65 results about "Forgery detection" patented technology

This invention presents a face forgery detection method based on a query-driven forensic adapter, belonging to the fields of artificial intelligence and machine learning. It aims to address issues such as insufficient modeling of local forgery regions, limited interaction between semantic and visual features, and poor cross-distribution generalization performance. First, this invention proposes a dynamic semantic query module. This semantic query is injected as a dynamic attention signal into the multi-head attention mechanism of the CLIP encoder, effectively guiding CLIP to focus on potential forgery regions, improving its response to local anomalies such as boundary discontinuities and texture inconsistencies, and compensating for its insufficient local modeling capabilities without altering the CLIP's core structure. Second, this invention proposes a multi-scale feature aggregation mechanism. It proposes a semantically guided attention fusion module and a feature enhancement strategy based on linear interpolation. This method can effectively improve sample diversity and enhance the model's robustness and generalization ability across forgery methods and datasets.

The application discloses a kind of face depth forgery detection methods based on multi-modal fusion, belong to artificial intelligence, computer vision and multimedia forensics field.For the generalization deficiency of existing detection method, audio and picture time sequence inconsistency problem, end-to-end detection scheme is proposed.The method fuses the time-aligned audio spectrum and continuous video frame mosaic picture in advance, forms multi-modal unified input to solidify audio and picture time sequence relationship.Global branch uses contrast learning pre-training visual Transformer, introduces modal bias and cross-modal attention bias to enhance feature distinction interaction;Local branch fuses local and global features through multi-scale region perception network, realizes adaptive weighted fusion by combining position coding, vector-level channel attention and scale attention, and is guided by region perception auxiliary loss to select discriminative features.The method provides an effective tool for content review, traceability forensics and identity authentication security.

This application provides a text-guided method and system for detecting face forgery. The method includes obtaining a face image to be detected (whether it is genuine or fake), inputting the face image into a face detection model to obtain the face authenticity detection result. The face detection model includes: constructing a text prompt lexicon covering multiple granularities and generating multi-dimensional text prototypes; extracting visual features, optimizing the feature distribution of visual features to obtain global visual features; performing feature separation and enhancement on the global visual features; mapping the global visual features after feature separation and enhancement to predicted text features; applying similarity constraints to obtain cross-modal prototype matching results; applying discriminative constraints on different-dimensional text prototypes to obtain feature measurement learning results; and outputting the detection result based on the cross-modal prototype matching results and feature measurement learning results. This method solves the problem of poor generalization in face forgery detection and improves detection accuracy and generalization ability.

The application discloses a face forgery detection method and system based on federal incremental learning, comprising the following steps: constructing a federal incremental learning framework, each client is provided with a local face forgery detection model, and a global server is provided with a global face forgery detection model; the local face forgery detection model is subjected to cross-entropy training in a basic training stage, generates a forgery substitute sample in an incremental training stage, and is used as training input together with a real face sample and a forged face sample; after training, the model parameters are uploaded to the global server for aggregation; the global face forgery detection model is updated based on a difference perception aggregation strategy; an adversarial perturbation is trained based on the global face forgery detection model converged in the present stage and the real face sample, and a perturbation pool is refreshed until a preset termination condition is reached; and a to-be-tested face image is identified as real or fake based on the trained global face forgery detection model. The application can relieve catastrophic forgetting and improve cross-task generalization ability and robustness.

The present application belongs to the field of computer vision and image processing, aiming at the double bottleneck of "semantic overfitting" and "space-frequency feature mislocation" existing in the existing deep fake detection, the present application proposes a deep fake face detection method based on dual domain. The present application constructs a dual domain complementary architecture of dual domain deep fake detection network DDSF-Net based on semantic suppression and space-frequency alignment, the micro mark difference module in the network significantly enhances the residual subtle fake artifacts between pixels by eliminating redundant face attributes. And the space-frequency mapping module uses the block transformation strategy to adaptively mine the abnormal distribution of frequency domain, realizes the multi-dimensional enhancement of the fake features. At the same time, through the complementary fusion of dual domain features, the detection accuracy and generalization are effectively balanced. Extensive experiments on multiple benchmark datasets show that the performance of the method in the same dataset and cross dataset scenarios is significantly better than that of the existing advanced technology.

