219results about "Image watermarking" patented technology

The invention relates to a method for generating an image watermark based on potential space multi-scale feature modulation. The method mainly comprises a watermark residual embedding and extracting method based on potential space multi-scale feature modulation, a watermark intensity regulation and control strategy based on time sequence gating and a robust watermark end-to-end training framework based on potential space. According to the method, watermark information is fused by using a multi-scale structure in a potential space of a diffusion model, meanwhile, a time sequence gating strategy dynamically determines the embedding time step of a watermark by calculating the convergence degree of a potential vector, and the image quality and the watermark robustness are balanced. Sigmoid weighted noise prediction loss is introduced in the model training process, and denoising control over low time steps is enhanced. The method can be widely applied to scenes such as image generation, copyright identification and content traceability, and has good practicability and popularization prospects.

The invention discloses a deep counterfeit face image source tracing evidence obtaining method and system based on a diffusion model, and relates to the technical field of deep counterfeit face image evidence obtaining. The method comprises the following steps: constructing a robust watermark framework based on a diffusion model, wherein the framework comprises a diffusion model encoder, a watermark decoder and a freeze parameter auto-encoder; in a training stage, a face image and a watermark are constructed as conditions, a diffusion model encoder is guided to denoise, and a corresponding watermark image is predicted; the trained robust watermark framework based on the diffusion model is used for testing, a specific depth forging model is added in the sampling stage for guiding, and a more robust watermark image is generated through iterative denoising; in the evidence obtaining stage, the watermark in the forged image to be subjected to evidence obtaining is obtained through the watermark decoder. The method can effectively cope with different counterfeiting technologies, provides a more robust and reliable deep counterfeiting traceability evidence obtaining scheme, and has strong adaptability and wide application prospects.

The invention discloses a diffusion model robust watermarking method based on affine coupling flow accurate coding. The method comprises the following steps: S1, training a watermark encoder and a watermark decoder; s2, freezing the trained watermark encoder and the diffusion model to perform diffusion iteration on the initial hidden variable to obtain a watermark-containing image, introducing an attack layer to finely adjust the pre-trained watermark decoder to generate the watermark-containing image, performing reverse diffusion of the diffusion model to form the initial hidden variable, and extracting watermark information by the pre-trained watermark decoder; and S3, uniformly and integrally deploying the trained watermark encoder and the diffusion model, and extracting the watermark in the user generated image to verify the identity. According to the diffusion model robust watermarking method based on affine coupling flow accurate coding, the problems that the robustness of a reconstruction watermark removing technology is insufficient, and the presentation of watermark information in an image generated by a user is single are solved.

The invention belongs to the field of image processing, and relates to a method for embedding a robust watermark in a diffusion model generated image, which comprises the following steps of: acquiring cue words, initial Gaussian noise and watermark information, and inputting the cue words, the initial Gaussian noise and the watermark information into a trained diffusion model based on watermark embedding to obtain a watermark-embedded image; the training process of the diffusion model comprises the following steps: acquiring cue words, initial Gaussian noise and watermark information, and inputting the cue words, the initial Gaussian noise and the watermark information into an encoder to obtain potential vectors; inputting the potential vector into a self-attention module to obtain an embedded position vector; embedding the watermark information into the potential vector according to the embedding position vector; inputting the potential vector embedded with the watermark information into a decoder to obtain an image embedded with the watermark; extracting watermark information from the image embedded with the watermark; updating parameters of a diffusion model according to the image embedded with the watermark and the extracted watermark information until a trained diffusion model is obtained; according to the method, the embedding position is selected by combining the potential of the diffusion model and the accuracy of the self-attention mechanism, so that efficient watermark embedding and extraction are realized.

A computer-implemented method for watermarking images includes providing a secret key network (SKN) that is adapted to output a standard multivariate normal (SMVN) distribution for a given input image distribution, applying an input image to the SKN, generating a secret key signature (SKS) as a real vector, and embedding a watermark in the input image by using an adversarial attack to modify the input image in a manner that aligns the SKN's output with the SKS. A computer-implemented method for detecting a watermark in an image is also provided.

