Generative steganography has recently attracted considerable attention due to its superior security properties. However, most existing approaches suffer from limited hiding capacity. To address this issue, this paper proposes a high-capacity image steganography framework that integrates an encoder–decoder architecture with a latent diffusion model. Specifically, a message encoder is designed to transform binary secret messages into latent-space representations through a series of ResDense modules, enabling efficient hiding of large-scale information. The encoded latent features are then guided by the latent diffusion model to synthesize visually realistic stego images. During message extraction, the stego image undergoes iterative noise addition within the diffusion process to reconstruct the latent representation, from which a message decoder accurately recovers the hidden message. Extensive experimental results demonstrate that the proposed method achieves a high hiding capacity of over 30,000 bits, outperforming state-of-the-art methods while ensuring reliable message recovery under common image storage formats such as JPEG and PNG.

In recent years, deep neural networks (DNNs) have been widely used in Vehicular Edge Computing (VEC), becoming the core technology for most intelligent applications. However, these DNN inference tasks are usually computation-intensive and latency-sensitive. In urban autonomous driving scenarios, when a large number of vehicles offload tasks to roadside units (RSUs), they face the problem of computational overload of edge servers and inference delay beyond tolerable limits. To address these challenges, we propose an edge-vehicle collaborative inference acceleration mechanism, namely Model partitioning and Early-exit point selection joint Optimization for Collaborative Inference (MEOCI). Specifically, we dynamically select the optimal model partitioning points with the constraint of RSU computing resources and vehicle computing capabilities; and according to the accuracy threshold set to choose the appropriate early exit point. The goal is to minimize the average inference delay under the inference accuracy constraint. Therefore, we propose the Adaptive Dual-Pool Dueling Double Deep Q-Network (ADP-D3QN) algorithm, which enhances the exploration strategy and experience replay mechanism of D3QN to implement the proposed optimization mechanism MEOCI. We conduct comprehensive performance evaluations using four DNN models: AlexNet, VGG16, ResNet50, YOLOv10n. Experimental results show the proposed ADP-D3QN algorithm reduces average inference delay by 15.8% for AlexNet and 8.7% for VGG16 compared to Edgent algorithm.

Unmanned Aerial Vehicle (UAV)-assisted Vehicular Edge Computing (VEC) has emerged as a novel communication paradigm for compute-intensive and latency-sensitive applications in Intelligent Connected Vehicles (ICVs). In urban hotspots with traffic congestion, UAVs can alleviate the overload on edge servers, enhancing the ICVs’ quality of service (QoS) and safety. However, due to the high mobility of vehicles, effective solutions that can support low-latency and higher QoS for ICVs still lacked. Based on this, we first investigated the UAV deployment problem of maximizing vehicle coverage and system energy efficiency, and we proposed an adaptive population differential evolution (APDE) algorithm to address it. Then, we investigate the service caching and computation offloading problem of minimizing the system energy consumption and task response delay. DRL has effectively solved sequential decision-making in dynamic ICV environments, and we proposed a DRL-based Bias Correction-A3C-Gradient Sharing (BC-A3C-GS) algorithm to address it, which improves the traditional A3C algorithm in bias correction and global model update. Finally, experiment results show that the proposed UAV deployment algorithm can bring about 11.58% vehicle coverage rate improvement, and BC-A3C-GS algorithm can decrease about 30.08% task response delay and 17.4% energy consumption, and increase about 10.73% service cache hit rate.

Due to the powerful feature extraction capabilities of deep neural networks (DNNs), deep image hashing has extensive applications in the fields such as image authentication, copy detection and content retrieval, making its security a critical concern. Among various security metrics, collision resistance serves as a crucial indicator of deep image hashing methods. Research on collision attacks not only reveals the potential vulnerabilities of deep image hashing but also can promote the development of more robust and secure hashing methods. In this paper, we propose a novel generative collision attack scheme, which achieves several advantages over existing attack schemes based on adversarial examples. Our scheme requires no additional perturbations added to the image, and can simultaneously generate multiple hash collision images of different classes specified by the attacker. To the best of our knowledge, this is the first generative collision attack scheme effective across various deep image hashing methods. Specifically, our attack framework consists of three parts, i.e., a Hash-to-Noise Network (HTNN), a pretrained BigGAN generator and a conditional discriminator. The designed HTNN embeds the hash code of the target image and the attacker-specified generation class information into a “noise” vector. By optimizing various hash distance loss functions between the generated and target images, this “noise” guides the generator to directly generate images that meet the collision requirement. At the same time, the discriminator ensures that the generated images are visually realistic. Extensive experimental results verify that our scheme can effectively generate multiple high-quality images with attacker-specified classes, achieving the high success rate of hash collision attack and the applicability across state-of-the-art deep hashing methods.