The present application relates to the technical field of image processing, and particularly relates to a medical image detection method based on multi-scale local mapping, which is specifically as follows: collecting medical images and generating fake medical images, and constructing a medical image dataset containing real and fake medical images; the medical images to be detected in the medical image dataset are input into a trained medical image fake detection model after pretreatment, and a detection result is obtained; wherein the medical image fake detection model comprises a sparse feature extractor, a fine-grained feature extractor, a frequency domain self-attention module, a multi-scale feature mapper, a local positioning filter and a fake determinator; the trained model calculates a loss function based on the detection result and a real result, and dynamically adjusts the parameters in the model by using an Adam optimizer. The present application can extract more fine local features, identify subtle fake traces, and improve the accuracy and efficiency of fake detection.

The embodiment of the invention discloses a training system of an anti-counterfeiting detection model, a sample generation agent responds to a sample generation instruction input by a controller and generates a scheme for manufacturing a forged certificate image, so that an automatic robot platform manufactures the forged certificate image based on the scheme and inputs the forged certificate image as a negative sample into the anti-counterfeiting detection model; the anti-counterfeiting detection model performs anti-counterfeiting detection on an input negative sample to obtain a detection result, and the controller adds the negative sample into the sample library when the detection result is that the negative sample is a normal certificate image, and subsequently uses the negative sample collected in the sample library to train the anti-counterfeiting detection model. Through the system, the negative samples which can break through anti-counterfeiting detection can be searched by utilizing the sample generation model, and the negative samples which break through the anti-counterfeiting detection are utilized to train the anti-counterfeiting detection model, so that the anti-counterfeiting detection model can detect a forged certificate image more accurately subsequently, and the security of online business based on eKYC is effectively improved.

This invention discloses a multimodal deepfake detection method for digital humans based on hue consistency analysis. A training dataset is obtained from real human speaking videos. A multimodal deepfake detection model based on hue consistency analysis is constructed. Speech features, visual features, and red hue features are extracted from the input video. The red hue features are fused into the visual features to obtain red hue visual features. Then, the speech features and red hue visual features are fused, and a matching score matrix is ​​generated based on the fused features. The multimodal deepfake detection model is trained using the training dataset. The trained multimodal deepfake detection model generates a matching score matrix for the video to be detected. The matching score matrices are then aggregated to obtain the overall matching score of the video to be detected, thereby achieving forgery detection. This invention can significantly improve the accuracy and generalization ability of speech and visual deepfake detection.

This invention proposes a deep face forgery detection method based on multi-level collaborative perception of forgery traces. To enhance the balance of multi-scale forgery trace perception and compensate for the lack of inter-level collaboration, the method constructs a differentiated configuration multi-level forgery trace collaborative perception network. The network adopts a four-stage architecture, with each stage sequentially performing downsampling and differentiated configuration of multi-level perception to achieve adaptive multi-level perception at different depths. The multi-level perception module generates multiple feature subgroups through uniform channel decomposition; each subgroup is selectively input into global, structural, texture, and pixel-level sub-modules for targeted feature enhancement to capture forgery traces at different levels from macro to micro; and the multi-level features are collaboratively fused to form a comprehensive forgery trace representation. This invention significantly improves the perception capability and model generalization performance of diverse forgery traces under a lightweight architecture, making it suitable for efficient and accurate deep forgery detection tasks.

This invention proposes a video-based face forgery detection method and system that integrates artifact features and attention guidance to address the problems of existing methods failing to fully utilize artifact details in forged video frames and imprecise decision region selection. The method includes: data preprocessing, extracting a set of consecutive frames from the video and performing face recognition and alignment; artifact highlighting feature map generation, amplifying artifact details to enable the detection model to more sensitively capture forgery traces; attention feature extraction, guiding the network to focus on important regions for decision-making and discovering more valuable discriminative features; and feature map fusion, organically integrating artifact features and attention features to enable the backbone network to learn richer and more effective information. This method integrates artifact features and attention guidance mechanisms to perceive and enhance subtle differences in important facial regions in the video, providing a more accurate and reliable solution for video-based face forgery detection.