The invention relates to a deep forgery active defense method based on watermarking, which belongs to the technical field of information security, firstly provides a semantic self-adaptive watermark embedding method based on Transform, and dynamically distributes watermark weights according to the semantic importance of a human face area by using a cross attention mechanism so as to enhance the defense effect on deep forgery attack; secondly, a separable decoder watermark architecture is constructed, the separable decoder watermark architecture comprises a robust decoder and a semi-robust decoder, a random image processing module (RIPM) is introduced during training, the separable decoder is trained by simulating images of conventional distortion and deep forgery attack, and stable traceability of user identity information and recognition of deep forgery behaviors are achieved; meanwhile, local watermark concentration difference caused by deep counterfeiting is analyzed, a thermodynamic diagram of a counterfeiting region is generated in combination with supervised learning, and positioning of the deep counterfeiting region is realized.

The invention discloses an image watermarking method based on a space channel interactive attention mechanism. The image watermarking method mainly comprises the following steps: acquiring an original image and constructing an image watermarking network based on the space channel attention mechanism; inputting the original image and the watermark into a watermark-containing image generation framework to obtain a watermark-containing image; inputting the image with the watermark into an image processing noise layer to obtain a noise image; inputting the noise image into a watermark extraction framework to obtain an extracted watermark; and constraining the training of the whole image watermark network based on the space channel attention mechanism by using the total loss. The image watermark network based on the space channel attention mechanism is used for copyright protection, and high-capacity embedding of watermarks, high-quality generation of images with watermarks and high-robustness extraction of the watermarks are achieved. According to the method, a depth feature map of the watermark is generated through watermark dimension extension, remodeling and diffusion by using a multi-layer sensor and the like. Meanwhile, the feature retention loss can promote the optimization of the total loss on the network training.

According to the invisible watermark embedding method based on the wavelet domain statistical characteristics, the high-frequency sub-band in the wavelet domain is selected as the embedding area, and the robustness of the watermark to conventional attacks such as compression and noise is improved while invisibility is guaranteed. Based on a self-adaptive embedding weight mechanism of a covariance matrix eigenvalue, the embedding strength of different texture regions can be dynamically adjusted, the robustness is enhanced by a smooth region, and distortion is suppressed by an edge region. Nonlinear disturbance is generated by adopting a deep neural network and chaotic encryption preprocessing is combined, so that the predictability of a linear statistical rule is broken, and the method has a relatively good application prospect.

The invention discloses a robust reversible watermarking method based on BFMs and adaptive normalization. The method comprises the steps of watermark embedding and watermark extraction. The watermark embedding specifically comprises the steps of generating watermark sequence information, performing integer wavelet transform on a carrier image, extracting a low-frequency region, and calculating BFMs of the low-frequency region; a proper watermark pair is selected through a private key, self-adaptive normalization is carried out according to the watermark pair, and the watermark is embedded in the normalized amplitude; reconstructing an image based on the amplitude of the embedded watermark; constructing a final reversible watermark image based on the reconstructed image; watermark extraction: judging whether the image is attacked or not; for an unattacked image, carrying out watermark extraction based on the auxiliary information; for an attacked image, watermark extraction is carried out by calculating the BFMs of the attacked image. The method has noise resistance and also has relatively good image reconstruction capability.

The invention provides an anti-screen-shooting robust text image watermarking method fusing edge attention gating and multi-scale cavity convolution, which comprises the following steps: step 1, designing a message processor for preprocessing a secret message, adding an expansion network ExpandNet and a channel attention SENet in the message processor, and carrying out edge attention gating and multi-scale cavity convolution on the expansion network ExpandNet and the channel attention SENet; inputting a secret message in a binary form and outputting a message feature map; step 2, constructing a text watermark framework based on edge attention gating and multi-scale cavity convolution fusion; adding a functional module in an encoder of the end-to-end watermark framework; 3, designing a noise layer, and performing simulation attack on the model in the watermark model training process; and step 4, designing an optimization mode of the loss function. According to the method, the robustness and imperceptibility of the watermark are remarkably improved.

