Electronic screen content tampering detection system and method based on dynamic watermark

Abstract

The invention discloses an electronic screen content tampering detection system and method based on a dynamic watermark. The system comprises a cloud server, a display terminal electronic screen and a safety monitoring terminal. The method comprises the following steps: S1, generating and uploading a display terminal key seed; s2, the cloud server generates a frame watermark key packet based on the key seed and the video; s3, downloading a to-be-played video, and obtaining a frame watermark key packet corresponding to the video through encryption communication; s4, calculating a dynamic offset, and rendering and outputting an image containing the watermark; s5, reconstructing the original image through reverse transformation based on the frame watermark key, and calculating an actual offset through a phase correlation method; and S6, judging tampering according to the residual error measurement and triggering a shutdown operation. According to the electronic screen content tampering detection method, an electronic screen content tampering detection scheme with higher security is constructed, the legality of the electronic screen video content is monitored, illegal playing is automatically identified and blocked, and illegal spreading of bad content is prevented.

Description

Technical Field

[0001] The present invention relates to the field of network electronic screen content security information technology, and in particular to an electronic screen content tampering detection system and method based on dynamic watermark. Background Art

[0002] With the advancement of smart city construction, electronic screens have become the core carrier of information dissemination in public places, and are widely used in square advertising screens, transportation hub information screens, commercial complex digital signage and other scenarios. However, public data shows that the current public display screen content tampering incidents are increasing every year, involving illegal advertising implantation, sensitive information tampering, malicious code injection and other forms of attack.

[0003] In this context, real-time video tampering detection technology has become the core line of defense to ensure public information security, and many related technical patents have also been generated, such as CN117336570A, a video anti-tampering system, method, electronic device and medium based on digital watermark. This solution adds a digital watermark to the original video, and determines whether the video has been tampered with by detecting the digital watermark when the video is played. The defect of this solution is that the watermark information in the video is transmitted along with the video, and there is a risk of the video watermark information being cracked. Even if the watermark information is not cracked, there is still a replay attack, which will cause the video to not play normally. Summary of the invention

[0004] In order to solve the security problems existing in the existing video tampering detection technology, the present invention proposes an electronic screen content tampering detection system and method based on dynamic watermark, constructs a more secure electronic screen content tampering detection scheme, monitors the legality of the electronic screen video content, automatically identifies and blocks illegal playback, and prevents the illegal dissemination of bad content.

[0005] The present application discloses an electronic screen content tampering detection system based on dynamic watermark, including a cloud server, a display terminal electronic screen and a security monitoring terminal. Multiple display terminal electronic screens are connected to the cloud server to obtain video content to be played. Each display terminal electronic screen is connected to a security monitoring terminal, and all security monitoring terminals are connected to the cloud server via TLS encrypted communication.

[0006] Preferably, the electronic screen of the display terminal is equipped with a built-in GPU module supporting programmable shaders, which is used in the stage of processing vertex coordinate transformation in the GPU rendering pipeline, and superimposes dynamic offsets after vertex coordinate transformation.

[0007] Preferably, the security monitoring terminal has a built-in FPGA module for capturing output signals of the electronic screen of the display terminal.

[0008] The present application also discloses a method for detecting electronic screen content tampering based on a dynamic watermark, which is implemented based on the above-mentioned electronic screen content tampering detection system based on a dynamic watermark, and includes the following steps: S1. Generate a display terminal key seed, bind the display terminal electronic screen to the security monitoring terminal, and upload the mapping relationship and key seed; S2, the cloud server generates a frame watermark key package based on the key seed and the video; S3, the display terminal electronic screen downloads the video to be played, and requests the cloud server to obtain the frame watermark key package corresponding to the video through encrypted communication; S4, the display terminal electronic screen calculates the dynamic offset, the vertex shader superimposes the dynamic offset, and performs image rendering to output the image containing the watermark; S5, collecting the current watermarked frame image output by the terminal electronic screen, reconstructing the original image through inverse transformation based on the frame watermark key, and calculating the actual offset through phase correlation method; S6. Calculate the residual metric using the actual offset and the theoretical offset. When the residual of three consecutive image frames is greater than a preset value, shut down the electronic screen of the display terminal and report to the cloud server.

[0009] Preferably, the S1 comprises the following steps: S11. The screen driver chip of the display terminal electronic screen with a unique serial number integrates a physical unclonable function to generate a key seed that is resistant to physical cloning; S12, pairing and binding the display terminal electronic screen with the security monitoring terminal to establish a mapping relationship; S13. Transmit the mapping relationship, the device serial number of the display terminal electronic screen and the security monitoring terminal, and the key seed to the cloud server through TLS encrypted communication.