The application provides a picture forgery detection method, comprising: extracting frequency domain features and spatial domain features of a to-be-detected picture and a plurality of derived pictures, wherein each derived picture is generated after a first operation is performed on the to-be-detected picture, and the to-be-detected picture is a picture of a preset size; determining intermediate feature vectors of the to-be-detected picture and the derived pictures according to the frequency domain features and the spatial domain features, respectively; inputting the intermediate features into a true-false discriminator and a model tracer in parallel, wherein the true-false discriminator is a binary classifier, and the model tracer is a multi-class classifier; determining a fake or real detection result according to the intermediate feature vectors by using the true-false discriminator, and generating a multi-class probability distribution according to the intermediate feature vectors by using the model tracer, wherein the multi-class probability distribution refers to a probability distribution of a picture forged by a forgery model; outputting information indicating whether the to-be-detected picture is real or fake based on the detection result of the true-false discriminator and the probability distribution generated by the model tracer, and outputting the probability distribution at least in the case that the picture is fake. Corresponding systems, program products, and the like are also provided.

This invention discloses an audio forgery detection method based on a heterogeneous graph collaborative attention network. It constructs multi-view feature representations for the input audio and introduces latent style mixing and random feature recombination strategies during the input feature construction stage to weaken style perturbations irrelevant to forgery detection while retaining stable discriminative features across different views. Based on the enhanced multi-view features, a hierarchical heterogeneous graph neural network is constructed to aggregate and model the multi-dimensional semantic relationships between different views. Simultaneously, a bidirectional collaborative attention module is introduced to capture cross-view semantic dependencies, enhance complementary information interaction, and improve the robustness and discriminative ability of feature representations in complex environments. The system identifies real and forged audio based on the output audio forgery probability score. Compared with existing technologies, this invention exhibits superior detection performance, robustness, and generalization ability under unknown attacks, noise interference, and cross-domain testing scenarios.

The application discloses a digital person video detection method based on facial semantic features, acquires real person voice visual video to constitute a training data set; constructs a digital person video detection model based on facial reality mode representation, respectively extracts facial reality mode representation features, mouth features and voice features, after multi-modal feature fusion, generates a matching score matrix according to the fused features; trains the digital person video detection model by using the training data set, generates a matching score matrix by using the trained digital person video detection model, and aggregates the matching score matrix to obtain the overall matching score of the to-be-detected video, so that the forgery detection is realized. The application proposes a unified audio and video forgery detection framework based on the facial reality mode, and improves the deep forgery detection performance in different scenes.

The application discloses a counterfeit video detection method, device, equipment, medium and program product. The method comprises the following steps: acquiring at least two target image frames of a to-be-detected video; wherein the target image frames are obtained by screening based on the differences between different image frames in the to-be-detected video; acquiring image description information of the target image frames; performing a preset each authenticity detection task on target detection data of the to-be-detected video to obtain a detection result corresponding to each authenticity detection task; wherein the target detection data at least comprises the image description information; and determining a counterfeit detection result of the to-be-detected video based on each detection result. The application can identify the authenticity of the content of the to-be-detected video, avoid the training set coverage limitation caused by recognizing the visual attributes based on the face and the picture, has better generalization, and can further improve the accuracy of detecting various counterfeit videos.

The present application relates to the field of intelligent detection, and proposes a method for deep fake detection and positioning based on visual Transformer, which specifically comprises: obtaining target data to be detected and performing preprocessing; performing feature extraction according to a DF-ViT feature extraction network to obtain global deep fake artifact features and patch-level local features; inputting the global deep fake artifact features and the patch-level local features into a double-branch output module to obtain classification results and segmentation results; performing video time sequence enhancement processing according to a video time sequence ViT enhancement module; visually marking the fake area and giving explainability analysis. The present application improves artifact capturing capability and detection accuracy, solves the problem that the prior art can only classify but cannot position, and is suitable for multi-scene deployment, thereby enhancing explainability and generalizability.

The application relates to the technical field of terminals, and discloses a video detection method, an electronic device, a storage medium and a program product. In the video detection method, the electronic device can acquire a call video, acquire a plurality of frames of to-be-detected images from the call video, and perform AI face changing risk detection based on the plurality of frames of to-be-detected images. In the detection process, the electronic device can perform forgery detection based on the Nth frame of to-be-detected images after performing face detection based on the Nth frame of to-be-detected images, and in the process of performing forgery detection based on the Nth frame of to-be-detected images, face detection is performed based on the (N+1)th frame of to-be-detected images, that is, the face detection process and the forgery detection process can be executed in parallel. In this way, the time consumption of the detection process of the plurality of frames of to-be-detected images can be shortened, and the detection efficiency is improved.

