the sample verification results and sample encrypted traffic; training the key feature extraction model based on the sample fusion feature error; and training the traffic discrimination model based on the sample fusion feature error and sample encrypted traffic error.
[0105] Among them, the sample fusion feature error refers to the error in the sample key feature output by the key feature extraction model, which leads to the error in the sample fusion feature obtained after fusing the sample key feature and the sample encrypted traffic; the sample encrypted traffic error refers to the error between the sample encrypted traffic integrity prediction in the sample verification result output by the traffic discrimination model and the integrity of the actual sample encrypted traffic.
[0106] Therefore, based on the definitions of sample fusion feature error and sample encryption traffic error, it is possible to determine the sample fusion feature error and sample encryption traffic error according to the sample verification results and sample encryption traffic, and then train the key feature extraction model according to the sample fusion feature error; and train the traffic discrimination model according to the sample fusion feature error and sample encryption traffic error.
[0107] In one embodiment of this application, the key feature extraction model can be trained according to the calculation function (1), wherein the calculation function (1) is as follows:
[0108]
[0109] Among them, Loss A This refers to the computation function (1); m refers to the number of sample keys used to train the key feature extraction model; z iIt refers to the i-th sample key; C refers to the sample key features output by the key feature extraction model; A(z)+e refers to the sample fusion features.
[0110] In one embodiment of this application, the traffic discrimination model can be trained according to the calculation function (2), wherein the calculation function (2) is as follows:
[0111]
[0112] Among them, Loss C This refers to the calculation function (1); m refers to the number of encrypted traffic samples trained on the traffic discrimination model; x i It refers to the encrypted traffic of the i-th sample; C refers to the sample key features output by the key feature extraction model; A(z)+e refers to the sample fusion features.
[0113] To further explain, before training the traffic discrimination model based on the sample fusion feature error and the sample encrypted traffic error, the traffic discrimination model can be pre-trained. The specific training includes: directly inputting the plaintext sample traffic of the sample encrypted traffic into the traffic discrimination model, obtaining the integrity verification result of the traffic discrimination model for the plaintext sample traffic, and determining the plaintext traffic error; and pre-training the traffic discrimination model based on the plaintext traffic error.
[0114] Plaintext flow error refers to the error between the integrity verification result of plaintext sample flow and the actual integrity of plaintext sample flow.
[0115] In one embodiment of this application, plaintext sample traffic can be imaged, and then a traffic discrimination model can be trained based on the imaged plaintext sample traffic. Specifically, the imaged processing includes the following: performing decimal processing on the plaintext sample traffic in 8-bit units, converting each element obtained from the processing into an image as a pixel value, thereby obtaining the imaged plaintext sample traffic.
[0116] The above-mentioned traffic integrity verification method trains a key feature extraction model and a traffic discrimination model, so that when performing integrity verification on encrypted traffic to be verified, it can first determine the key features based on the key feature extraction model, and then input the key fusion feature obtained by fusing the key features with the encrypted traffic to be verified into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0117] In one embodiment, such as Figure 6As shown, when an encrypted traffic receiver wants to perform integrity verification on encrypted traffic to be verified sent by an encrypted traffic sender, the following steps may be included: The encrypted traffic sender, the encrypted traffic receiver, and the server establish a secure connection, wherein the server stores information related to the secure connection between the encrypted traffic sender and the encrypted traffic receiver; the encrypted traffic sender sends the encrypted traffic to be verified and its traffic identifier to the encrypted traffic receiver; the encrypted traffic receiver sends an integrity verification request to the server, which includes the receiver's secondary identity information and the traffic identifier of the encrypted traffic to be verified; the server determines the encryption key of the encrypted traffic to be verified based on the traffic identifier, and extracts features from the encryption key using a key feature extraction model to obtain key features; the server sends the key features, the traffic feature extraction model, and the traffic discrimination model to the encrypted traffic receiver, enabling the receiver to input the encrypted traffic to be verified into the traffic feature extraction model to obtain the traffic features output by the model; based on the key features and the encrypted traffic to be verified, a key fusion feature is determined; and the key fusion feature is input into the traffic discrimination model to obtain the integrity verification result output by the model.
