72 results about "Image steganography" patented technology

The invention discloses a generative image steganography method and system based on a diffusion model and face key points, and relates to the technical field of image steganography, and the method comprises the steps: inputting secret information needing to be hidden into a pre-trained face key point generative adversarial network, and automatically selecting face key points based on a face key point selection coding strategy, the secret information is coded into the face key points, and a face key point image of the coded secret information is generated; inputting the face key point image of the coded secret information into a diffusion model as a condition, and generating a secret-carrying face image corresponding to the face key point image by guiding the diffusion model; obtaining a secret-carrying face image, and extracting face key points in the secret-carrying face image by using a Dlib model; and inputting the extracted face key points into a face key point generative adversarial network, selecting a coding strategy based on the face key points, and recovering secret information through an inverse process of secret information coding. According to the invention, the detection resistance and safety of the steganography system can be improved.

The invention discloses an image hiding method based on a space-channel attention mechanism and a related device, and belongs to the technical field of image hiding. The method comprises the following steps: inputting a secret image and a carrier image into a pre-trained image hiding network model to obtain a secret-containing image and loss information, and completing image hiding; the image hiding network model is an image hiding network model based on a space-channel attention mechanism and comprises a preprocessing network, a hiding network and an extraction network; the hidden network takes a reversible neural network as a basic framework, forward propagation and reverse propagation processes of the reversible neural network are modeled as encoding and decoding processes of an image according to the requirement of an image steganography task, and reversible hiding and high-quality extraction of a secret image are realized in combination with DWT (Discrete Wavelet Transform).

The invention discloses a generative image steganography method and device based on Stable Diffusion and discrete wavelet transform, and the method comprises the following steps: S1, sampling a potential representation of a to-be-generated image through employing a Stable Diffusion diffusion model, embedding secret information into a potential space of the diffusion model, processing the potential representation through employing discrete wavelet transform to carry out frequency domain information modulation, and carrying out the frequency domain information modulation; obtaining the potential representation after the secret information is embedded; s2, inputting the potential representation embedded with the secret information into a diffusion model, and generating a visual natural steganographic image through a diffusion inversion process; s3, inputting the received steganographic image into a diffusion model, and decrypting the received steganographic image without original model weight modification and empty prompt conditions to obtain embedded secret information; according to the method, the frequency domain embedding technology is combined with the potential diffusion model, so that high-fidelity, high-capacity and high-robustness image steganography is realized.

The invention discloses enhanced image steganography based on multi-scale cavity fusion iterative optimization, which is suitable for the field of image steganography and comprises the following steps of: after acquiring an enhanced image E corresponding to a cover image C by using the cover image C, respectively performing feature extraction on the enhanced image E, and then introducing an attention mechanism of multi-scale cavity fusion; fusing the features of the two images to obtain an image X; then connecting with a secret to form a secret-carrying tensor M; the encoder receives three inputs: the feature of the image M, the current disturbance and the gradient of the loss function of the disturbance are spliced to form the input of a GRU unit; a steganographic image is finally generated by repeatedly applying the encoder; the decoder receives the steganographic image generated by the encoder, and original hidden information is recovered from the steganographic image through a series of convolution; the critter network evaluates the naturalness of the generated steganographic image and provides feedback; and repeating the steps 2-5. The finally generated image is the steganographic image containing the hidden information. According to the method, a learning method and an iterative optimization method are combined, and a multi-scale fusion attention mechanism is combined under the enhancement of a dual-channel input image, so that a part which is more suitable for hiding information in the image is found, and the generated steganographic image is more hidden.

The technology described adds a ML inference to the output of an image signal processor (ISP) associated with a camera. The combined image and ML inference may be described herein as an augmented image. Once generated, the augmented image may be communicated to other components of a computing system associated with the camera and / or ISP. The initial inference may be generated by a neural processing unit (NPU) associated with the ISP. The ISP may communicate a generated image to the NPU prior to communicating the image to a computing system. In an aspect, the NPU inference is combined with the image using image steganography. Once communicated from the camera to the computing device, the augmented image may be separated into a base image and inference by a camera driver or other component associated with the image management.

