In recent years, video steganography technique based on H.265/HEVC has received widespread attention. Typically, video steganography selects various syntax elements during the encoding process as carriers, and utilizing Prediction Unit (PU) as carrier is currently one of the most significant research directions. However, due to the limited number of PU types, such algorithms often suffer from insufficient capacity and visual quality. To alleviate the aforementioned issues, this paper proposes an H.265/HEVC video steganography algorithm that utilizes polygon encoding and Improved Deep Learnable Similarity Network Filter (IDLSNF). Firstly, we design a new polygon encoding rule, which maps different integers into several polygons. Secondly, we propose a novel steganography method based on polygon encoding and PU partition mode. This method selects the PUs of$8\times 8$and$16\times 16$coding unit in P-frames as carriers and hides the secret message by modifying the partition mode of two adjacent PUs. Due to the ability of polygon encoding to represent more information within a small range, it increases capacity with low steganographic distortion. Thirdly, we further propose a filter by improving DLSN, which enhances the visual quality of the entire stego video by processing I-frames. Extensive experimental results show that the video steganography algorithm proposed in this paper achieves higher capacity and superior visual quality compared to current State-of-the-Art methods. Meanwhile, our algorithm can also obtain good BRI and anti-steganalysis performance. This method has promising application prospects in the field of video covert communication.

The rapid advancement of Generative Adversarial Networks (GANs) and diffusion models has enabled the creation of highly realistic synthetic images, presenting significant societal risks, such as misinformation and deception. As a result, detecting AI-generated images has emerged as a critical challenge. Existing research emphasizes extracting fine-grained features to enhance detector generalization, yet they often lack consideration for the importance and interdependencies of internal elements within local regions and are limited to a single frequency domain, hindering the capture of general forgery traces. To overcome the aforementioned limitations, we first utilize a sliding window to restrict the attention mechanism to a local window, and reconstruct the features within the window to model the relationships between neighboring internal elements within the local region. Then, we design a dual frequency domain branch framework consisting of four frequency domain subbands of DWT and the phase part of FFT to enrich the extraction of local forgery features from different perspectives. Through feature enrichment of dual frequency domain branches and fine-grained feature extraction of reconstruction sliding window attention, our method achieves superior generalization detection capabilities on both GAN and diffusion model-based generative images. Evaluated on diverse datasets comprising images from 65 distinct generative models, our approach achieves a 2.13% improvement in detection accuracy over state-of-the-art methods.

Image steganalysis is a detection task to distinguish whether a secret message is embedded in a digital image. Due to the domain inconsistency caused by Cover Source Mismatch(CSM) and Steganographic Algorithm Mismatch (SAM), most of them suffer from significant performance degradation. Recent mismatched steganalysis focused on extracting domain invariant features by domain adversarial training or feature alignment. However these schemes are limited to unstable performance in diverse domain mismatch scenarios, and are even ineffective in some cases. In this paper, we propose a Universal Mismatched Steganalysis PCD-UMS via pair-wise confidence difference-based pseudo-label selection from the perspective of optimizing target training data. Specifically, we reveal a strong positive correlation commonality between pair-wise confidence difference and the detection performance of steganalysis among various mismatch scenarios. Based on this, a novel pseudo-label selection strategy consisting of maximum confidence difference first (MCDF) rule and pair-wise label differential storage (PLDS) rule is designed to select and filter the reliable target pseudo-labels. Furthermore, a multi-perspective pair-wise feature alignment loss is designed to initially transfer the classification ability of source steganalysis, thus solving the problem that source steganalysis fails completely under some domain mismatch scenarios. Comprehensive experiments show that our PCD-UMS outperforms the existing mismatched steganalysis by 12.07% and 3.40% in terms of detection performance under CSM and SAM scenarios.

Cost-based image steganography can significantly enhance its performance through a Reinforcement Learning (RL) framework. However, existing methods still face limitations in the generation of reward signals and the capture of image texture details. To address these challenges, this paper proposes a Dual-Branch Texture Enhancement Reinforcement Learning framework (DBT-RL) for symmetric embedding cost learning. This framework incorporates a Texture Information Enhancement Module (TIEM), enabling the policy network to more effectively focus on complex textured regions. Additionally, DBT-RL integrates multiple steganalysis to construct an ensemble environment network and introduces a novel adaptive update strategy. This strategy dynamically selects the best-performing steganalyzer to provide rewards to the policy network while self-updating weaker steganalyzers, ensuring that the policy network receives precise and dynamically balanced feedback. A large number of experimental results show that DBT-RL achieves high performance in the security of symmetric-cost embedding steganography.