[0010] Preferably, S2 comprises the following steps: S21. Generate a master key corresponding to the electronic screen of the display terminal, which is used to derive the watermark key of each frame. The master key is generated by performing hash calculation based on the hardware identifier:

[0011] in, is the master key, is a cryptographic hash function, is the key seed; S22, independently generate a frame key for each frame of the video by deriving the master key and the frame number:

[0012] in, For video frames The frame key, Based on Counter mode encryption operation, is the frame number; S23, video frame Calculate the content hash value:

[0013] Hash value With frame key Combined to generate the watermark key:

[0014] in, It is a hash-based message authentication code algorithm; S24. After processing the video frame by frame in S21-S23, a frame watermark key package of the video is obtained, and the frame watermark key package is stored in the cloud server in correspondence with the video number and the serial number of the display terminal electronic screen device.

[0015] Preferably, S4 comprises the following steps: S41, obtaining a key seed through a GPU module built into the electronic screen of the display terminal; S42: Video frame to be played Calculate the frame content hash value:

[0016] Generate watermark key for the frame to be played:

[0017] in, The video frame to be played The frame number of S43: Based on the watermark key of the frame to be played Calculate the dynamic offset, which is the offset used for dynamic adjustment of vertex coordinates:

[0018] in, is the uniform distribution mapping function, is the normalization coefficient; At the same time, the key of the corresponding frame is obtained from the frame watermark key package obtained from the cloud server , and calculate the theoretical offset:

[0019] in, is the lateral displacement component of the theoretical displacement, is the vertical offset component of the theoretical offset; S44, through the stage of processing vertex coordinate transformation in the GPU module rendering pipeline, after the vertex coordinate transformation, the vertex shader superimposes the dynamic offset ; The transformed vertex set is rasterized into screen pixels by the GPU module, and a frame image containing a watermark is rendered and output.

[0020] Preferably, S5 comprises the following steps: S51, using the built-in FPGA module of the security monitoring terminal to collect the current frame image containing the watermark output by the electronic screen of the display terminal, recorded as ; S52, using theoretical offset , reconstruct the original image through inverse transformation and obtain the theoretical unwatermarked image:

[0021] in, is the inverse transformation function;

[0022] represents the image to be inverse transformed, , are the coordinates of the image pixels, is the inverse transform offset, for The deflection components in the lateral and vertical directions, sign Represents the translation transformation operation in image processing, represents the inverse translation transformation of coordinates, Represents the original coordinates after applying the inverse translation operation; S53, calculate the actual offset through the phase correlation algorithm:

[0023] in, represents the two-dimensional discrete Fourier transform, represents the two-dimensional inverse Fourier transform, is the complex conjugate operator, represents the peak value of Fourier transform, and the corresponding position is the actual offset of the two images. is the lateral displacement component of the actual displacement, It is the vertical component of the actual offset.

[0024] Preferably, S6 comprises the following steps: Calculate the residual metric using the actual offset and the theoretical offset:

[0025] When three consecutive frames of images meet hour, It is a preset value, and it is determined that the current playing content of the electronic screen has been tampered with. A message that illegal playback exists on the electronic screen of the display terminal is sent to the cloud server, and the electronic screen of the display terminal is shut down.

[0026] Beneficial effects of the present invention: (1) The watermark information is separated from the video. The downloaded video does not contain the watermark information, which eliminates the possibility of attackers downloading the video and then cracking it by analyzing the video watermark information, thus providing higher security.

[0027] (2) The watermark embedding is transferred from the pixel domain to the geometric domain, and the irreversible characteristics of the GPU rendering pipeline are utilized to make the watermark information impossible to extract through conventional image processing methods.

[0028] (3) In the process of watermark information generation, the master key is bound to the key seed generated by the physical unclonable function of the electronic screen driver chip to achieve hardware-level protection of "one machine, one secret". The watermark information generation is bound to the video frame to achieve dynamic changes of the watermark and prevent replay attacks.

[0029] (4) Pseudo-random offsets are applied to vertex coordinates at the sub-pixel level, with almost zero loss in image quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is an overall framework diagram of an electronic screen content tampering detection system based on dynamic watermarking according to an embodiment of the present invention.