The invention discloses a cross-modal generative image steganography method based on a diffusion model, which comprises the following steps of: firstly, constructing and pre-training a reversible diffusion model, a stable diffusion model and a variational auto-encoder VAE, and deploying the reversible diffusion model and the pre-trained stable diffusion model to a sender and a receiver; deploying a VAE decoder in a variational auto-encoder VAE to a sender, and deploying a VAE encoder to a receiver; a sender maps a secret image into Gaussian potential representation by adopting a denoising diffusion model, inputs a stable diffusion model and a VAE decoder to generate a steganographic image under the prompt of a text key, and then sends the steganographic image and an encrypted text key to a receiver; and the receiver decrypts the text key, maps the steganographic image into a potential representation under the prompt of the text key by adopting a VAE encoder and a stable diffusion model, and recovers the secret image by adopting a reversible diffusion model after extracting the potential representation of the secret image from the steganographic image. According to the method, cross-modal image steganography can be realized on the basis of completely controlling the content of the steganography image.

The invention discloses a medical image steganography method and system based on a reversible deep network, and aims to solve the defects that in the prior art, the steganography capacity is limited, and a multi-modal medical image scene is difficult to adapt. The method designed by the invention comprises the following steps: receiving an original medical image and secret information to be embedded; normalization and spatial alignment are carried out on the medical image; inputting a multi-scale feature extraction network, extracting low-layer texture features, middle-layer edge features and high-layer semantic features, and splicing in channel dimensions to form fusion features; the fusion feature and the encrypted secret information are spliced and then input into a reversible neural network encoder to generate a steganographic image; reversely extracting fusion features and encrypted information through a reversible neural network decoder, and reconstructing an original medical image and secret information; optimizing the network performance by adopting a structure-aware joint loss function; the method can be applied to safe storage of medical images, multi-center cooperation and medical block chain evidence storage.

The invention relates to the technical field of image encryption, and discloses an image steganography method and system based on dynamic latent variables and frequency domain embedding, and the method comprises the steps: obtaining a hash value and a plurality of secret keys of a to-be-encrypted color plaintext image; constructing a hyperchaotic system, and iteratively generating a plurality of key streams; a to-be-encrypted color plaintext image is decomposed into R, G and B channel matrixes, and three ciphertext sequences are obtained based on the three channel matrixes; the method comprises the following steps: initializing a noise image, determining a time step by using a secret key, and executing reverse denoising of a denoising diffusion implicit model (DDIM) with a fixed step length to obtain an intermediate latent variable; based on the intermediate latent variable and the three ciphertext sequences, obtaining a dense frequency domain-containing sub-band, and performing inverse discrete wavelet transform on the low-frequency sub-band and the dense frequency domain-containing sub-band to obtain a dense latent variable; and executing DDIM denoising of the time step by taking the secret-containing latent variable as a starting point to obtain a secret-containing image. By adopting the method, the security and visual quality of image steganography can be improved, and high embedding capacity is ensured.

The present application is a backdoor attack method based on image steganography, comprising: S1, constructing an image steganography network and an image transformation network; S2, performing spatial transformation on a poisonous image to obtain a first trigger; S3, inputting the spatially transformed poisonous image back into the attack network to restore it to obtain a second trigger; S4, constructing a steganalysis loss function of the image steganography network based on the distance loss between the first trigger and the second trigger; S5, iteratively training the image steganography network; S6, performing a backdoor attack using a poisonous image. When training the steganography network, a loss function is constructed based on the degree of deformation of the trigger, and the image steganography network generates a poisonous image that can adapt to image transformation through the back propagation of the loss function. The poisonous image generated by the present application can trigger an attack in the victim model even after image transformation processing, so that the victim model recognizes the corresponding target label.

The invention relates to the technical field of image information security, and discloses a controllable image steganography method and system based on a steganography diffusion model. Comprising the following steps: acquiring a hash value of a color plaintext image, and obtaining a plurality of random sequences according to the hash value and three-dimensional memristor chaotic mapping; decomposing the color plaintext image into three channel matrixes, and performing scrambling and diffusion operation on the channel matrixes based on a random sequence to generate a color ciphertext image; adding noise to the carrier image to obtain a preprocessed carrier image; obtaining a plurality of wavelet coefficient matrixes according to the preprocessed carrier image; generating a ciphertext-containing wavelet coefficient matrix according to the color ciphertext image and the wavelet coefficient matrix; performing inverse discrete wavelet transform on the confidential wavelet coefficient matrix to obtain a noisy and confidential carrier image; and de-noising the noisy and confidential carrier image by using the steganography diffusion model to generate a final confidential carrier image. According to the method, the visual quality of the carrier image can be ensured, steganography analysis is effectively resisted, and the image steganography safety is improved.