[0118] Specifically, when determining the encryption key of the encrypted traffic to be verified based on the traffic identifier, the server's information database can be traversed and searched according to the traffic identifier to determine the secure connection information of the encrypted traffic sender, which includes the encryption key.
[0119] To further clarify, before performing integrity verification on the encrypted traffic to be verified, it is also necessary to verify the identities of the encrypted traffic sender and the encrypted traffic receiver. Specifically: determine the first identity information of the encrypted traffic sender and the second identity information of the encrypted traffic receiver; verify the identity information of the first and second identity information. If the verification result is successful, then perform the step of extracting the features of the encryption key of the encrypted traffic to be verified according to the key feature extraction model to obtain the key features.
[0120] The second identity information can be obtained based on the integrity verification request, while the first identity information can be obtained by traversing and searching the server's information database based on the traffic identifier to determine the secure connection information of the encrypted traffic sender. The secure connection information includes the first identity information.
[0121] In one embodiment of this application, when identity verification of the first identity information and the second identity information is required, the method may include: verifying whether both the first identity information and the second identity information are in an information whitelist. If both the first identity information and the second identity information are in the information whitelist, the verification result is determined to be successful; if the first identity information and / or the second identity information are not in the information whitelist, the verification result is determined to be unsuccessful.
[0122] In another embodiment of this application, when identity verification of the first identity information and the second identity information is required, the method may further include: verifying whether both the first identity information and the second identity information are in an information blacklist. If neither the first identity information nor the second identity information is in an information blacklist, the verification result is determined to be successful; if the first identity information and / or the second identity information is in an information whitelist, the verification result is determined to be unsuccessful.
[0123] The above-mentioned traffic integrity verification method enables the integrity verification of encrypted traffic to be verified under the premise of verifying the identity security of the encrypted traffic sender and the encrypted traffic receiver, thus ensuring the smooth progress of the verification process.
[0124] In one embodiment, such as Figure 7 As shown, when it is necessary to determine the integrity verification result of the encrypted traffic to be verified, the following may be included:
[0125] Step 701: Normalize the encryption key to obtain the processed encryption key.
[0126] Step 702: Input the processed encryption key into the key feature extraction model to obtain the key features output by the key feature extraction model.
[0127] Step 703: Input the encrypted traffic to be verified into the traffic feature extraction model to obtain the traffic features output by the traffic feature extraction model.
[0128] Step 704: Perform feature fusion on key features and traffic features to obtain key fusion features.
[0129] Step 705: Input the key fusion features into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0130] The aforementioned traffic integrity verification method extracts key features from the encryption key to obtain key features, determines key fusion features based on the key features and the encrypted traffic to be verified, and then obtains the integrity verification result output by the traffic discrimination model based on the key fusion features. Since the above process does not directly verify the integrity of the encrypted traffic to be verified, but rather verifies the integrity through the key fusion features obtained by fusing the encrypted traffic to be verified with the key features, compared to existing methods that directly verify the integrity of the encrypted traffic to be verified, this application introduces key features of the encryption key when verifying the integrity of the encrypted traffic to be verified. By establishing a correspondence between the encrypted traffic to be verified and the key features, the accuracy of the integrity verification of the encrypted traffic to be verified is improved, ensuring that the integrity verification result of the encrypted traffic to be verified accurately reflects whether the integrity of the encrypted traffic to be verified is missing.
[0131] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0132] Based on the same inventive concept, this application also provides a traffic integrity verification device for implementing the traffic integrity verification method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more traffic integrity verification device embodiments provided below can be found in the limitations of the traffic integrity verification method described above, and will not be repeated here.
[0133] In one embodiment, such as Figure 8 As shown, a traffic integrity verification device is provided, comprising: an extraction module 10, a first determination module 20, and a second determination module 30, wherein:
[0134] The extraction module 10 is used to extract features from the encryption key of the encrypted traffic to be verified according to the key feature extraction model, so as to obtain key features.
[0135] The extraction module is also used to determine the encryption key of the encrypted traffic to be verified based on the traffic identifier of the encrypted traffic to be verified.
[0136] The first determining module 20 is used to determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified.