Non-convertible tokens (NFTs) have become a fundamental part of the metaverse ecosystem due to its uniqueness and immutability. However, existing copyright protection schemes of NFT image art relied on the NFTs itself minted by third-party platforms. A minted NFT image art only tracks and verifies the entire transaction process, but the legitimacy of the source and ownership of its mapped digital image art cannot be determined. The original author or authorized publisher lack an active defense mechanism to prove ownership of the digital image art mapped by the unauthorized NFT. Therefore, we propose a self-defense copyright protection scheme for NFT image art based on information embedding in this article, called SDCP-IE. The original author or authorized publisher can embed the copyright information into the published digital image art without damaging its visual effect in advance. Different from the existing information embedding works, the proposed SDCP-IE can generally enhance the invisibility of copyright information with different embedding capacity. Furthermore, considering the scenario of copyright information being discovered or even destroyed by unauthorized parties, the designed SDCP-IE can efficiently generate enhanced digital image art to improve the security performance of embedded image, thus resisting the detection of multiple known and unknown detection models simultaneously. The experimental results have also shown that the PSNR values of enhanced embedded image are all over 57db on three datasets BOSSBase, BOWS2, and ALASKA#2. Moreover, compared with existing information embedding works, the enhanced embedded images generated by SDCP-IE reaches the best transferability performance on the advanced CNN-based detection models. When the target detector is the pre-trained SRNet at 0.4 bpp, the test error rate of SDCP-IE at 0.4 bpp on the evaluated detection model YeNet reaches 53.38%, which is 4.92%, 28.62%, and 7.05% higher than that of the UTGAN, SPS-ENH, and Xie-Model, respectively.

Adversarial embedding for image steganography is a novel technology to effectively enhance the steganographic security of the traditional steganographic algorithms. However, the existing schemes still have room for further improvement in the design of optimization strategy and the steganographic post-processing of optimization failure. In this paper, we design the progressive probability optimizing strategy (PPO). It dynamically selects more efficient gradients to guide the optimization of the probability optimization in a progressive manner. Moreover, we propose a discarded stego recycling mechanism (DSR) to re-select the stego from the discarded stego set that have failed to deceive the target steganalyzer after the optimzation fails. In such way, the statistical distribution of the stego can still further approximate the cover, thus further improving the steganographic security on re-trained steganalyzers in adversary-aware scenario. Comprehensive experiments show that compared with the existing advanced schemes, the proposed method boosts the security improvement against both the re-trained hand-crafted feature-based and deep leanring-based steganalysis models.

Adversarial example-based steganographic methods that utilize the gradients of target steganalyzer to update symmetric costs are emerging. The existing adversarial adjustment strategies for costs still have limited improvements in steganographic security. The existing gradient selection scheme, which sets a fixed gradient selection ratio for all images, is not delicate enough. To address the above problems, this paper proposes an iterative two-stage probability adjustment strategy with a progressive incremental searching mechanism (ITPA-PIS) to further improve the security of updated asymmetric distortions. Unlike previous works that adopted the cost as the adjustment object, we explore a new adjustment object, i.e., probability, and then design an iterative two-stage probability adjustment strategy (ITPA) to obtain a more secure asymmetric distortion, thereby improving the anti-detection performance of the traditional symmetric distortion algorithms against deep learning-based steganalyzers. In addition, we specifically design a progressive incremental searching mechanism (PIS) to select partially efficient gradients to guide the probability adjustment. Unlike existing gradient selection schemes that manually set a fixed selection ratio, PIS adopts a progressive searching method to dynamically determine the gradient selection ratio suitable for each image, thereby enhancing the overall performance of the proposed ITPA again. The experimental results show that our proposed ITPA-PIS achieves outstanding security performance on the CNN-based steganalysis models XuNet, YedroujNet, SRNet, and EfficientNet and hand-crafted feature-based steganalysis models SRM and MaxSRMd2 under the adversary unawareness and adversary awareness scenarios.

Linguistic steganalysis is an important topic in the field of information security and signal processing. In recent years, linguistic steganalysis have mainly utilized deep learning techniques and make great success. But suffer from the following major disadvantages. From the perspective of model structure, current methods only extract coarse features of the text, without focusing on the fine-grained representations. In terms of application, most of the studies only focus on single hidden scene and ignore the more realistic mixed hidden scenes which are more complex and realistic. These weaknesses limit the performance and the application of linguistic steganalysis in reality. In this paper, we propose a novel linguistic steganalysis method to overcome these weaknesses. This proposed method can extract distinguished text representation which fuses hierarchical features and perform excellently in sophisticated conditions. Firstly, we adapt gated graph neural networks as the coarse graph updater to update node representations on the graph level. Then we design a fine graph updater composed of the graph attention mechanism to focus on the highlighted nodes on the node-level. Moreover, we extract the most notable feature on the dimension-level of node by the graph channel attention module. Finally, the readout function is designed to fuse the hierarchical features and make the classification. The experimental results show that our method achieves the best results compared with the previous methods in both single hidden scene and mixed hidden scenes, which prove the effectiveness of the proposed method.