The invention belongs to the image processing technology, and particularly relates to a safe and available visual anonymization pedestrian privacy protection method and system, and the method comprises the steps: constructing an image reconstruction network which employs a conditional variation auto-encoder and a structural feature encoder to extract appearance features and structural features from an original image, the method comprises the following steps: extracting structural features in an image, enabling an appearance feature decoder to randomly generate appearance features according to the distribution of the appearance features in the image, inputting the randomly generated appearance features and the extracted structural features into a generator to obtain an anonymized image, and writing the extracted appearance features into the anonymized image based on an image steganography technology to obtain a reversible anonymized image. According to the method, the original pedestrian information is decoupled and then subjected to style migration, so that the feature change of the pedestrian is realized, the effect of changing the clothes by the pedestrian is visually presented, and the balance between privacy protection and availability is effectively solved.

This invention relates to an adaptive image steganography transmission and reception method, belonging to the field of image steganography technology. Before steganography using a steganography model, the invention first expands the image to be steganized (the secret image) and the carrier image according to the input size of the steganography model, making them a square with the same size as the input size of the steganography model. The excess parts are then filled with a solid color. The images are then segmented and scrambled before being input into the steganography model for processing. Finally, the outputs of the steganography model are merged, and the excess parts are cropped. Similarly, during reception, the image is processed in the same way. Therefore, the steganography model of this invention can support images of various sizes, ensuring the security and invisibility of the steganography model while improving its practicality and generalization ability; it also avoids the problem of poor steganography image quality due to image size mismatch.

The invention discloses a self-adaptive asymmetric image steganography method and system based on a diffusion model, and relates to the field of artificial intelligence and information security. According to the method, the corresponding cumulative distribution probability is calculated according to the noise to be embedded, then the secret information is embedded by slightly modifying the cumulative distribution probability, and the Gaussian noise after the information is embedded is obtained by using the inverse cumulative distribution function, so that the probability distribution of the embedded Gaussian noise is kept unchanged. Before actual embedding, simulation embedding is carried out in noise to be embedded, processes of simulation embedding + 1 and-1 are respectively completed to eliminate pixel points of which information cannot be correctly extracted, and modifications introduced by embedding + 1 and-1 to the noise are calculated. And then the asymmetric steganography embedding cost of each pixel point is obtained through calculation according to the modification amount, then secret information is embedded into cumulative distribution of Gaussian noise, and finally a reverse process is completed and a secret-carrying image is generated and obtained. The problem that an existing steganography method is insufficient in detection resistance and imperceptibility is solved.

The application discloses a kind of based on parallel confrontation's generative image steganography method, system, electronic equipment and computer readable storage medium, belong to image steganography technical field.The application proposes a kind of based on adding channel attention mechanism U-Net structure generation confrontation sample, enhance the security of multiple confrontation network architecture of existing steganography method, original image is generated by generator generation confrontation noise, and confrontation noise is reasonably distributed to original image to generate confrontation sample, and the steganography image generated by using the generated confrontation sample as carrier image through existing steganography algorithm can resist the detection of several most advanced steganalysis of present time;Solve the problem that " cannot resist the simultaneous detection of multiple steganalysis and cannot resist the detection of most advanced steganalysis of present time" in prior art.

The present invention provides a method for improving the efficiency and security of image steganography by utilizing a reinforcement learning algorithm and a GAN model, comprising the following steps: performing image steganography pre-training using a GAN model. Utilizing the Div2K dataset as the original cover image and selecting a random information set, the model is enabled to obtain a steganographic image similar to the original image; and optimizing the steganographic parameters using a reinforcement learning algorithm. Initial parameters are randomly confirmed, and then the optimal parameters are selected and replaced based on the pre-training results; and the GAN model is trained and the image steganography effect is evaluated. Image steganography is implemented using the pre-trained model and the optimal parameters, and the performance is evaluated based on the steganographic performance and steganographic security. The present invention effectively improves the efficiency of the steganographic task by selecting a suitable steganographic method based on an analysis of the task situation, including embedded information and original image features.

