This paper presents a novel watermarking scheme designed to address the copyright protection challenges encountered with Neural radiation field (NeRF) models. We employ an embedding network to integrate the watermark into the images within the training set. Then, the NeRF model is utilized for 3D modeling. For copyright verification, a secret image is generated by inputting a confidential viewpoint into NeRF. On this basis, design an extraction network to extract embedded watermark images from confidential viewpoints. In the event of suspicion regarding the unauthorized usage of NeRF in a black-box scenario, the verifier can extract the watermark from the confidential viewpoint to authenticate the model’s copyright. The experimental results demonstrate not only the production of visually appealing watermarks but also robust resistance against various types of noise attacks, thereby substantiating the effectiveness of our approach in safeguarding NeRF.

Deep steganography utilizes the powerful capabilities of deep neural networks to embed and extract messages, but its reliance on an additional message extractor limits its practical use due to the added suspicion it can raise from steganalyzers. To address this problem, we propose StegaINR, which utilizes Implicit Neural Representation (INR) to implement steganography. StegaINR embeds a secret function into a stego function, which serves as both the message extractor and the stego medium for secure transmission on a public channel. Recipients only need to use a shared key to recover the secret function from the stego function, allowing them to obtain the secret message. Our approach employs continuous functions, enabling it to handle various types of messages. To our knowledge, this is the first work to introduce INR into steganography. We perform evaluations on image, climate data, and Neural Radiance Field (NeRF) synthetic dataset to test our method in different deployment contexts.

As neural radiance fields continue to advance in 3D content representation, the copyright issues surrounding 3D models oriented towards implicit representation become increasingly pressing. In response to this challenge, this paper treats the embedding and extraction of neural radiance field watermarks as inverse problems of image transformations and proposes a scheme for protecting neural radiance field copyrights using invertible neural network watermarking. Leveraging 2D image watermarking technology for 3D scene protection, the scheme embeds watermarks within the training images of neural radiance fields through the forward process in invertible neural networks and extracts them from images rendered by neural radiance fields through the reverse process, thereby ensuring copyright protection for both the neural radiance fields and associated 3D scenes. However, challenges such as information loss during rendering processes and deliberate tampering necessitate the design of an image quality enhancement module to increase the scheme’s robustness. This module restores distorted images through neural network processing before watermark extraction. Additionally, embedding watermarks in each training image enables watermark information extraction from multiple viewpoints. Our proposed watermarking method achieves a PSNR (Peak Signal-to-Noise Ratio) value exceeding 37 dB for images containing watermarks and 22 dB for recovered watermarked images, as evaluated on the Lego, Hotdog, and Chair datasets, respectively. These results demonstrate the efficacy of our scheme in enhancing copyright protection.

Recent research advances in implicit neural representation have shown that a wide range of video data distributions are achieved by sharing model weights for Neural Representation for Videos (NeRV). While explicit methods exist for accurately embedding ownership or copyright information in video data, the nascent NeRV framework has yet to address this issue comprehensively. In response, this paper introduces MarkINeRV, a scheme designed to embed watermarking information into video frames using an invertible neural network watermarking approach to protect the copyright of NeRV, which models the embedding and extraction of watermarks as a pair of inverse processes of a reversible network and employs the same network to achieve embedding and extraction of watermarks. It is just that the information flow is in the opposite direction. Additionally, a video frame quality enhancement module is incorporated to mitigate watermarking information losses in the rendering process and the possibility of malicious attacks during transmission, ensuring the accurate extraction of watermarking information through the invertible network’s inverse process. This paper evaluates the accuracy, robustness, and invisibility of MarkINeRV through multiple video datasets. The results demonstrate its efficacy in extracting watermarking information for copyright protection of NeRV. MarkINeRV represents a pioneering investigation into copyright issues surrounding NeRV.

Traditional steganography is the practice of embedding a secret message into an image by modifying the information in the spatial or frequency domain of the cover image. Although this method has a large embedding capacity, it inevitably leaves traces of rewriting that can eventually be discovered by the enemy. The method of Steganography by Cover Synthesis (SCS) attempts to construct a natural stego image, so that the cover image is not modified; thus, it can overcome detection by a steganographic analyzer. Due to the difficulty in constructing natural stego images, the development of SCS is limited. In this paper, a novel generative SCS method based on a Generative Adversarial Network (GAN) for image steganography is proposed. In our method, we design a GAN model called Synthetic Semantics Stego Generative Adversarial Network (SSS-GAN) to generate stego images from secret messages. By establishing a mapping relationship between secret messages and semantic category information, category labels can generate pseudo-real images via the generative model. Then, the receiver can recognize the labels via the classifier network to restore the concealed information in communications. We trained the model on the MINIST, CIFAR-10, and CIFAR-100 image datasets. Experiments show the feasibility of this method. The security, capacity, and robustness of the method are analyzed.