[0031] Figure 2 This is a flow chart of a method for detecting electronic screen content tampering based on dynamic watermark according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and examples.

[0033] An embodiment of the present application discloses an electronic screen content tampering detection system based on dynamic watermark, and its overall framework is as follows: Figure 1As shown, it includes a cloud server, a display terminal electronic screen and a security monitoring terminal. Multiple display terminal electronic screens are connected to the cloud server to obtain the video content to be played. Each display terminal electronic screen is connected to a security monitoring terminal, and all security monitoring terminals are connected to the cloud server through TLS encrypted communication. The display terminal electronic screen has a built-in GPU module that supports programmable shaders, which is used in the GPU rendering pipeline to process vertex coordinate transformation, and the dynamic offset is superimposed after the vertex coordinate transformation. The security monitoring terminal has a built-in FPGA module for capturing the output signal of the display terminal electronic screen. In this embodiment, the FPGA model is Decklin 8K Pro G2.

[0034] Another embodiment of the present application discloses a method for detecting electronic screen content tampering based on dynamic watermarks. Based on the above-mentioned electronic screen content tampering detection system based on dynamic watermarks, the implementation process is as follows: Figure 2 As shown, the following steps are included: S1. Generate a display terminal key seed, bind the display terminal electronic screen to the security monitoring terminal, and upload the mapping relationship and key seed.

[0035] S11, the screen driver chip with a unique serial number on the display terminal electronic screen (NVIDIA Quadro driver board in this embodiment) integrates a physical unclonable function (PUF) to generate a key seed that is resistant to physical cloning .

[0036] S12, pairing and binding the display terminal electronic screen with the security monitoring terminal to establish a mapping relationship; S13, through TLS encrypted communication, the mapping relationship, the device serial number of the display terminal electronic screen and the security monitoring terminal, and the key seed Transmit to cloud server.

[0037] S2. The cloud server generates a frame watermark key package based on the key seed and video.

[0038] S21. Generate a master key corresponding to the electronic screen of the display terminal , used to derive the watermark key for each frame, which is generated by hashing the hardware identifier:

[0039] in, is the master key, is a cryptographic hash function, The key seed.

[0040] S22, independently generate a frame key for each frame of the video , which is derived from the master key and frame number using AES-CTR mode:

[0041] in, For video frames The frame key, Based on Counter mode encryption operation, is the frame number.

[0042] S23, video frame Calculate content hash value :

[0043] Hash value With frame key Combine to generate watermark key :

[0044] in, It is a hash-based message authentication code algorithm.

[0045] S24. After processing the video frame by frame in S21-S23, a frame watermark key package of the video is obtained, and is stored in a cloud server in correspondence with the video number and the serial number of the display terminal electronic screen device.

[0046] S3. The electronic screen of the display terminal downloads the video to be played, and requests the cloud server to obtain the frame watermark key package of the video corresponding to the video to be played through TLS encrypted communication.

[0047] S4, the electronic screen of the display terminal calculates the dynamic offset and performs image rendering and output. The electronic screen of the display terminal calculates the dynamic offset, the vertex shader superimposes the dynamic offset, and performs image rendering and outputs the image containing the watermark.

[0048] S41. Obtain a key seed through a GPU module built into the electronic screen of the display terminal.

[0049] S42: Video frame to be played Calculate the frame content hash value :

[0050] Generate watermark key for frames to be played :

[0051] in, The video frame to be played The frame number.

[0052] S43: Based on the watermark key of the frame to be played Calculate dynamic offset, which is the offset used for dynamic adjustment of vertex coordinates :

[0053] in, is the uniform distribution mapping function, is the normalization coefficient, which is taken as .

[0054] At the same time, the key of the corresponding frame is obtained from the frame watermark key package obtained from the cloud server , and calculate the theoretical offset :

[0055] in, is the lateral displacement component of the theoretical displacement, is the vertical offset component of the theoretical offset; S44, through the stage of processing vertex coordinate transformation in the GPU module rendering pipeline, after the vertex coordinate transformation, the vertex shader superimposes the dynamic offset The transformed vertex set is rasterized into screen pixels by the GPU module, and a frame image with a watermark (dynamic offset) is rendered and output.

[0056] S5, frame-by-frame watermark detection: The current watermarked frame image output by the terminal electronic screen is collected, the original image is reconstructed through inverse transformation based on the frame watermark key, and the actual offset is calculated through the phase correlation method.