The invention discloses a vision enhancement robust digital dark watermarking method based on deep learning, a storage medium and equipment, and belongs to the technical field of digital image processing and information security. According to the method, a visual enhancement module comprising a self-adaptive watermark region adjustment module and a frequency enhancement module is constructed, and a multi-region local loss training mechanism and a screen shooting simulation module are combined, so that the visual quality of a watermark image is improved, and meanwhile, the robustness of the watermark image for resisting physical attacks such as screen shooting is enhanced. The specific processing flow comprises the following steps: acquiring an original image and watermark information; embedding the watermark information into the image by using an encoder, wherein an embedded region is optimized by a self-adaptive region guide matrix generated based on the image edge and gray information; in the model training process, a noise layer simulating screen shooting physical distortion is introduced, and the area weight is dynamically adjusted according to residual error distribution in the later stage of training so as to focus and optimize the image quality; watermark information is extracted from an image which may suffer from an attack by using a decoder.

The invention discloses a watermark embedding method, a watermark extraction method, equipment, a readable storage medium and a product, and relates to the technical field of image processing, and the method comprises the steps: obtaining an original image to be subjected to watermark embedding and watermark information to be embedded, and inputting the original image and the watermark information to a pre-trained watermark embedding model; performing feature extraction on the original image through a feature extraction network to obtain a multi-domain fusion feature; a watermark embedding mode is determined through an adaptive attention network according to the multi-domain fusion features, and the watermark embedding mode at least comprises a watermark embedding position; watermark information is embedded in the multi-domain fusion features in a residual error mode through a watermark embedding network based on a watermark embedding mode, and embedded features are obtained; and through an image reconstruction network, the embedded features are converted to an airspace to obtain a watermark image after watermark embedding. According to the method, the watermark robustness is ensured, and meanwhile, the influence on the visual quality of the image is reduced.

The invention discloses a generative model redrawing attack-oriented image robust watermark traceability method and system and a computer readable storage medium, and belongs to the field of digital information security and artificial intelligence content governance. The method comprises the following steps: in a watermark embedding stage, performing error correction coding and digital signature processing on traceability information containing identity information and a timestamp to generate a load to be embedded, and embedding the load to be embedded and a synchronization template for geometric synchronization into a host image in a function separation manner by using a deep neural network; in the training stage, combined optimization is carried out on the watermark embedding and extracting process by introducing generative model redrawing and microsimulation of image distortion attack, so that the robustness of the watermark under a complex attack condition is improved; in the extraction and verification stage, under the condition that an original image is not needed, geometric synchronous correction and blind extraction of a watermark load are carried out on an image to be analyzed, and authenticity confirmation of traceability information is completed through error correction decoding and digital signature verification. By adopting the technical scheme of the invention, the problems of insufficient traceability information robustness, difficult source confirmation and incomplete evidence chain in a generative model redrawing scene in the prior art are solved, and verifiable traceability and credible evidence generation of the image source information are realized.

The invention provides a high-fidelity anti-compression image watermarking method and system based on spectrum-airspace decoupling, and belongs to the field of information security. Firstly, the watermark information is mapped and remodeled; a watermark encoder based on multi-granularity spectrum-spatial domain feature decoupling is constructed, discrete cosine transform is introduced to filter out high-frequency components, Haar wavelet transform is adopted to realize lossless downsampling, a fast Fourier transform dynamic filter is combined to capture global semantic features, and local texture details are combined through multi-scale spatial domain volume accumulation; designing a physical perception and visual self-adaptive dual embedding strategy, and anchoring watermark energy to an anti-compression brightness channel; constructing an anti-attack layer containing differentiable JPEG compression simulation and mixed noise simulation, and participating in network training; and constructing a decoder and designing a loss function to carry out network optimization. According to the method, the robustness of the watermark under strong compression and complex black box attacks is improved, and extremely high visual imperceptibility is realized through physical and visual constraints.

