Key distribution is the foundation for protecting the user’s privacy and communication security in cloud environment. Information hiding is an effective manner to hide the transmission behavior of secret information such as keys, and thus it makes the secure key distribution possible. However, the traditional information hiding systems usually embed the secret information by modifying the carrier, which inevitably leaves modification traces on the carrier. Thus, they cannot resist the detection of the steganalysis algorithm effectively. To avoid this issue, the coverless information hiding technique has been proposed accordingly, in which the original images of which features can express the secret information are directly used as stego-images. Since the existing coverless information hiding methods use the low-level handcrafted image features to express secret information, it is hard for them to realize desirable robustness to common image attacks. Moreover, their hiding capacity is limited. To conquer these problems, we design a novel robust image coverless information hiding system using Faster Region-based Convolutional Neural Networks (Faster-RCNN). We employ Faster RCNN to detect and locate objects in images and utilize the labels of these objects to express secret information. Since the original images without any modification are used as stego-images, the proposed method can effectively resist steganalysis and will not cause attackers’ suspicion. The experimental results demonstrate that the proposed system has higher performance in terms of robustness and capacity compared to the typical coverless information hiding methods.

Text steganography has received a lot of attention in the application of covert communication. How to ensure desirable capacity and imperceptibility has become a key issue in text steganography. There are two typical approaches, i.e., text-selection-based steganography and text-generation-based steganography. However, the text-selection-based approaches generally have the very low hidden capacity and are not applicable in practical scenarios. Although the text-generation-based approaches can embed secret messages with higher capacity during text generation, they are prone to semantic incoherence and semantic errors when generating long texts. To address the abovementioned issues, this article proposes a novel text steganography based on long readable text generation. It first determines the topic of the stego-text according to the scenarios of the communication parties. Then, the plug and play language model (PPLM) is explored to generate the long readable stego-text conforming to the topic with semantic coherency. A given secret message is hidden during text generation by selecting proper words in an established embeddable candidate word pool (ECWP). Establishing the ECWP prevents the language model (LM) from selecting words with low probability in the text generation, thereby avoiding the generation of low-quality or even grammatically incorrect stego-text. Experimental results show that the proposed approach significantly increases hidden capacity while maintaining good imperceptibility compared with the existing approaches.

Classroom behavior detection is a key task in constructing intelligent educational environments. However, the existing models are still deficient in detail feature capture capability, multi-layer feature correlation, and multi-scale target adaptability, making it challenging to realize high-precision real-time detection in complex scenes. This paper proposes an improved classroom behavior detection algorithm, YOLO-AMM, to solve these problems. Firstly, we constructed the Adaptive Efficient Feature Fusion (AEFF) module to enhance the fusion of semantic information between different features and improve the model’s ability to capture detailed features. Then, we designed a Multi-dimensional Feature Flow Network (MFFN), which fuses multi-dimensional features and enhances the correlation information between features through the multi-scale feature aggregation module and contextual information diffusion mechanism. Finally, we proposed a Multi-Scale Perception and Fusion Detection Head (MSPF-Head), which significantly improves the adaptability of the head to different scale targets by introducing multi-scale feature perception, feature interaction, and fusion mechanisms. The experimental results showed that compared with the YOLOv8n model, YOLO-AMM improved the mAP0.5 and mAP0.5-0.95 by 3.1% and 4.0%, significantly improving the detection accuracy. Meanwhile, YOLO-AMM increased the detection speed (FPS) by 12.9 frames per second to 169.1 frames per second, which meets the requirement for real-time detection of classroom behavior.

The complexity of urban road scenes at night and the inadequacy of visible light imaging in such conditions pose significant challenges. To address the issues of insufficient color information, texture detail, and low spatial resolution in infrared imagery, we propose an enhanced infrared detection model called LFIR-YOLO, which is built upon the YOLOv8 architecture. The primary goal is to improve the accuracy of infrared target detection in nighttime traffic scenarios while meeting practical deployment requirements. First, to address challenges such as limited contrast and occlusion noise in infrared images, the C2f module in the high-level backbone network is augmented with a Dilation-wise Residual (DWR) module, incorporating multi-scale infrared contextual information to enhance feature extraction capabilities. Secondly, at the neck of the network, a Content-guided Attention (CGA) mechanism is applied to fuse features and re-modulate both initial and advanced features, catering to the low signal-to-noise ratio and sparse detail features characteristic of infrared images. Third, a shared convolution strategy is employed in the detection head, replacing the decoupled head strategy and utilizing shared Detail Enhancement Convolution (DEConv) and Group Norm (GN) operations to achieve lightweight yet precise improvements. Finally, loss functions, PIoU v2 and Adaptive Threshold Focal Loss (ATFL), are integrated into the model to better decouple infrared targets from the background and to enhance convergence speed. The experimental results on the FLIR and multispectral datasets show that the proposed LFIR-YOLO model achieves an improvement in detection accuracy of 4.3% and 2.6%, respectively, compared to the YOLOv8 model. Furthermore, the model demonstrates a reduction in parameters and computational complexity by 15.5% and 34%, respectively, enhancing its suitability for real-time deployment on resource-constrained edge devices.

Existing generative image steganography methods typically encode secret information into latent vectors, which are transformed into the entangled features of generated images. This approach faces two main challenges: (1) Transmission can degrade the quality of stego-images, causing bit errors in information extraction. (2) High embedding capacity often reduces the accuracy of information extraction. To overcome these limitations, this paper presents a novel generative image steganography via encoding pose keypoints. This method employs an LSTM-based sequence generation model to embed secret information into the generation process of pose keypoint sequences. Each generated sequence is drawn as a keypoint connectivity graph, which serves as input with an original image to a trained pose-guided person image generation model (DPTN-TA) to generate an image with the target pose. The sender uploads the generated images to a public channel to transmit the secret information. On the receiver’s side, an improved YOLOv8 pose estimation model extracts the pose keypoints from the stego-images and decodes the embedded secret information using the sequence generation model. Extensive experiments on the DeepFashion dataset show that the proposed method significantly outperforms state-of-the-art methods in information extraction accuracy, achieving 99.94%. It also achieves an average hiding capacity of 178.4 bits per image. This method is robust against common image attacks, such as salt and pepper noise, median filtering, compression, and screenshots, with an average bit error rate of less than 0.87%. Additionally, the method is optimized for fast inference and lightweight deployment, enhancing its real-world applicability.

Steganography is a technique for hiding secret information in imperceptible carriers and transmitting it. Unlike traditional embedding-based steganography, generative steganography can generate stego-carriers directly from secret messages, thus avoiding modifications to natural carriers that steganalysis can detect. As a branch of generative steganography, game-behavior-based steganography transmits secret information by encoding game behavior. It can naturally integrate with real interaction scenarios, exhibiting strong concealment and undetectability. To this end, this paper proposes a generative steganography based on Chinese Chess record construction. Firstly, an AlphaZero model was trained to achieve a high level in Chinese Chess, then transmit secret information by encoding chess behavior. Specifically, in each chess step, the model generates all the current feasible moves and encodes the moves that meet the threshold strategy according to probability. Then, the appropriate move will be selected according to the secret information. To ensure the reasonableness of the generated chess records, this paper controlled the game process and designed a database of fixed opening chess records. The proposed method can hide an average of 413 bits of information for each carrier and effectively resist common image attacks. Regarding anti-steganalysis, the proposed method achieved accuracy rates of 0.498 and 0.497 on XuNet and YeNet, respectively, outperforming other behavior-based steganography techniques.