Attribute-Based Encryption (ABE) is an advanced public-key encryption paradigm that enforces fine-grained access control over encrypted data. For instance, the data owner can generate the ciphertext associated with ((”Cardiology” OR ”Critical Care Medicine”) AND ”Consultant Physician”), which can only be decrypted by other data users whose attributes satisfy this access policy. However, a major efficiency drawback of ABE is that ciphertext size, encryption time, and decryption time grow with the complexity of the access policy and the number of attributes. To address this issue, we propose an adaptively secure, offline/online and outsourcing ABE scheme under the Generic Group Model. The majority of encryption operation is performed during the offline phase, while ABE ciphertext is quickly assembled during the online phase. Decryption outsourcing enables the edge node to convert the original ABE ciphertext into an ElGamal-style ciphertext using a transformation key without revealing the plaintext message to the edge node. Our approach is efficient and suitable for mobile devices. Performance evaluation demonstrates the system can balance computation and power consumption over an extended period, effectively addressing challenges in data sharing.

Gaze-based object manipulation intention inference is pivotal to natural and intuitive human-robot interaction. Existing methods confine spatial regularity to independent object selection and treat temporal regularity only as sequential order, thus spatio-temporal gaze regularities remain insufficiently exploited and lack a unified treatment. The objective of this study is to statistically analyze, model, and integrate gaze regularities within a unified probabilistic framework for inference. Accordingly, we propose a spatio-temporal gaze regularities guided dynamic fuzzy Bayesian network (DFBN) for intention inference. We statistically analyze the spatial gaze regularity as mutual exclusion and co-occurrence in joint object selection patterns, and the temporal regularity as duration-dependent attention with sequential dependencies. The regularities are modeled into probabilistic form, with spatio regularity modeled by autoregressive logistic regression and temporal regularity modeled by a Fuzzy Gaze-LSTM that fuses gaze duration with sequential order. These probabilistic models are fused into a likelihood modifier to generate interpretable posterior probabilities of intention, integrating a Bayesian network and sequential inference. Cross-dataset evaluations indicate stable and high performance. DFBN attains 96.47 1.75% accuracy and 96.41 1.85% F1 score, maintains accuracy on error sequences, and generalizes across younger and older groups, supporting robust intention inference. This study has the potential to inform other human-robot interaction assistance strategies by serving as intuitive gaze regularity cues.

In recent years, the rapid development of the industrial Internet of things (IIoT) has brought new innovation opportunities to the manufacturing industry, but it also faces some major challenges. Currently, the IIoT systems often lack flexibility in sensing capabilities and have rigid communication architectures, resulting in insufficient coordination between different control tasks. In addition, the disconnect between sensing, communication, and computing further limits the system's ability to achieve optimal control, and the lack of intelligent data processing in the system also increases the control cost. In response to these challenges, this paper proposes an intelligent control framework, CISCC, which combines industrial edge computing technology with artificial intelligence (AI) models to achieve a deep integration of sensing, communication, and computing resources in IIoT systems, aiming to jointly optimize the configuration of these resources to improve the overall system performance and reduce control costs. Simulation results show that the CISCC framework can effectively handle resource allocation problems in IIoT systems, thereby better supporting the development of smart manufacturing applications.

In the Social Internet of Things (SIoT), edge computing integrates artificial intelligence to learn intricate relationships. The scale and complexity of SIoT cause a data explosion from diverse objects, hindering tailored services to users who own objects. Moreover, conventional edge computing in SIoT depends on centralized data collection, raising concerns about data privacy. To address the above two issues, federated recommender systems (FRSs) present a promising solution. FRSs can provide SIoT services to users and train a shared model while retaining sensitive data locally on objects. However, as FRSs are driven by data, they are inherently susceptible to algorithmic bias, raising substantial fairness concerns that have attracted considerable attention in SIoT. Recent fairness studies predominantly concentrate on a single sensitive attribute for users, thereby overlooking their autonomy. Therefore, we propose CustomFair, a personalized fairness framework that enables users in FRSs to select preferred sensitive attributes and acquire satisfied recommendation services in SIoT scenarios. First, we define customized fairness to ensure group fairness based on users’ sensitive attributes. The server segments users into subgroups in a privacy-preserving manner. Second, CustomFair employs the DynBalance method with a flexible regularization coefficient to improve recommendation performance and utilizes the AdaptEpoch strategy to achieve fairness. Extensive experiments indicate that CustomFair improves recommendation performance by 0.1–42.92 and enhances fairness by reducing disparities of 0.03–5.41 compared to two baselines across three datasets.