The invention belongs to the crossing field of information hiding and digital image processing, and particularly relates to an image steganography method and system based on frequency domain transformation and a reversible neural network, and the system comprises a wavelet transformation module which is used for executing frequency domain decomposition of a carrier image, a secret image and a steganography image, the inverse wavelet transform module is used for executing reconstruction from frequency domain features to pixel domain images, the reversible network is used for realizing reversible conversion of 24-channel fusion features, the reversible network is formed by sequentially connecting 16 GlowBlocks in series, and each GlowBlock comprises an activation standardization layer, a reversible 1 * 1 convolution layer and an affine coupling layer which are cascaded. According to the method, through the cooperation of the frequency domain feature hierarchical modeling and the reversible network, while the steganography reversibility is ensured, the visual difference between the steganography and the original carrier is remarkably reduced, the recovery precision of secret information is improved, and the method is suitable for image steganography scenes with high requirements for reversibility, concealment and recovery quality.

The present invention relates to a method and system for encrypted domain image steganography based on Huffman coding. The method comprises: obtaining the pixel value of each pixel block in the original image and encoding it based on Huffman coding to obtain an initial code table; encrypting the secret information based on an encryption algorithm to obtain encrypted data; embedding the encrypted data based on a least significant bit algorithm to obtain an embedded pixel value for each pixel block; and updating the initial code table based on the embedded pixel value to obtain an embedded code table. The present invention reduces the total number of bits of transmitted data and increases capacity, thereby increasing the amount of information embedded without affecting image distortion and providing high security.

This invention relates to the field of image steganalysis defense technology, and particularly to an active image steganalysis defense method and system based on signal enhancement. The method involves adding interference noise to the image to be processed based on signal texture features to enhance the stegana signal. The enhanced image is then input into a pre-trained active image steganalysis defense network. This network restores the stegana signal features and recovers the original carrier image from the processed image through an inverse difference operation. The active image steganalysis defense network employs a dual-channel parallel network model to reconstruct the stegana signal distribution by mining the correlation and spatial relationships between the stegana signals. This invention does not require knowledge of the steganalysis algorithm type and embedding rate. Through image noise addition and neural network modeling, it achieves dual destruction of secret information in the image under a heterogeneous balance state, while simultaneously restoring the quality of the original image.

The invention discloses a generative image steganography method based on robust position mapping. According to the technical scheme, a steganography system composed of a run length coding module, an initial Gaussian noise generation module, a candidate pool processing module, a pseudorandom sequence generation module, an index sorting module, an information embedding module and a stable diffusion model SD is constructed. The run length coding module carries out run length coding on the secret information to obtain a two-tuple Y; an initial Gaussian noise generation module generates a Gaussian noise tensor zinit; the candidate pool processing module performs positive and negative value division on the zinit; the pseudo-random sequence module generates a random sequence P, and an index matrix S'is obtained through the index sorting module. The information embedding module embeds the secret sequence after run length coding in the Y into an empty tensor zemed to obtain a tensor zemed conforming to Gaussian distribution; and the SD carries out denoising on the zzzled and decodes the zzzled to generate a steganographic image. According to the method, the secret information extraction accuracy and steganography capacity can be effectively improved.

The invention provides a method and device for image steganography information detection, a twin neural network system and a method and device for training the neural network system. The detection method comprises the following steps: separating a to-be-identified image into at least three color channels, and respectively constructing image vectors based on each color channel based on the at least three color channels; combining the image vectors of the at least three color channels in pairs to form image vector pairs of two color channels in the plurality of color channels; respectively inputting the image vector of each color channel in the image vector pairs of the plurality of color channels into a trained twin neural network to generate the similarity between the image vector pairs of each color channel; and determining whether steganography information exists in the to-be-identified image based on the similarity between the generated image vector pairs of each color channel.