[0057] S51, use the built-in FPGA module of the security monitoring terminal to capture the DP / HDMI output signal at 120fps to collect the current frame image containing the watermark (dynamic offset) output by the electronic screen of the display terminal, recorded as .

[0058] S52, using theoretical offset , reconstruct the original image through inverse transformation, and obtain the theoretical unwatermarked image :

[0059] in, is the inverse transformation function;

[0060] represents the image to be inverse transformed, , are the coordinates of the image pixels, is the inverse transform offset, for The deflection components in the lateral and vertical directions, sign Represents the translation transformation operation in image processing, represents the inverse translation transformation of coordinates, Represents the original coordinates after the inverse translation operation is applied.

[0061] S53, calculate the actual offset through the phase correlation algorithm:

[0062] in, represents the two-dimensional discrete Fourier transform, represents the two-dimensional inverse Fourier transform, is the complex conjugate operator, represents the peak value of Fourier transform, and the corresponding position is the actual offset of the two images. is the lateral displacement component of the actual displacement, It is the vertical component of the actual offset.

[0063] S6. Calculate the residual metric using the actual offset and the theoretical offset. When the residual of three consecutive image frames is greater than a preset value, shut down the electronic screen of the display terminal and report to the cloud server.

[0064] Calculate the residual metric using the actual offset and the theoretical offset:

[0065] When three consecutive frames of images meet hour, is a preset value. In this embodiment, the value is , determine that the current playing content of the electronic screen has been tampered with and is illegally played. Send a message that the electronic screen of the display terminal is illegally played to the cloud server, and disconnect the power supply of the screen by triggering the power relay to shut down the electronic screen of the display terminal.

[0066] In a specific embodiment, the effect of the solution of the present application is described through a comparative experiment. The experimental environment is as follows: Hardware: NVIDIA Quadro RTX 6000 GPU (CUDA core, 24GB video memory); Software: Unity rendering engine, CUDA 11.6, custom watermark embedding / extraction module; Dataset: 3D model library (including 1,000 high-precision models), 4K video sequences (60fps dynamic scenes).

[0067] The comparison baseline is as follows: Traditional static watermark: DCT / DWT-based static watermark, embedded in the frequency domain of the final rendered frame.

[0068] Traditional dynamic watermark: Based on pixel domain dynamic watermark, watermarks that are invisible to the naked eye are dynamically generated in the pixel domain or at certain fixed positions.

[0069] The anti-attack test and quantitative index results obtained from the comparative experiment are shown in Tables 1 and 2, where Table 1 is the visual quality evaluation result and Table 2 is the watermark defense success rate result.

[0070] Table 1 Visual quality evaluation (PSNR / SSIM)

[0071] As can be seen from Table 1, the scheme proposed in this application is significantly better than the traditional scheme in terms of PSNR (>39 dB) and SSIM (>0.96).

[0072] Table 2 Watermark defense success rate (success rate%)

[0073] As can be seen from Table 2, the traditional solution is easy to be analyzed and cracked because the watermark content is fixed. Even for dynamic watermarks, the watermark content is not separated from the video and there is a risk of being cracked. The solution proposed in this application significantly improves security through dynamic watermark keys and pipeline-level embedding.

[0074] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An electronic screen content tampering detection system based on dynamic watermark, characterized in that: It includes a cloud server, a display terminal electronic screen and a security monitoring terminal. Multiple display terminal electronic screens are connected to the cloud server to obtain the video content to be played. Each display terminal electronic screen is connected to a security monitoring terminal, and all security monitoring terminals are connected to the cloud server through TLS encrypted communication.

2. The electronic screen content tampering detection system based on dynamic watermark according to claim 1 is characterized in that: The display terminal electronic screen is built with a GPU module that supports programmable shaders, which is used in the GPU rendering pipeline to process vertex coordinate transformation and superimpose dynamic offsets after vertex coordinate transformation.

3. The electronic screen content tampering detection system based on dynamic watermark according to claim 2 is characterized in that: The safety monitoring terminal is equipped with a built-in FPGA module for capturing output signals of the electronic screen of the display terminal.