[0137] The second determining module 30 is used to input the key fusion features into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0138] The aforementioned traffic integrity verification device extracts key features from the encryption key, determines key fusion features based on the key features and the encrypted traffic to be verified, and then obtains the integrity verification result output by the traffic discrimination model based on the key fusion features. Since the above process does not directly verify the integrity of the encrypted traffic to be verified, but rather verifies the integrity through the key fusion features obtained by fusing the encrypted traffic to be verified with the key features, compared to existing methods that directly verify the integrity of the encrypted traffic to be verified, this application introduces key features of the encryption key when verifying the integrity of the encrypted traffic to be verified. By establishing a correspondence between the encrypted traffic to be verified and the key features, the accuracy of the integrity verification of the encrypted traffic to be verified is improved, ensuring that the integrity verification result of the encrypted traffic to be verified accurately reflects whether the integrity of the encrypted traffic to be verified is missing.
[0139] In one embodiment, such as Figure 9 As shown, a traffic integrity verification device is provided. The first determination module 20 in this device includes: a first determination unit 21 and a fusion unit 22, wherein:
[0140] The first determining unit 21 is used to determine the traffic characteristics corresponding to the encrypted traffic to be verified.
[0141] The first determining unit is specifically used to input the encrypted traffic to be verified into the traffic feature extraction model to obtain the traffic features output by the traffic feature extraction model.
[0142] The fusion unit 22 is used to perform feature fusion on key features and traffic features to obtain key fusion features.
[0143] In one embodiment, such as Figure 10 As shown, a traffic integrity verification device is provided. The extraction module 10 of the traffic integrity verification device includes: a processing unit 11 and a second determining unit 12, wherein:
[0144] The processing unit 11 is used to normalize the encryption key to obtain the processed encryption key.
[0145] The second determining unit 12 is used to input the processed encryption key into the key feature extraction model to obtain the key features output by the key feature extraction model.
[0146] In one embodiment, such as Figure 11 As shown, a traffic integrity verification device is provided, which further includes: a first input module 40, a fusion module 50, a second output module 60, and a training module 70, wherein:
[0147] The first input module 40 is used to input the sample key corresponding to the sample encrypted traffic into the key feature extraction model to obtain the sample key features output by the key feature extraction model.
[0148] The fusion module 50 is used to obtain sample fusion features based on sample key features and sample encryption traffic.
[0149] The second output module 60 is used to input the sample fusion features into the traffic discrimination model to obtain the sample verification results output by the traffic discrimination model.
[0150] Training module 70 is used to train the key feature extraction model and the traffic discrimination model based on the sample verification results and sample encrypted traffic.
[0151] In one embodiment, such as Figure 12 As shown, a traffic integrity verification device is provided. The training module 70 in this device includes: a third determination unit 71, a first training unit 72, and a second training unit 73, wherein:
[0152] The third determining unit 71 is used to determine the sample fusion feature error and the sample encryption traffic error based on the sample verification results and the sample encryption traffic.
[0153] The first training unit 72 is used to train the key feature extraction model based on the sample fusion feature error.
[0154] The second training unit 73 is used to train the traffic discrimination model based on the sample fusion feature error and the sample encryption traffic error.
[0155] In one embodiment, such as Figure 13 As shown, a traffic integrity verification device is provided, which further includes: a sending module 80 and a receiving module 90, wherein:
[0156] The sending module 80 is used to send the traffic identifier of the encrypted traffic to be verified to the server, so that the server can determine the encryption key of the encrypted traffic to be verified based on the traffic identifier and provide feedback.
[0157] The receiving module 90 is used to receive the encryption key fed back by the server.
[0158] Each module in the aforementioned traffic integrity verification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.
[0159] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 14 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a traffic integrity verification method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.
[0160] Those skilled in the art will understand that Figure 14 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0161] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0162] Based on the key feature extraction model, the encryption key of the encrypted traffic to be verified is extracted to obtain key features;
[0163] Determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified;
[0164] The key fusion features are input into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0165] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0166] Determine the traffic characteristics corresponding to the encrypted traffic to be verified;
[0167] The key features and traffic features are fused to obtain the key fused features.