The invention discloses a copyright protection method for a 3DGS three-dimensional scene and objects in the scene, and belongs to the technical field of three-dimensional reconstruction. Target objects needing to be protected are automatically extracted from a multi-view image data set through an image sequence segmentation model; combining the original image with the target object image to construct a new data set for watermark network training, and carrying out network training; performing high-quality scene reconstruction on the multi-view image by adopting a 3DGS method; a hidden information loss function is introduced to finely adjust scene color information and a decoder of a watermark network, and copyright watermark embedding of the whole scene and a target object is achieved; the frequency domain consistency loss and the image difference loss are combined and optimized, and the quality of the reconstruction model after the watermark is embedded is ensured. According to the method, copyright protection of a three-dimensional scene level can be realized, fine-grained protection can be carried out on specific objects in the scene, and the method has relatively high practicability and robustness and is suitable for application scenes such as digital asset management and virtual reality content protection.

The invention discloses a DCT (Discrete Cosine Transform) frequency domain watermark embedding optimization method and system based on a potential space, and the method comprises the steps: firstly coding an original image into the potential space, segmenting the original image into small blocks, embedding a single-bit watermark into the frequency domain of each small block through weighted voting, then carrying out the inverse transformation to a spatial domain, merging, and forming a potential representation with a watermark; decoding through a stable diffusion model to generate an image with a watermark; iteratively optimizing the potential representation through a multi-objective loss function until the loss is minimum; and finally, decoding the optimized representation again, linearly mixing with the original image, adjusting a mixing coefficient through binary search, and outputting a final image on the premise of meeting preset image quality. According to the method, a multi-dimensional robustness optimization strategy is combined, the stability and the non-erasable property of the watermark under the attack of the generative model are systematically improved, and the core requirements of AI copyright protection and content traceability are met.

The systems and methods disclosed herein embed and store traceable watermarks across multiple data modalities including text, image, audio, video, and structured data. The systems and methods disclosed herein receive an input dataset and generate unique watermark patterns for each data modality using cryptographic hash functions applied to dataset identifiers. The watermark patterns include parameters that provide instructions to watermark the input dataset. Watermarking includes modifying discrete data values, relationships, or arrangements within the original dataset at predetermined locations. The watermarked dataset is used to generate a hierarchical fingerprint structure including multiple levels of cryptographic hash identifiers that represent different portions of the data (e.g., at varying granularities). Both the watermark patterns and hierarchical fingerprints are stored in a distributed database accessible through a decentralized network, thus enabling authorized computing devices to verify data provenance and detect potential misappropriation across heterogeneous digital content types.

The invention discloses an anti-multi-attack medical image robust watermarking method based on a Mama architecture, which comprises the following steps: an original medical image and watermark information are processed through an encoder network to generate a watermark-containing image, and an encoder comprises a hierarchical feature refined sampler module and a channel perception Mama architecture bottleneck layer; a watermark is recovered from a watermark-containing image which may be attacked through a decoder network, and a decoder carries out dual-path processing through a wavelet domain Mama module and a sequence context dependence module; randomly extracting 2-4 attacks from the attack library to apply dynamic composite attacks to the watermark-containing image in a random sequence and intensity; and performing end-to-end optimization through a composite loss function including reconstruction loss, clean decoding loss, robust decoding loss and perception loss. According to the method, the image frequency band is decoupled through discrete wavelet transform, meanwhile, the watermark is embedded at the high frequency, the long-range dependency relationship of the wavelet coefficient is modeled by using the selective state space mechanism of Mamba, and the robustness of the watermark is improved.

The invention relates to a robust watermarking method of a diffusion model based on an error correction code, which belongs to the technical field of large model watermarking, and comprises the following steps of: encoding a watermark message by using a Reed-Solomon error correction code to generate a code word containing redundancy check information; carrying out randomization processing on the code word to generate a pseudo-random bit stream; embedding the pseudo-random bit stream into a variable of an initial Gaussian potential space of a diffusion model by adopting a distribution preserving sampling technology; and finally, generating an image with a watermark through a denoising process of the diffusion model. When the watermark is extracted, reverse diffusion processing is carried out on an image which is possibly damaged to recover an approximate value of a potential space variable, a code word which is possibly damaged is extracted from the approximate value, and original watermark information is recovered by utilizing the error correction capability of a Reed-Solomon decoder. On the premise of keeping the generation performance, the robustness of the watermark to compression, noise, cutting and other potential tampering attacks is enhanced.

