Facial information is widely used in security fields like identity authentication. But the large number of facial images online makes them vulnerable to unauthorized capture, posing privacy and security risks. Existing face privacy protection methods aim to mitigate these risks. However, many of these methods lack reversibility, making it impossible to restore the original face when needed. Additionally, they often neglect model intellectual property (IP) protection, leaving methods vulnerable to unauthorized stealing. Therefore, to address the shortcomings of existing face privacy protection methods in IP protection, this paper proposes an invertible privacy protection mask network with IP protection. The proposed method consists of two main parts: facial privacy protection and IP protection. For facial privacy protection, the mask generator replaces facial features with other faces and generates the mask, which is then embedded with the watermark to generate the watermarked mask. This watermarked mask conceals the original face by the putting on mask network, and the original face can be restored by the putting off mask network. For IP protection, the watermark extractor network is a key component that can extract the watermark from images of the sender, receiver and attacker to verify the method’s IP. Experimental results show that the proposed method has good effects in both privacy protection and IP protection, providing double security for face privacy protection.

The explosive growth of generative AI has saturated the internet with AI-generated images, raising security concerns and increasing the need for reliable detection methods. The primary requirement for such detection is generalizability, typically achieved by training on numerous fake images from various models. However, practical limitations, such as closed-source models and restricted access, often result in limited training samples. Therefore, training a general detector with few-shot samples is essential for modern detection mechanisms. To address this challenge, we propose FAMSeC, a general AI-generated image detection method based on LoRA-basedForgeryAwarenessModule andSemantic feature-guidedContrastive learning strategy. To effectively learn from limited samples and prevent overfitting, we developed a forgery awareness module (FAM) based on LoRA, maintaining the generalization of pre-trained features. Additionally, to cooperate with FAM, we designed a semantic feature-guided contrastive learning strategy (SeC), making the FAM focus more on the differences between real/fake image than on the features of the samples themselves. Experiments show that FAMSeC outperforms state-of-the-art method, enhancing classification accuracy by 14.55% with just 0.56% of the training samples.

The rapid advancement of large language models (LLMs) has raised concerns regarding potential misuse and underscores the importance of verifying text authenticity. Text watermarking, which embeds covert identifiers into generated content, offers a viable means for such verification. Such watermarking can be implemented either by modifying the generation process of an LLM or via post-processing techniques like lexical substitution, with the latter being particularly valuable when access to model parameters is restricted. However, existing lexical substitution-based methods often face a trade-off between maintaining text quality and ensuring robust watermarking. Addressing this limitation, our work focuses on enhancing both the robustness and imperceptibility of text watermarks within the lexical substitution paradigm. We propose a localization-based watermarking method that enhances robustness while maintaining text naturalness. First, a precise localization module identifies optimal substitution targets. Then, we leverage LLMs to generate contextually appropriate synonyms, and the watermark is embedded through binary-encoded substitutions. To address different usage scenarios, we focus on the trade-off between watermark robustness and text quality. Compared to existing methods, our approach significantly enhances watermark robustness while maintaining comparable text quality and achieves similar robustness levels while improving text quality. Even under severe semantic distortions, including word deletion, synonym substitution, polishing, and re-translation, the watermark remains detectable.

Enzymes are genetically encoded biocatalysts capable of accelerating chemical reactions. How can we automatically design functional enzymes? In this paper, we propose EnzyGen, an approach to learn a unified model to design enzymes across all functional families. Our key idea is to generate an enzyme's amino acid sequence and their three-dimensional (3D) coordinates based on functionally important sites and substrates corresponding to a desired catalytic function. These sites are automatically mined from enzyme databases. EnzyGen consists of a novel interleaving network of attention and neighborhood equivariant layers, which captures both long-range correlation in an entire protein sequence and local influence from nearest amino acids in 3D space. To learn the generative model, we devise a joint training objective, including a sequence generation loss, a position prediction loss and an enzyme-substrate interaction loss. We further construct EnzyBench, a dataset with 3157 enzyme families, covering all available enzymes within the protein data bank (PDB). Experimental results show that our EnzyGen consistently achieves the best performance across all 323 testing families, surpassing the best baseline by 10.79% in terms of substrate binding affinity. These findings demonstrate EnzyGen's superior capability in designing well-folded and effective enzymes binding to specific substrates with high affinities. Our code, model and dataset are provided at https://github.com/LeiLiLab/EnzyGen.