[0168] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0169] The encrypted traffic to be verified is input into the traffic feature extraction model to obtain the traffic features output by the traffic feature extraction model.
[0170] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0171] The encryption key is normalized to obtain the processed encryption key;
[0172] The processed encryption key is input into the key feature extraction model to obtain the key features output by the key feature extraction model.
[0173] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0174] Input the sample key corresponding to the encrypted traffic into the key feature extraction model to obtain the sample key features output by the key feature extraction model;
[0175] Based on the sample key characteristics and sample encryption traffic, sample fusion characteristics are obtained;
[0176] The sample fusion features are input into the traffic discrimination model to obtain the sample verification results output by the traffic discrimination model;
[0177] Based on the sample verification results and sample encrypted traffic, the key feature extraction model and traffic discrimination model are trained.
[0178] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0179] Based on the sample verification results and sample encryption traffic, determine the sample fusion feature error and sample encryption traffic error;
[0180] The key feature extraction model is trained based on the sample fusion feature error.
[0181] The traffic discrimination model is trained based on the sample fusion feature error and the sample encryption traffic error.
[0182] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0183] The traffic identifier of the encrypted traffic to be verified is sent to the server so that the server can determine the encryption key of the encrypted traffic to be verified based on the traffic identifier and provide feedback.
[0184] Receive the encryption key from the server.
[0185] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:
[0186] Based on the key feature extraction model, the encryption key of the encrypted traffic to be verified is extracted to obtain key features;
[0187] Determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified;
[0188] The key fusion features are input into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0189] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0190] Determine the traffic characteristics corresponding to the encrypted traffic to be verified;
[0191] The key features and traffic features are fused to obtain the key fused features.
[0192] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0193] The encrypted traffic to be verified is input into the traffic feature extraction model to obtain the traffic features output by the traffic feature extraction model.
[0194] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0195] The encryption key is normalized to obtain the processed encryption key;
[0196] The processed encryption key is input into the key feature extraction model to obtain the key features output by the key feature extraction model.
[0197] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0198] Input the sample key corresponding to the encrypted traffic into the key feature extraction model to obtain the sample key features output by the key feature extraction model;
[0199] Based on the sample key characteristics and sample encryption traffic, sample fusion characteristics are obtained;
[0200] The sample fusion features are input into the traffic discrimination model to obtain the sample verification results output by the traffic discrimination model;
[0201] Based on the sample verification results and sample encrypted traffic, the key feature extraction model and traffic discrimination model are trained.
[0202] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0203] Based on the sample verification results and sample encryption traffic, determine the sample fusion feature error and sample encryption traffic error;
[0204] The key feature extraction model is trained based on the sample fusion feature error.
[0205] The traffic discrimination model is trained based on the sample fusion feature error and the sample encryption traffic error.
[0206] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0207] The traffic identifier of the encrypted traffic to be verified is sent to the server so that the server can determine the encryption key of the encrypted traffic to be verified based on the traffic identifier and provide feedback.
[0208] Receive the encryption key from the server.
[0209] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:
[0210] Based on the key feature extraction model, the encryption key of the encrypted traffic to be verified is extracted to obtain key features;
[0211] Determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified;
[0212] The key fusion features are input into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model.
[0213] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0214] Determine the traffic characteristics corresponding to the encrypted traffic to be verified;
[0215] The key features and traffic features are fused to obtain the key fused features.
[0216] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0217] The encrypted traffic to be verified is input into the traffic feature extraction model to obtain the traffic features output by the traffic feature extraction model.
[0218] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0219] The encryption key is normalized to obtain the processed encryption key;
[0220] The processed encryption key is input into the key feature extraction model to obtain the key features output by the key feature extraction model.
[0221] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0222] Input the sample key corresponding to the encrypted traffic into the key feature extraction model to obtain the sample key features output by the key feature extraction model;
[0223] Based on the sample key characteristics and sample encryption traffic, sample fusion characteristics are obtained;
[0224] The sample fusion features are input into the traffic discrimination model to obtain the sample verification results output by the traffic discrimination model;
[0225] Based on the sample verification results and sample encrypted traffic, the key feature extraction model and traffic discrimination model are trained.