The invention discloses an image watermarking method for a stable diffusion model, and the method comprises the steps: selecting one of all potential features in a reverse diffusion process of the stable diffusion model as a target potential feature, and constructing an image watermark generation recognition model which comprises a watermark information embedding module and a watermark extraction module; the watermark information embedding module is used for embedding user watermark information into the target potential features, and inputting the obtained watermark target potential features instead of the original target potential features into the remaining sub-models of the stable diffusion model to generate a watermark image; and the watermark information extraction module is used for extracting user watermark information from the watermark potential features obtained by carrying out DDIM inversion on the watermark image, and the user generating the watermark image can be identified according to the extracted user watermark information. According to the method, the user watermark information is embedded into the potential features of the stable diffusion model, so that the image traceability with high robustness and high concealment is realized on the premise of not damaging the quality of the generated image.

The invention discloses a medical image robust watermarking algorithm based on a re-parameterized high-efficiency attention network, and relates to the field of image data processing methods, and the algorithm comprises the steps: obtaining an original medical image; a pre-trained RepEA-Net model is used for extracting multi-scale deep features with good generalization performance from an original medical image, and then a mean perceptual hash algorithm is used for generating feature vectors. Obtaining an original watermark image; the watermark image is encrypted by using a Logistic chaotic encryption algorithm, the security of the watermark image is improved, and finally, the encrypted watermark image and the binary feature vector are subjected to XOR operation to generate the zero watermark. Through the innovative design of the re-parameterization efficient attention network, the contradiction among robustness, generalization and image integrity of a traditional medical image watermarking algorithm is broken through, and a solution with technical advancement and clinical practicability is provided for copyright protection and safe transmission of medical images in the medical Internet of Things.

The invention discloses an image watermarking method and system based on decoding guided by a self-supervised visual model. The method comprises the following steps: acquiring watermark information m and an original image I of each data sample in a training data set; for each data sample, preprocessing the watermark information m to generate a message tensor M, and performing degradation distortion processing on the original image I to generate a distortion guide heat map DGH, thereby obtaining a preprocessed training data set; and performing self-supervising training on the self-supervising visual model by using the preprocessed training data set to finally obtain the trained self-supervising visual model. The invention aims to solve the problem that the decoding robustness is poor when the mask prediction is inaccurate due to the fact that the existing printing-resistant shooting watermark technology excessively depends on the positioning mask, and the semantic comprehension capability of the depth vision model is utilized to replace the traditional geometric synchronization, so that the end-to-end robust decoding without correction is realized.

The invention discloses a screen watermark embedding method and device based on deep learning, and relates to the technical field of image watermark embedding. Obtaining a to-be-displayed original image and an original watermark image; inputting the original image into a preset adaptive intensity prediction network to obtain a current embedded intensity graph; according to the current embedding strength graph and the original watermark graph, additive watermark embedding is carried out on the original image, and an image with a watermark is obtained; calculating the image with the watermark and the original image to obtain an image quality evaluation value; if the image quality evaluation value meets a preset quality threshold value, outputting the currently generated image with the watermark as a final embedding result image; and if the image quality evaluation value does not meet the preset quality threshold value, multiplying the current embedding strength graph by an attenuation coefficient, and taking the attenuated embedding strength graph as a new embedding strength graph. By implementing the provided technical scheme, the problem that the image quality is difficult to accurately control by a fixed model is solved.

