Search

Multi-image hiding, which embeds multiple secret images into a cover image and is able to recover these images with high quality, has gradually become a research hotspot in the field of image steganography. However, due to the need to embed a large amount of data in a limited cover image space, issues such as contour shadowing or color distortion often arise, posing significant challenges for multi-image hiding. In this paper, we propose StegaINR4MIH, a novel implicit neural representation steganography framework that enables the hiding of multiple images within a single implicit representation function. In contrast to traditional methods that use multiple encoders to achieve multi-image embedding, our approach leverages the redundancy of implicit representation function parameters and employs magnitude-based weight selection and secret weight substitution on pre-trained cover image functions to effectively hide and independently extract multiple secret images. We conduct experiments on images with a resolution of from three different datasets: CelebA-HQ, COCO, and DIV2K. When hiding two secret images, the PSNR values of both the secret images and the stego images exceed 42. When hiding five secret images, the PSNR values of both the secret images and the stego images exceed 39. Extensive experiments demonstrate the superior performance of the proposed method in terms of visual quality and undetectability., Comment: 46pages,14figures

Cloth-changing person Re-IDentification (Re-ID) aims at recognizing the same person with clothing changes across non-overlapping cameras. Conventional person Re-ID methods usually bias the model's focus on cloth-related appearance features rather than identity-sensitive features associated with biological traits. Recently, advanced cloth-changing person Re-ID methods either resort to identity-related auxiliary modalities (e.g., sketches, silhouettes, keypoints and 3D shapes) or clothing labels to mitigate the impact of clothes. However, relying on unpractical and inflexible auxiliary modalities or annotations limits their real-world applicability. In this paper, we promote cloth-changing person Re-ID by effectively leveraging abundant semantics present within pedestrian images without the need for any auxiliaries. Specifically, we propose the Content and Salient Semantics Collaboration (CSSC) framework, facilitating cross-parallel semantics interaction and refinement. Our framework is simple yet effective, and the vital design is the Semantics Mining and Refinement (SMR) module. It extracts robust identity features about content and salient semantics, while mitigating interference from clothing appearances effectively. By capitalizing on the mined abundant semantic features, our proposed approach achieves state-of-the-art performance on three cloth-changing benchmarks as well as conventional benchmarks, demonstrating its superiority over advanced competitors.

To protect the copyright of the 3D scene represented by the neural radiation field, the embedding and extraction of the neural radiation field watermark are considered as a pair of inverse problems of image transformations. A scheme for protecting the copyright of the neural radiation field is proposed using invertible neural network watermarking, which utilizes watermarking techniques for 2D images to achieve the protection of the 3D scene. The scheme embeds the watermark in the training image of the neural radiation field through the forward process in the invertible network and extracts the watermark from the image rendered by the neural radiation field using the inverse process to realize the copyright protection of both the neural radiation field and the 3D scene. Since the rendering process of the neural radiation field can cause the loss of watermark information, the scheme incorporates an image quality enhancement module, which utilizes a neural network to recover the rendered image and then extracts the watermark. The scheme embeds a watermark in each training image to train the neural radiation field and enables the extraction of watermark information from multiple viewpoints. Simulation experimental results demonstrate the effectiveness of the method.

Financial crime detection using graph learning improves financial safety and efficiency. However, criminals may commit financial crimes across different institutions to avoid detection, which increases the difficulty of detection for financial institutions which use local data for graph learning. As most financial institutions are subject to strict regulations in regards to data privacy protection, the training data is often isolated and conventional learning technology cannot handle the problem. Federated learning (FL) allows multiple institutions to train a model without revealing their datasets to each other, hence ensuring data privacy protection. In this paper, we proposes a novel two-stage approach to federated graph learning (2SFGL): The first stage of 2SFGL involves the virtual fusion of multiparty graphs, and the second involves model training and inference on the virtual graph. We evaluate our framework on a conventional fraud detection task based on the FraudAmazonDataset and FraudYelpDataset. Experimental results show that integrating and applying a GCN (Graph Convolutional Network) with our 2SFGL framework to the same task results in a 17.6\%-30.2\% increase in performance on several typical metrics compared to the case only using FedAvg, while integrating GraphSAGE with 2SFGL results in a 6\%-16.2\% increase in performance compared to the case only using FedAvg. We conclude that our proposed framework is a robust and simple protocol which can be simply integrated to pre-existing graph-based fraud detection methods., Comment: IEEE

A watermarking algorithm is proposed in this paper to address the copyright protection issue of implicit 3D models. The algorithm involves embedding watermarks into the images in the training set through an embedding network, and subsequently utilizing the NeRF model for 3D modeling. A copyright verifier is employed to generate a backdoor image by providing a secret perspective as input to the neural radiation field. Subsequently, a watermark extractor is devised using the hyperparameterization method of the neural network to extract the embedded watermark image from that perspective. In a black box scenario, if there is a suspicion that the 3D model has been used without authorization, the verifier can extract watermarks from a secret perspective to verify network copyright. Experimental results demonstrate that the proposed algorithm effectively safeguards the copyright of 3D models. Furthermore, the extracted watermarks exhibit favorable visual effects and demonstrate robust resistance against various types of noise attacks.