[0226] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0227] Based on the sample verification results and sample encryption traffic, determine the sample fusion feature error and sample encryption traffic error;
[0228] The key feature extraction model is trained based on the sample fusion feature error.
[0229] The traffic discrimination model is trained based on the sample fusion feature error and the sample encryption traffic error.
[0230] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0231] The traffic identifier of the encrypted traffic to be verified is sent to the server so that the server can determine the encryption key of the encrypted traffic to be verified based on the traffic identifier and provide feedback.
[0232] Receive the encryption key from the server.
[0233] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.
[0234] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0235] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0236] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for verifying traffic integrity, characterized in that, Applied to a ciphertext receiving end, the method includes: Based on the key feature extraction model, the encryption key of the encrypted traffic to be verified is extracted to obtain key features; Based on the key characteristics and the encrypted traffic to be verified, the key fusion characteristics are determined; The key fusion features are input into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model; The training process for the key feature extraction model and the traffic discrimination model includes: The sample key corresponding to the encrypted traffic is input into the key feature extraction model to obtain the sample key features output by the key feature extraction model; Based on the sample key characteristics and the sample encryption traffic, the sample fusion characteristics are obtained; The sample fusion features are input into the traffic discrimination model to obtain the sample verification results output by the traffic discrimination model; Based on the sample verification results and the sample encrypted traffic, determine the sample fusion feature error and the sample encrypted traffic error; The key feature extraction model is trained based on the sample fusion feature error. The traffic discrimination model is trained based on the sample fusion feature error and the sample encryption traffic error.
2. The method according to claim 1, characterized in that, The step of determining the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified includes: Determine the traffic characteristics corresponding to the encrypted traffic to be verified; The key features and the traffic features are fused to obtain the key fusion features.
3. The method according to claim 2, characterized in that, Determining the traffic characteristics corresponding to the encrypted traffic to be verified includes: The encrypted traffic to be verified is input into the traffic feature extraction model to obtain the traffic features output by the traffic feature extraction model.
4. The method according to any one of claims 1-3, characterized in that, The step of extracting features from the encryption key of the encrypted traffic to be verified according to the key feature extraction model to obtain key features includes: The encryption key is normalized to obtain the processed encryption key; The processed encryption key is input into the key feature extraction model to obtain the key features output by the key feature extraction model.
5. The method according to claim 1, characterized in that, The integrity verification result includes integrity verification passed and integrity verification failed. Further, integrity verification passed means that the key fusion characteristics determine that there is no missing traffic in the encrypted traffic to be verified; integrity verification failed means that the key fusion characteristics determine that there is missing traffic in the encrypted traffic to be verified.
6. The method according to claim 1, characterized in that, The method further includes: The traffic identifier of the encrypted traffic to be verified is sent to the server, so that the server determines the encryption key for the encrypted traffic to be verified based on the traffic identifier and provides feedback. Receive the encryption key returned by the server.
7. A flow integrity verification device, characterized in that, The device includes: The extraction module is used to extract features from the encryption key of the encrypted traffic to be verified according to the key feature extraction model, so as to obtain key features; The first determining module is used to determine the key fusion characteristics based on the key characteristics and the encrypted traffic to be verified; The second determining module is used to input the key fusion features into the traffic discrimination model to obtain the integrity verification result output by the traffic discrimination model; wherein, the training process of the key feature extraction model and the traffic discrimination model includes: inputting the sample key corresponding to the sample encrypted traffic into the key feature extraction model to obtain the sample key features output by the key feature extraction model; obtaining sample fusion features based on the sample key features and the sample encrypted traffic; inputting the sample fusion features into the traffic discrimination model to obtain the sample verification result output by the traffic discrimination model; determining the sample fusion feature error and the sample encrypted traffic error based on the sample verification result and the sample encrypted traffic; training the key feature extraction model based on the sample fusion feature error; and training the traffic discrimination model based on the sample fusion feature error and the sample encrypted traffic error.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.
Citation Information
Patent Citations
Signature based safe and efficient data fusion method
CN104618102A
Private data fusing method capable of detecting data integrity
CN104735654A