This invention discloses a face forgery detection method and system based on a multimodal large language model, relating to the fields of artificial intelligence security and image processing technology. The method includes: acquiring a face image to be detected and preprocessing it to obtain a standardized face image; inputting it into a multi-classification visual detection network to obtain a visual feature map and initial classification results; based on the standardized face image and visual feature map, using a multimodal large language model to generate explanatory text associated with a preset forgery category, and extracting text embedding vectors; mapping the visual feature map to a visual embedding vector, and inputting it and the text embedding vector into a visual-language fusion module, performing feature interaction through a bidirectional cross-attention mechanism to obtain a joint representation vector; and based on the joint representation vector, obtaining the classification result of the face image to be detected. This invention achieves fine-grained forgery detection, improves detection accuracy and interpretability consistency through deep closed-loop fusion of visual and semantic methods, and solves the problems of coarse detection granularity and insufficient multimodal fusion in existing technologies.

The application provides a face forgery detection method and device and electronic equipment, comprising: acquiring a to-be-detected face video; inputting the to-be-detected face video into a face image reconstruction model to perform frame sampling on the to-be-detected face video through the face image reconstruction model, obtaining N first to-be-detected face video frames, performing feature extraction on the N first to-be-detected face video frames to obtain at least one first initial feature, determining a first reconstructed face image feature according to at least one first real face feature and the at least one first initial feature, obtaining N first reconstructed face images according to the first reconstructed face image feature, wherein N is a positive integer; detecting whether the to-be-detected face video is a forged face video according to the difference between the N first to-be-detected face video frames and the N first reconstructed face images; wherein the face image reconstruction model is obtained by training a real face video. To improve the accuracy of face forgery detection.

The application provides a face deep fake detection method and system based on feature decoupling and contrast learning, which is independent of the forgery method. The method applies random augmentation to face images to destroy specific fake traces; a semantic visual encoder based on CLIP is used to extract semantic features and project them into a contrast space; global true and false sample contrast loss and different forgery method cohesion loss are calculated by combining a difficult sample mining mechanism; the global true and false separation and intra-class aggregation are balanced through multi-objective optimization, forcing the model to strip method-specific features and learn essential fake attributes. The application uses the semantic prior of CLIP and the feature decoupling mechanism to effectively solve the problem of overfitting to specific fake patterns in the prior art, significantly improving the generalization ability and robustness of the model to unknown fake methods.

This invention relates to the field of image detection technology, and more particularly to a method, device, and storage medium for cross-domain AIGC image forgery detection based on unsupervised domain adaptation. The method includes: S1: preprocessing the source and target domain image sets to obtain dual-stream images; S2: extracting high-dimensional image features from the dual-stream images in the backbone network and then reducing the dimensionality; S3: dividing the reduced-dimensional feature vectors into a supervised classification branch and an unsupervised alignment branch, calculating the distribution distance in the unsupervised alignment branch to obtain the transfer loss; S4: calculating the cross-entropy classification loss in the supervised classification branch to construct a joint loss function, updating the weights of the backbone network and the classifier to obtain a detection model, and performing authenticity identification on images in the unknown target domain. This invention significantly improves the generalization ability and robustness of the AIGC forged image detection model in cross-generator scenarios by removing the global average pooling layer to retain microscopic forgery traces and combining multi-kernel maximum mean difference to achieve explicit alignment of feature distributions between the source and target domains.

The present application belongs to the technical field of computer, and particularly to a face forgery detection system based on uncertain modeling.The system comprises a probabilistic Transformer module, an image block screening module and an uncertainty-aware single classification loss function module.The present application firstly models the dependency relationship between image blocks as Gaussian random variables, extends the Transformer model in a probabilistic manner, then introduces an image block selection module to identify areas with high uncertainty information for final classification, and finally quantifies the uncertainty of the entire image, uses the designed uncertainty-aware single classification loss function to make the model focus more on samples with high uncertainty and difficult to determine, and through only enhancing the internal compactness of real faces, improves the inter-class separability of real and false classes in the embedding space.