No-reference image quality assessment is a basic and challenging problem in the field of image processing. Among them, contrast distortion has a great impact on the perception of image quality. However, there are relatively few studies on no-reference quality assessment of contrast-distorted images. This article proposes a no-reference quality assessment algorithm for contrast-distorted images based on gray and color-gray-difference (CGD) space. In terms of gray space, we consider the local and global aspects, and use the distribution characteristics of the grayscale histogram to represent global features, while local features are described by the fusion of Local Binary Pattern (LBP) operator and gradient. In terms of CGD space, we first randomly extract patches from the entire image and then extract appropriate quality perception features in the patch’s CGD histogram. Finally, the AdaBoosting back propagation (BP) neural network is used to train the prediction model to predict the quality of the contrast-distorted image. Extensive analysis and cross-validation are carried out on five contrast-related image databases, and the experimental results have proved the superiority of this method compared with recent related algorithms.

With the popularity of social networks and the increase of cloud platform applications, service computing has also developed. Therefore, the protection of information even privacy uploaded to the cloud server has become critical. Recently, some researchers have proposed encryption schemes of visual meaningful image by using compressive sensing. However, these schemes generally cannot hide the large-size of plain image into the small-size of cover image and cannot recover the original plain image lossless. To solve above problems, this paper proposed a visually meaningful image encryption scheme based on lossless compression set partitioning in hierarchical trees (SPIHT) coding. The sender encrypts the plain image into the cipher image through the proposed encryption scheme, and then uploads the cipher image to the cloud server which is assumed as semi-honest trusted. Authorized receiver can completely decrypt the plain image after downloading the cipher image. In addition, even if the cipher image is attacked by attacker in the cloud server, the final decrypted image is still readable. Experimental results show that the proposed scheme is not only completely reversible and can hide the large-size of plain image into the small-size of cover image, but also superior to other schemes in visual quality and anti-attack performance.

Reversible data hiding methods for color images are investigated because of the popularity of color images. However, the traditional RDH methods for color images only take PSNR as the assessment metric and pursue a high PSNR value. To further consider the different subjective perception in the R, G, and B channels of the color image, this paper proposes a high visual quality color image reversible data hiding scheme based on the B-R-G embedding principle and the CIEDE2000 assessment metric. In this method, a double-layer least square prediction is proposed to satisfy the sorting requirement and maintain prediction accuracy, and then the B-R-G embedding principle is proposed to improve the visual quality of the marked color images based on the different visual perception in the three channels, and finally, a one-by-one embedding method is proposed to reduce the embedding distortion by maintaining the inter channel correlation. The experimental results show that the proposed method is superior to the state-of-the-art RDH methods for color images.

Abstract A reversible data hiding method based on partition is researched because it can effectively reduce shifting distortion in given embedding capacity. However, traditional partition is to divide an image into equal‐sized blocks, which cannot be divided reasonably according to the content of the image. In order to achieve dynamic partition and effectively utilize the complexity of the image, this paper proposes a novel reversible data hiding based on adaptive block‐partition and payload‐allocation method. In this technique, instead of equal partition, adaptive block‐partition is proposed to establish multiple histograms by dividing the cover image into several image blocks of different sizes dynamically, and the image blocks of different sizes are processed successively through multiple sorting and implement adaptive payload allocation according to complexity, then the data is embedded into two sides of prediction‐error histograms to effectively reduce the shifting distortion. Experimental results show that the proposed method is superior to the state‐of‐the‐art traditional fixed‐sized blocking‐based reversible data hiding methods.

Protection of medical data has become a prerequisite in medical imaging clouds due to the semi-trusted cloud. Aiming at preserving patients' privacy and increasing the security of medical images in the cloud, this letter proposes a secure and privacy-preserving technique which provides a new security mechanism for medical data. In this technique, a novel reversible data hiding (RDH) based on adaptive texture classification is proposed to embed privacy data into medical images for preserving patients' privacy and improving image quality, and plaintext encryption is proposed to encrypt the marked medical image into the similar image of target image for increasing image security. Extensive experiments have shown that the proposed RDH is better than other RDH methods. Plaintext encryption can reduce the attacker's attention and increase the security of medical images well.