4. A method for detecting electronic screen content tampering based on dynamic watermark, characterized in that: The detection system according to any one of claims 1 to 3 is implemented, comprising the following steps: S1. Generate a display terminal key seed, bind the display terminal electronic screen to the security monitoring terminal, and upload the mapping relationship and key seed; S2, the cloud server generates a frame watermark key package based on the key seed and the video; S3, the display terminal electronic screen downloads the video to be played, and requests the cloud server to obtain the frame watermark key package corresponding to the video through encrypted communication; S4, the display terminal electronic screen calculates the dynamic offset, the vertex shader superimposes the dynamic offset, and performs image rendering to output the image containing the watermark; S5, collecting the current watermarked frame image output by the terminal electronic screen, reconstructing the original image through inverse transformation based on the frame watermark key, and calculating the actual offset through phase correlation method; S6. Calculate the residual metric using the actual offset and the theoretical offset. When the residual of three consecutive image frames is greater than a preset value, shut down the electronic screen of the display terminal and report to the cloud server.

5. The method for detecting electronic screen content tampering based on dynamic watermark according to claim 4 is characterized in that: The S1 comprises the following steps: S11. The screen driver chip of the display terminal electronic screen with a unique serial number integrates a physical unclonable function to generate a key seed that is resistant to physical cloning; S12, pairing and binding the display terminal electronic screen with the security monitoring terminal to establish a mapping relationship; S13. Transmit the mapping relationship, the device serial number of the display terminal electronic screen and the security monitoring terminal, and the key seed to the cloud server through TLS encrypted communication.

6. The method for detecting electronic screen content tampering based on dynamic watermark according to claim 5 is characterized in that: The S2 comprises the following steps: S21. Generate a master key corresponding to the electronic screen of the display terminal, which is used to derive the watermark key of each frame. The master key is generated by performing hash calculation based on the hardware identifier: in, is the master key, is a cryptographic hash function, is the key seed; S22, independently generate a frame key for each frame of the video by deriving the master key and the frame number: in, For video frames The frame key, Based on Counter mode encryption operation, is the frame number; S23, video frame Calculate the content hash value: Hash value With frame key Combined to generate the watermark key: in, It is a hash-based message authentication code algorithm; S24. After processing the video frame by frame in S21-S23, a frame watermark key package of the video is obtained, and is stored in a cloud server in correspondence with the video number and the serial number of the display terminal electronic screen device.

7. The method for detecting electronic screen content tampering based on dynamic watermark according to claim 6 is characterized in that: The S4 comprises the following steps: S41, obtaining a key seed through a GPU module built into the electronic screen of the display terminal; S42: Video frame to be played Calculate the frame content hash value: Generate watermark key for the frame to be played: in, The video frame to be played The frame number of S43: Based on the watermark key of the frame to be played Calculate the dynamic offset, which is the offset used for dynamic adjustment of vertex coordinates: in, is the uniform distribution mapping function, is the normalization coefficient; At the same time, the key of the corresponding frame is obtained from the frame watermark key package obtained from the cloud server , and calculate the theoretical offset: in, is the lateral displacement component of the theoretical displacement, is the vertical offset component of the theoretical offset; S44, through the stage of processing vertex coordinate transformation in the GPU module rendering pipeline, after the vertex coordinate transformation, the vertex shader superimposes the dynamic offset ; The transformed vertex set is rasterized into screen pixels by the GPU module, and a frame image containing a watermark is rendered and output.

8. The method for detecting electronic screen content tampering based on dynamic watermark according to claim 7 is characterized in that: The S5 comprises the following steps: S51, using the built-in FPGA module of the security monitoring terminal to collect the current frame image containing the watermark output by the electronic screen of the display terminal, recorded as ; S52, using theoretical offset , reconstruct the original image through inverse transformation and obtain the theoretical unwatermarked image: in, is the inverse transformation function; represents the image to be inverse transformed, , are the coordinates of the image pixels, is the inverse transform offset, for The deflection components in the lateral and vertical directions, sign Represents the translation transformation operation in image processing, represents the inverse translation transformation of coordinates, Represents the original coordinates after applying the inverse translation operation; S53, calculate the actual offset through the phase correlation algorithm: in, represents the two-dimensional discrete Fourier transform, represents the two-dimensional inverse Fourier transform, is the complex conjugate operator, represents the peak value of Fourier transform, and the corresponding position is the actual offset of the two images. is the lateral displacement component of the actual displacement, It is the vertical component of the actual offset.

9. The method for detecting electronic screen content tampering based on dynamic watermark according to claim 8, characterized in that: The S6 comprises the following steps: Calculate the residual metric using the actual offset and the theoretical offset: When three consecutive frames of images meet hour, It is a preset value, and it is determined that the current playing content of the electronic screen has been tampered with. A message that illegal playback exists on the electronic screen of the display terminal is sent to the cloud server, and the electronic screen of the display terminal is shut down.

Images