The application provides a face forgery detection method and system based on multi-level discrimination, and belongs to the technical field of face recognition. The method comprises the following steps: inputting a to-be-detected face image into a visual encoder composed of a plurality of encoding layers connected in sequence to obtain a global visual feature vector corresponding to the to-be-detected face image; classifying the global visual feature vector to obtain a face forgery result corresponding to the to-be-detected face; the face forgery result comprises whether the face is forged and a forgery type; wherein in the visual encoder, the input vector of at least part of the encoding layers is obtained by fusing the output vector of the previous encoding layer and the visual cue vector corresponding to the previous encoding layer; the visual cue vector corresponding to each encoding layer is determined based on a visual cue pyramid; and each level of the visual cue pyramid is used to provide a visual cue vector of a different forgery type. The application can determine the forgery type of a face image while identifying the authenticity of the face image.

This invention discloses a method and system for deepfake detection of face images, belonging to the field of deepfake detection technology. A training set is constructed. When the face image to be detected belongs to a real face image in the training set, the loss function is the minimum distance between the original image features and the real features. When the face image to be detected belongs to a fake face image in the training set, the loss function is the maximum difference between the outer margin of the fake face image and the distance between the original image features and the fake features, determined by the distance between the original image features and the fake features. A binary cross-entropy loss is constructed based on the difference between the labels and the detection results. A face image detection model for distinguishing between real and fake face images is trained based on the loss function and the binary cross-entropy loss. This method improves the detection accuracy, generalization, and robustness of the face image detection model by injecting noise into the latent space and using differential reprojection distance to distinguish between real and fake samples.

This invention relates to the field of face forgery detection technology, and in particular provides a face forgery detection method based on watermark feature assistance and cross-task distillation. The method includes constructing a dataset of face image samples, embedding watermarks into the preprocessed face image samples to obtain watermarked images; inputting the watermarked images into a jointly trained model with dual-task branches for watermark extraction and forgery detection to obtain fine-grained image feature knowledge; and introducing knowledge distillation to transfer the fine-grained image feature knowledge to the forgery detection branch for dual-task collaborative optimization, thereby detecting face forgery. This method improves the detection accuracy.

The present application relates to the technical field of deep fake detection, in particular to a deep fake detection method based on local-global self-supervised contrastive learning; the method comprises the following steps: firstly, collecting unlabelled face images and labelled real-fake data and uniformly preprocessing, including face detection, extension cropping and key point positioning; secondly, dividing two global perspectives and seven local perspectives according to the key points, and constructing multi-view contrastive learning samples; further, designing a self-supervised pre-training process based on a teacher-student framework, learning robust face representation unsupervisedly by comparing the consistency of local and global features and reconstructing mask image blocks; finally, supervisedly fine-tuning the pre-trained model, and optimizing the classification structure by using neural network architecture search. The present application realizes high-precision and strong-generalization deep fake detection.

The application discloses a content forgery detection and positioning method and an electronic device. The method comprises the following steps: inputting a to-be-detected picture into a mixed expert model to obtain a forgery mode involved in the to-be-detected picture; taking the forgery mode involved in the to-be-detected picture as a prompt word, fine-tuning a visual large model to obtain a forgery detection large model; and generating a picture forgery detection result of the to-be-detected picture based on the forgery detection large model, wherein the picture forgery detection result comprises a picture forgery label and a picture forgery region positioning mask, so that the positioning accuracy of a forgery region is improved.

This invention relates to the field of computer vision and image recognition technology, and discloses a method and system for visually identifying the authenticity of cards based on floral anti-counterfeiting features. The method includes: macro imaging and adaptive preprocessing of the floral area, extraction of the floral line skeleton based on curvature flow analysis, hierarchical encoding of floral features and construction of multidimensional fingerprints, depth comparison based on Fourier descriptors and KL divergence, and counterfeit detection and comprehensive judgment based on generative adversarial networks. The accuracy rate of floral anti-counterfeiting feature recognition reaches 99.2%, the detection rate of high-quality counterfeit products reaches 98.5%, and the identification time per card is less than 3 seconds.

The application discloses a deep fake video detection method fusing ViT and spatial features, belongs to the technical field of video recognition, and is used for detecting deep fake videos. The application comprises the following steps: constructing a neural network fusing ViT and spatial features; training a deep fake video detection network; acquiring face data information in a deep fake video; inputting processed video information into the trained deep fake video detection network and outputting whether the video belongs to a fake video. The application fully utilizes the advantages of a convolutional neural network in extracting image fake details in deep video fake detection, combines orthogonal convolution, attention mechanism, residual connection and other ideas, maintains the complexity of the model, improves the accuracy of deep fake video detection, and has relatively stable detection performance in videos generated by various fake technologies.