Recursive code construction (RCC), based on the optimal transition probability matrix (OTPM), approaching the rate-distortion bound of reversible data hiding (RDH) has been proposed. Using the existing methods, OTPM can be effectively estimated only for a consistent distortion metric, i.e., if the host elements at different positions share the same distortion metric. However, in many applications, the distortion metrics are position dependent and should thus be inconsistent. Inconsistent distortion metrics can usually be quantified as a multi-distortion metric. In this paper, we first formulate the rate-distortion problem of RDH under a multi-distortion metric and subsequently propose a general framework to estimate the corresponding OTPM, with which RCC is extended to approach the rate-distortion bound of RDH under the multi-distortion metric. We apply the proposed framework to two examples of inconsistent distortion metrics: RDH in color image and reversible steganography. The experimental results show that the proposed method can efficiently improve upon the existing techniques.

Image and video labeling is important for computers to understand images and videos and for image and video search. Manual labeling is tedious and costly. Automatically image and video labeling is yet a dream. In this paper, we adopt a Web 2.0 approach to labeling images and videos efficiently: Internet users around the world are mobilized to apply their "common sense" to solve problems that are hard for today's computers, such as labeling images and videos. We first propose a general human computation framework that binds problem providers, Web sites, and Internet users together to solve large-scale common sense problems efficiently and economically. The framework addresses the technical challenges such as preventing a malicious party from attacking others, removing answers from bots, and distilling human answers to produce high-quality solutions to the problems. The framework is then applied to labeling images. Three incremental refinement stages are applied. The first stage collects candidate labels of objects in an image. The second stage refines the candidate labels using multiple choices. Synonymic labels are also correlated in this stage. To prevent bots and lazy humans from selecting all the choices, trap labels are generated automatically and intermixed with the candidate labels. Semantic distance is used to ensure that the selected trap labels would be different enough from the candidate labels so that no human users would mistakenly select the trap labels. The last stage is to ask users to locate an object given a label from a segmented image. The experimental results are also reported in this paper. They indicate that our proposed schemes can successfully remove spurious answers from bots and distill human answers to produce high-quality image labels.

JPEG 2000 provides multiple scalable accesses to a single codestream. Digital Rights Management of a JPEG 2000 codestream should preserve the original flexibility of scalability yet provide a mechanism to ensure what you see is what you pay: a low resolution version displayed on a smart phone should pay less than a high resolution version displayed on a PC. We present an efficient key scheme for multi-type, multilevel scalable access control for JPEG 2000 and motion JPEG 2000 codestreams. The scheme is based on a poset representation of the scalable access control and a hash based hierarchical access key scheme, both proposed elsewhere. The proposed key scheme exploits the information contained in a codestream and the features invariant under truncations to minimize the file size overhead for DRM applications yet preserve correct derivation of keys for descendants even when an encrypted codestream is truncated.

An optimal source-channel packetization scheme for MPEG-4 fine granularity scalability (FGS) codestreams is proposed in this paper. The channel is modeled with a uniform error distribution to the enhancement layer transmission. A cost function that models the error expansion for a MPEG-4 FGS stream is derived, and then used in the optimal packetization problem subject to the same overhead as the conventional packetization scheme. An efficient scheme to find the optimal solution is described, which takes time similar to encoding an MPEG-4 FGS codestream. Experiments show that our scheme has up to 1.96 dB gain over the conventional packetization scheme.

An efficient syntax-compliant encryption scheme for JPEG 2000 and motion JPEG 2000 is proposed in this paper. Compressed visual data is completely encrypted yet the full scalability of the unencrypted codestream is completely preserved to allow near RD-optimal truncations and other manipulations securely without decryption. Compared with other reported schemes, our scheme shows advantages on syntax compliance, compression overhead, scalable granularity, and error resilience. In addition to preserving the original scalability, a JPEG 2000 codestream encrypted with our scheme has the same error resilience capability as the unencrypted codestream. The encrypted codestream is still syntax-compliant so that an encryption-unaware decoder can still decode the encrypted codestream, although the decoded visual data is completely garbled and meaningless. Our scheme has virtually no adverse impact on the compression efficiency.

In this paper, we present an encryption scheme for MPEG-4 FGS which provides the same or a little coarser granularity of scalability after encryption. The scheme encrypts compressed data of each video packet or block independently. Initialization vectors are generated with a method to minimize the overhead. The scalability provided in an encrypted codestream using this scheme enables intermediate nodes to truncate an encrypted bitstream at near R-D optimality directly without decryption, which enhances system security. The scheme has virtually negligible overhead, and produces encrypted codestream with virtually the same error resilience performance as the unencrypted case. These features are very desirable in many applications