This invention discloses a reversible image steganography method based on multi-scale feature enhancement and dynamic attention. First, discrete wavelet transform is performed on the carrier image and the secret image to obtain multi-channel wavelet domain features. Then, these features are input into multiple parameter-shared reversible hidden blocks. During the coupled transform process, a multi-scale spatial information enhancement module and a dynamic attention feature refiner module are introduced to extract local and global contextual information and dynamically adjust the importance of channel and spatial features, achieving high-quality embedding of the secret information. Finally, the cryptic image is obtained through inverse wavelet transform. In the inverse recovery stage, the cryptic image and auxiliary variables are input into a symmetrical reversible recovery path to separate and reconstruct the recovered secret image and the recovered carrier image. This invention achieves near-lossless recovery of the secret information while maintaining high visual quality, significantly improving the concealment and recovery accuracy of steganography.

The invention discloses an adaptive image steganography method based on a generative adversarial network, which is suitable for the field of image steganography, and comprises the following steps: obtaining a cover image C and secret information M, and embedding the secret information into the cover image through an improved CSPNet encoder to generate a steganography image S; the decoder d receives the steganographic image S and extracts secret information M'through a symmetric CSPNet architecture; and a reviewer network C. The distribution consistency of the steganographic image and the real image is evaluated, and an optimization signal is fed back by using a Wasserstein loss function; an MSE targeting technology is introduced, hyper-parameters are dynamically adjusted through linear fitting, and the mean square error of the steganographic image and the cover image is controlled within a target range; a soft label loss function is adopted to prevent network overfitting; reed-Solomon coding is firstly carried out on secret information, and the information is ensured to be completely recovered through an error correction mechanism; and repeating the training process until the steganographic image meets the transparency and capacity requirements. According to the method, deep learning and a steganography technology are combined, part of calculation paths are separated through a CSPNet architecture, and the feature extraction capability is kept while the calculation complexity is reduced by 30%; the MSE targeting technology realizes dynamic balance of capacity and transparency, and relatively high hiding capacity is realized on a DIV2K data set; the soft label is combined with Reed-Solomon coding, so that the decoder is high in recovery accuracy under the large pixel depth; the local features are monitored by the reviewer network, the steganographic image is forced to keep natural distribution, and the invisibility and robustness of the steganographic image are effectively improved.

This invention discloses an image steganography method, apparatus, electronic device, and storage medium. The method designs a Res-SS2D module, which, through four-way global spatial modeling, improves the quality of the secret image while maintaining linear complexity. A high-frequency feature enhancement strategy is proposed. By extracting the edges of the carrier image and fusing them into the encoder, the secret information is preferentially embedded in high-frequency regions, reducing the likelihood of detection by steganalysis. A multi-objective loss function is designed, combining PSNR and MS-SSIM to optimize generation quality. The L1 norm loss of the low-frequency components is used to constrain the low-frequency consistency between the carrier and the secret image, ensuring that the secret information is preferentially hidden in the high-frequency components. This invention provides an efficient and secure solution for image steganography.

The invention discloses a high-capacity image steganography method and system based on multi-stage learning and a medium. The method comprises the following steps: acquiring an image to be processed; and inputting the to-be-processed image into a pre-trained multi-stage learning high-capacity depth image steganography model, and obtaining a target image output by the multi-stage learning high-capacity depth image steganography model. From two perspectives of contrast refinement and multi-scale adjustment, a multi-stage adjustment high-capacity image steganography network is designed, and by designing an optimization stage from coarse to fine in a hiding process, multi-stage iterative optimization is realized, and the modeling capability of a model in a high-capacity steganography condition is improved.

The application discloses a kind of based on image space random distribution lossless secret image steganography and extraction method, specifically is: using space technology in carrier image pixel low 4 place write secret information, the pixel value of secret image is using random sample to break up pixel order before embedding carrier image, for the embedding position of secret image in carrier image, using key generation random uniform distribution pixel position;Image extraction method, 16 bits character is extracted from the end of key, decode as the width and height value of secret image, through key generation secret image pixel position random sample and secret information embedding position in carrier image, extract secret information from embedding position, and restore each pixel of secret image, generate the secret image after restoration.The beneficial effects of the present application are: the present application can be used for covert information and the like Hidden transmission, with lossless extraction, embedding capacity is larger, information security is good, not easy to detect, the characteristics such as small consumption of computing power.