The utilization of implicit representation for visual data (such as images, videos, and 3D models) has recently gained significant attention in computer vision research. In this letter, we propose a novel model steganography scheme with implicit neural representation. The message sender leverages Neural Radiance Fields (NeRF) and its viewpoint synthesis capabilities by introducing a viewpoint as a key. The NeRF model generates a secret viewpoint image, which serves as a backdoor. Subsequently, we train a message extractor using overfitting to establish a one-to-one mapping between the secret message and the secret viewpoint image. The sender delivers the trained NeRF model and the message extractor to the receiver over the open channel, and the receiver utilizes the key shared by both parties to obtain the rendered image in the secret view from the NeRF model, and then obtains the secret message through the message extractor. The inherent complexity of the viewpoint information prevents attackers from stealing the secret message accurately. Experimental results demonstrate that the message extractor trained in this letter achieves high-capacity steganography with fast performance, achieving a 100\% accuracy in message extraction. Furthermore, the extensive viewpoint key space of NeRF ensures the security of the steganography scheme., Comment: 6 pages, 7 figures

Vision-and-language navigation (VLN), a frontier study aiming to pave the way for general-purpose robots, has been a hot topic in the computer vision and natural language processing community. The VLN task requires an agent to navigate to a goal location following natural language instructions in unfamiliar environments. Recently, transformer-based models have gained significant improvements on the VLN task. Since the attention mechanism in the transformer architecture can better integrate inter- and intra-modal information of vision and language. However, there exist two problems in current transformer-based models. 1) The models process each view independently without taking the integrity of the objects into account. 2) During the self-attention operation in the visual modality, the views that are spatially distant can be inter-weaved with each other without explicit restriction. This kind of mixing may introduce extra noise instead of useful information. To address these issues, we propose 1) A slot-attention based module to incorporate information from segmentation of the same object. 2) A local attention mask mechanism to limit the visual attention span. The proposed modules can be easily plugged into any VLN architecture and we use the Recurrent VLN-Bert as our base model. Experiments on the R2R dataset show that our model has achieved the state-of-the-art results., Comment: ICMR 2022

This paper studies limit measures of stationary measures of stochastic ordinary differential equations on the Euclidean space and tries to determine which invariant measures of an unperturbed system will survive. Under the assumption for SODEs to admit the Freidlin-Wentzell or Dembo-Zeitouni large deviations principle with weaker compactness condition, we prove that limit measures are concentrated away from repellers which are topologically transitive, or equivalent classes, or admit Lebesgue measure zero. We also preclude concentrations of limit measures on acyclic saddle or trap chains. This illustrates that limit measures are concentrated on Liapunov stable compact invariant sets. Applications are made to the Morse-Smale systems, the Axiom A systems including structural stability systems and separated star systems, the gradient or gradient-like systems, those systems possessing the Poincare-Bendixson property with a finite number of limit sets to obtain that limit measures live on Liapunov stable critical elements, Liapunov stable basic sets, Liapunov stable equilibria and Liapunov stable limit sets including equilibria, limit cycles and saddle or trap cycles, respectively. A number of nontrivial examples admitting a unique limit measure are provided, which include monostable, multistable systems and those possessing infinite equivalent classes., Comment: 37 pages, 12 figures

The coherent transmission technology using digital signal processing and advanced modulation formats, is bringing networks closer to the theoretical capacity limit of optical fibres, the Shannon limit. The in-phase quadrature electro-optic modulator that encodes information on both the amplitude and the phase of light, is one of the underpinning devices for the coherent transmission technology. Ideally, such modulator should feature low loss, low drive voltage, large bandwidth, low chirp and compact footprint. However, these requirements have been only met on separate occasions. Here, we demonstrate integrated thin-film lithium niobate in-phase/quadrature modulators that fulfil these requirements simultaneously. The presented devices exhibit greatly improved overall performance (half-wave voltage, bandwidth and optical loss) over traditional lithium niobate counterparts, and support modulation data rate up to 320 Gbit s-1. Our devices pave new routes for future high-speed, energy-efficient, and cost-effective communication networks.