In order to safeguard image copyrights, zero-watermarking technology extracts robust features and generates watermarks without altering the original image. Traditional zero-watermarking methods rely on handcrafted feature descriptors to enhance their performance. With the advancement of deep learning, this paper introduces “ZWNet”, an end-to-end zero-watermarking scheme that obviates the necessity for specialized knowledge in image features and is exclusively composed of artificial neural networks. The architecture of ZWNet synergistically incorporates ConvNeXt and LK-PAN to augment the extraction of local features while accounting for the global context. A key aspect of ZWNet is its watermark block, as the network head part, which fulfills functions such as feature optimization, identifier output, encryption, and copyright fusion. The training strategy addresses the challenge of simultaneously enhancing robustness and discriminability by producing the same identifier for attacked images and distinct identifiers for different images. Experimental validation of ZWNet’s performance has been conducted, demonstrating its robustness with the normalized coefficient of the zero-watermark consistently exceeding 0.97 against rotation, noise, crop, and blur attacks. Regarding discriminability, the Hamming distance of the generated watermarks exceeds 88 for images with the same copyright but different content. Furthermore, the efficiency of watermark generation is affirmed, with an average processing time of 96 ms. These experimental results substantiate the superiority of the proposed scheme over existing zero-watermarking methods.

The existing commutative encryption and watermarking (CEW) methods based on feature invariants can achieve both the robustness of the watermarking algorithm and the security of the encryption algorithm. However, they are only applicable to the raster data such as images, videos, etc. In particular, the organization structure and storage structure of vector map have not been considered in these methods. Therefore, they cannot be used for vector map. This paper derives two feature invariants to solve this problem, which are the sum of inner angles and the storage direction of two adjacent objects according to the inherent characteristics of vector map. Based on these two feature invariants, a new CEW method is proposed in this paper, which includes the feature invariants based watermarking algorithm and the perceptual stream cipher based encryption algorithm on coordinates. Since the coordinate values used in encryption and the feature invariants used in watermarking are independent of each other, the commutativity is achieved for the proposed CEW method. The experiments are given to verify that the proposed CEW method can achieve the commutativity between encryption and watermarking without deteriorating accuracy of data. Besides, it has been verified that the proposed method is more robust to rotate, scaling, translation, and projection transformation compared with the existing CEW methods and has high security. The proposed algorithm has good scalability of encryption, and arbitrary encryption methods based on encrypting the coordinate values can be applied without affecting the extracted feature invariants.

In cross-modal retrieval, the hashing technique has sparked a great revolution because of its competitive query speed and minimal storage. However, existing approaches may have critical limitations: 1) Label Intrinsic Relations. They barely explore category information inherent in labels and only consider labels as distinct entities, losing rich latent semantic information. 2) Modality-specific and Modality-coherence Semantics. They often construct a common subspace and an affinity matrix to learn modality-specific features and modality-coherence correlations, respectively. The former will lead to considerable quantization errors because the subspaces should be approximate rather than exactly equal. The latter is not scalable due to its high computational costs. 3) Non-relaxation Optimization Strategy. To solve constraints, some approaches relax the binary constraints to continuous, rising significant quantization errors. To mitigate these problems, we propose Disperse Asymmetric Subspace Relation Hashing, termed DASRH. In particular, it first embeds modality-specific kernel features into dispersed latent spaces, which can effectively fuse heterogeneous patterns. Additionally, it exploits fine-grained categories from labels by reconstructing collective semantic representations, making discriminative binary codes. Furthermore, it constructs an asymmetric consistent relation integration, preserving both inter-modal disparities and intra-class differences. In the optimization process, an effective alternative iterative optimization scheme is established. Theoretical analysis and comprehensive experiments highlight the advantages of our DASRH against cutting-edge technology.