Traditional threshold secret sharing scheme provides a mechanism to prevent the over-concentration of secrets while allowing for flexibility through the distribution and reconstruction of sub-secrets. However, this approach often simplifies participant behavior into categories of complete honesty or continuous deceit, neglecting the nuances of rational decision-making. To address this limitation, the rational secret sharing scheme merges threshold secret sharing with game theory, where each participant is considered rational and acts solely in self-interest. Nonetheless, existing schemes encounter challenges such as the prisoner's dilemma and the inability to reconstruct secrets due to the prioritization of individual interests. To mitigate these issues, our proposed scheme integrates a reward and punishment mechanism that balances short-term gains with long-term incentives, effectively deterring malicious behavior among participants. Moreover, traditional solutions based on elliptic curves and bilinear pairs lack resilience against quantum attacks. In response, our solution incorporates lattice-based cryptography to enhance security in the face of quantum threats. Additionally, we introduce an attribute access control tree to empower secret dealers in selecting suitable participants based on attribute restrictions, ensuring a more flexible, convenient, and secure rational secret sharing plan. This comprehensive approach improves participant selection and strengthens security measures in secret sharing scenarios.

With the continuous development of Internet of Things (IoT) technology and artificial intelligence (AI) technology, the demand for Artificial Intelligence of Things (AIoT) edge applications is increasing. However, there are challenges in AIoT edge applications, such as limited resources of edge devices, data privacy leakage, inconsistent model deployment, device authentication, and data sharing difficulties, which can affect the security and intelligence level of AIoT edge applications. Therefore, we propose a trusted cloud–edge decision architecture that ensures trustworthy authentication of terminal devices. We use lightweight deep neural network training technology to run multilayer perceptron (MLP) models on resource-limited edge devices, reducing the difficulty of model design and development. We also introduce blockchain technology to enhance the security and privacy of model and data processing. We describe the four-layer architecture and corresponding workflow details, and we introduce the main data models and focus on the core technologies of the architecture. Finally, we completed the simulation verification of the model using carbon emissions data as a sample, demonstrating the feasibility and effectiveness of the model.

Infrared small target detection (IRSTD) is crucial in both military and civilian applications. However, challenges such as low contrast, low signal-to-noise ratio (SNR), and lack of shape and texture information limit the effectiveness of existing methods in capturing edge details and representing target areas. To address these issues, we propose the dual-stream edge-target learning network (DETL-Net) for IRSTD. This network enhances feature cross-fusion by learning edge details and target regions through a dual-stream framework, significantly improving detection performance. Specifically, we extract multilevel features of the image based on the encoder-decoder structure of U-Net and then reconstruct the feature map. In the decoder, we propose the dual-guided cross-fusion module (DGCFM) to capture edge details of small targets and global contextual features of the target region, achieving complementary advantages. The multiscale context fusion module (MCFM) within DGCFM uses central difference convolution to enhance local contrast and extract rich contextual details, thereby retaining edge information and enhancing overall target representation. In addition, we introduce the cross-dimension interactive aggregation attention module (CIAAM), which dynamically adjusts feature fusion weights across layers to effectively suppress noise and enhance the discrimination of small targets. These modules are sequentially interconnected to progressively refine edge details, and the acquired target features are subsequently utilized for predicting the final target mask via the segmentation head. Experiments on the NUAA-SIRST and IRSTD-1k datasets demonstrate that DETL-Net outperforms state-of-the-art (SOTA) methods. The source code is available athttps://github.com/rayyao/DETL-Net.