With accelerating development of artificial intelligence, neural network models have been applied in many fields. The structure designing and training for models consume vast manpower and computing resources, which are the core interests of related research institutions and enterprises. However, the high-value attributes of neural network models also attract the attention of pirates, who may steal them for illegal profits and also slightly modify model parameters to escape model piracy detection. In order to solve the problem, in this work, we propose a robust and secure model hashing method based on dynamic branch reorganization and multi-feature fusion. Detailedly, we dynamically adjust the branches in our model hashing network to extract the robust features of all kinds of model parameters for generating the hash sequence. Besides, we integrate the encryption and the feature matrix generation to a unified stage in the hash generation for resisting possible encryption escape attack. Thus, the pirated models, even with some modifications, can be correctly detected through calculating hash distances. Experimental results demonstrate the effectiveness and superiority of our model hashing method with respect to pirated model detection, non-pirated model discrimination and security.

Perceptual hashing is a cutting-edge technique in the field of digital multimedia security, which maps the perceptual content of multimedia information to a fixed-length hash sequence to achieve content authentication. This survey provides a systematic overview of the definition, basic steps, main characters, and application scenarios of perceptual hashing. According to the different authentication objects, representative schemes of perceptual image hashing, perceptual video hashing, and perceptual hashing for neural network models are introduced, respectively. Both perceptual image hashing and perceptual video hashing can be divided into classical methods-based schemes and learning-based schemes, where learning-based schemes can be subdivided into supervised and unsupervised. Classical methods-based image hashing schemes can be divided into four categories: local feature-based, transformation-based, statistical feature-based, and dimensionality reduction-based. Classical methods-based video hashing schemes are mainly categorized into spatial feature-based schemes and spatial-temporal feature-based schemes. Additionally, we introduce the dataset composition and hash distance metric strategies for perceptual hashing and analyze the performance of some representative schemes. Finally, we summarize the existing schemes and offer prospects for future research directions and development trends.

Since the significant advancements and open-source support of latent diffusion models (LDMs) in the field of image generation, numerous researchers and enterprises start fine-tuning the pre-trained models to generate specialized images for different objectives. However, the criminals may turn their attention to generate images by LDMs and then carry out illegal activities. The watermarking technique is a typical solution to deal with this problem. But, the post-hoc watermarking methods can be easily escaped to obtain the non-watermarked images, and the existing watermarking methods designed for LDMs can only embed a fixed message, i.e., the to-be-embedded message cannot be changed unless retraining the model. Therefore, in this work, we propose an end-to-end watermarking method based on the encoder-decoder (ENDE) and message-matrix. The message can be embedded into generated images through fusing the message-matrix and intermediate outputs in the forward propagation of image generation based on LDM. Thus, the message can be flexibly changed by utilizing the message-encoder to generate message-matrix, without training the LDM again. On the other hand, the security mechanism in our watermarking method can defeat the attack that the users may escape the message-matrix usage during image generation. A series of experiments demonstrate the effectiveness and the superiority of our watermarking method compared with SOTA methods.

With the rapid development of neural network, a vast number of neural network models have been developed in recent years, which condense numerous manpower and hardware resource. However, the original models are at risk of being pirated by the adversary to obtain illegal profits. On the other hand, malicious tampering on models, such as implanting the vulnerability and backdoor, may cause catastrophic consequences. We propose a model hash generator method to protect neural network models. Detailedly, our model hash sequence is composed of two parts: one is the model piracy identification hash, which is based on the dynamic convolution and a dual-branch network; the other is the model tampering localization hash, which can help the model owner to accurately detect the tampered locations for further recovery. Experimental results demonstrate the effectiveness of the proposed method for neural network model protection.