This invention discloses an image steganography method and system based on the NICE model. The method comprises: constructing the NICE model, acquiring an image dataset to train the NICE model; after training, reversing the generator in the NICE model to obtain an extractor; directly generating a secret image from a secret message using the generator; and extracting the secret message from the secret image using the extractor to retrieve the secret message. The images generated by this method fully match the data distribution of real images, making it difficult for machines and humans to verify their authenticity. Therefore, the secret images generated by the model cannot be detected by steganalysis tools based on probabilistic statistics, making them theoretically more secure.

The invention provides a generative image steganography method and system based on a diffusion model and multiple encryption. The method comprises an encryption step and a decryption step. The encryption step comprises the following steps of: A1, converting an input image into a potential code through a VAE encoder; a2, performing forward diffusion on the potential code to obtain a noise vector, and further disturbing the noise vector to obtain a disturbed noise vector; a3, projecting the disturbed noise vector to a new vector space, and generating a reference image through a key and a cue word; step A4, carrying out back diffusion on the noise vector after projection to obtain a steganographic image; and a decryption step: decrypting the steganographic image according to the reference image, the prompt word and the key, and recovering to obtain an input image serving as an original image. According to the method, the information amount of a far hypertext steganography method can be borne, the bottleneck faced by traditional generative steganography when a large data amount is hidden is solved, and the effective load of a steganography channel is remarkably improved.

This invention discloses a generative image steganography method based on a conditional diffusion model, SD-Stego. The algorithm is based on the Guided-Diffusion model, using controllable conditional text as input. During the inverse generation process of the latent diffusion model, an embedding and encoding strategy is designed. DenseNet deep connections and SEBlock channel self-attention mechanisms are introduced to fuse the intermediate generation in the latent space with the message matrix, achieving efficient embedding of steganographic information. Then, a frozen VAE decoder completes the steganographic image generation. In the decoding stage, a multi-layer convolutional network is used to extract high-level features of the generated image layer by layer. Batch normalization and non-linear activation functions are combined to extract embedded information, and the information is gradually mapped through flattening and fully connected layers, finally outputting the decoded message vector. To optimize the steganography effect and generation quality, a joint loss function is designed, including decoding loss and image quality loss, ensuring the stealth of the generated image and the accuracy of message decoding. This invention enables steganography without the need for a carrier image, making it suitable for information security and data steganography. By utilizing denoising generation and text guidance through a conditional diffusion model, the steganography process exhibits advantages such as high robustness, excellent image generation quality, and controllability of generated content. It is more suitable for complex real-world scenarios (such as social network transmission) and has broad application prospects.

The invention discloses an application of double-flow U-Net in security image steganography based on edge guidance, which is suitable for the field of image steganography, and comprises the following steps: firstly, carrying out edge detection enhancement on a carrier image by using a Sobel operator, and generating an edge enhanced image to provide texture details; an original image and an enhanced image serve as double-flow input, features are extracted through independent contraction paths respectively, and then edge and global information is fused in a shared expansion path. A multi-scale median attention mechanism is introduced into each layer to enhance steganography related features and suppress redundancy, and an InceptionDWK module is further embedded into an enhancement channel to capture multi-scale features. And iteratively optimizing the fused features and secret information through a dense convolution block and a GRU unit to generate a steganographic image. And the decoder extracts hidden information from the steganographic image by using a lightweight convolutional network. The discriminator distinguishes the cover and the steganographic image, and the concealment is improved through adversarial training. According to the method, the information hiding area is optimized through double-flow input and multi-scale attention, and the visual concealment of the steganographic image is remarkably improved.

The invention provides an image steganography method, device and equipment for user level-to-level management, and a medium, and the method comprises the steps: carrying out the compression of a DWT coefficient of a plaintext image through employing a compressed sensing technology, carrying out the partitioning, and dynamically setting a differentiated threshold value for each image block through employing a threshold secret image sharing method; and in combination with a double-image embedding method, the image is steganographically written into a carrier image, and finally a ciphertext image with visual significance is generated. And different threshold values are set for different image blocks, so that hierarchical steganography and extraction of the image are realized. When the number of users participating in decryption is smaller than a set threshold value, any effective information related to the plaintext image cannot be obtained; when the number of the users participating in decryption is greater than or equal to the threshold value, the related information of the plaintext image can be obtained, and the reconstruction quality of the plaintext image is improved along with the increase of the number of the users participating in decryption.