The present application proposes an image watermark generation method, an image watermark generation device, and a computer storage medium. The image watermark generation method includes: obtaining the original latent features of the original image; fusing the watermark information of the same size as the original latent features with the original latent features to obtain fused latent features; obtaining the pixel-level visual sensitivity mask parameters of the original image; adjusting the watermark intensity of the fused latent features using the pixel-level visual sensitivity mask parameters to obtain the adjusted latent features; generating an image watermark based on the adjusted latent features; and generating a watermarked image based on the image watermark and the original image. Through the above-mentioned image watermark generation method, the pixel-level visual sensitivity mask parameters are used to adaptively adjust the watermark embedding strength, thereby achieving global coordinated adaptation of the watermark energy distribution and the image visual characteristics, and significantly improving the robustness of the watermark against complex attacks.

The invention relates to the technical field of digital watermarking, in particular to a watermark embedding and extracting method and device based on deep learning. According to the vector character watermark embedding and extracting method based on the multi-modal features, information redundancy and complementation are provided through multi-modal feature fusion, and a loss function system (particularly a triple, redundancy and anti-loss) with extremely high robustness is constructed, so that vector character watermark embedding has high anti-attack capability.

The invention relates to an implicit black box watermarking method for copyright protection of a multi-modal model, and belongs to the technical field of artificial intelligence safety. The method specifically comprises the following steps: 1, generating a multi-modal model black box backdoor trigger; 2, completing model training of a conversion module according to the backdoor trigger set in the step 1; and 3, performing ownership verification and infringement model judgment on the suspicious model according to the backdoor trigger set in the step 1 and the conversion module in the step 2. According to the method, the resistance trigger is generated by adopting the original samples in the original data set, the limit of an existing distributed external trigger is broken, the method can adapt to a real application scene of a multi-modal model under the condition of small overhead, and the method has good practicability and expandability. In addition, two-stage watermark verification based on a conversion module is adopted, so that the infringement problem caused by hostile attacks can be effectively avoided.

The invention discloses an anti-printing and anti-scanning digital watermark method for a text image, which comprises the following steps of: embedding and extracting a watermark on the basis of a stroke-like thought, segmenting characters and determining the average skeleton quality ASM of each character during embedding, and forming a group by every two characters, changing the ASM of each group of characters according to the to-be-embedded information to embed the watermark and replace the corresponding characters of the source document; during extraction, two characters are also taken as a group, ASM is extracted, and watermark information is extracted by comparing ASM among the characters, so that 1-bit information can be embedded into the two characters, the language type and font of the characters are not limited, the watermark information amount of the document is ensured, and meanwhile, the watermark information is extracted. The problems that algorithms among different languages are limited, and the robustness is poor and the capacity is small when digital watermarks in a space domain and a transform domain resist printing and scanning attacks are effectively solved.

The invention discloses a copyright protection method and device for a potential diffusion model based on a frequency domain watermark, and the method comprises the steps: carrying out the preprocessing of a training data set and a copyright protection watermark, carrying out the Fourier transformation, and embedding the watermark into the training data set in a frequency domain space; the watermark extractor is pre-trained and divided into two stages, a discriminator is trained firstly to judge whether the output of the watermark extractor contains the copyright protection watermark, then the watermark extractor is trained, and the copyright protection watermark is extracted by optimizing network parameters; then, a decoder is finely adjusted in the potential diffusion model, so that the generated image contains a copyright protection watermark which can be extracted by a watermark extractor; in practical application, when a third-party user uses the model to generate an image, a model owner can extract the watermark in the image through the watermark extractor, and through comparison with a copyright protection watermark, copyright protection of the model is realized. According to the method, the copyright verification efficiency is improved, and infringement behaviors can be quickly and accurately found.

The invention provides a digital image watermark embedding method, a digital image watermark extracting method and electronic equipment. The digital image watermark embedding method comprises the following steps: constructing an image watermark embedding network model and an image watermark extracting network model; jointly training an image watermark embedding network model and an image watermark extraction network model; training an image watermark embedding network model; the image watermark embedding network model is used for embedding watermarks, and the image watermark extraction network model is used for extracting the watermarks. During training, the image watermark embedding network model and the image watermark extraction network model are jointly trained, so that the robustness can be improved. And through joint training, a confrontation relationship is formed between the invisibility and the robustness, and finally, an optimal balance point is found between the invisibility and the robustness.