Vision-Language Models (VLMs) have demonstrated remarkable capabilities in visual classification tasks. Existing methods for enhancing VLMs on this task often rely heavily on direct category-to-image matching, which limits generalization and results in suboptimal performance. In addition, these methods provide no understanding of why a specific category is chosen. To address these limitations, we introduce a new deliberative visual classification task that decomposes the classification process into multiple deliberative steps and leverages Large Language Models (LLMs) to perform explicit reasoning before the final decision. Specifically, we propose a Retrieval-driven Reasoning model (RdR) with two components, i.e., retrieval database construction and deliberative category prediction. The first component leverages LLMs to extract category-relevant descriptors and constructs a retrieval database for effective image–descriptor matching. The second component facilitates multiple deliberative steps and performs explicit reasoning based on the retrieved descriptors to augment the category prediction. Extensive experiments on multiple datasets demonstrate that RdR consistently outperforms strong baselines, highlighting its robustness and generalization ability.

In the emerging Industrial Internet of Things (IIoT) applications, federated learning (FL) enables model training without the need to transmit raw data directly. Nevertheless, transmitting model parameters could still reveal private information. To further protect local model parameters, differential privacy combined with FL (DPFL) has been introduced. Nonetheless, adding noise in DPFL can severely impact model performance, especially in non-independent and identically distributed (non-iid) data scenarios typical of IIoT environments. It is necessary to carefully balance privacy preservation and utility. In this article, we propose a robust DPFL scheme leveraging local model partition and sparsification (namely, FedMPS) for heterogeneous IIoT scenarios. The local model is divided into a shared part, which is sparsified before adding noise to mitigate its impact, and a private part that remains on the client. We provide a theoretical analysis of the privacy guarantees. Extensive experiments on common datasets, including Fashion-MNIST, CIFAR-10, and CIFAR-100, demonstrate that the proposed approach achieves a better privacy-utility tradeoff, with a 10%–20% improvement compared to baseline methods, and performs well especially in non-iid scenarios.

Summary In postdisaster rescue scenario, unmanned aerial vehicles (UAVs) are effective tools to help ground users in disaster areas to transmit rescue‐critical data to the relief center in time due to their flexible mobilities and fast deployment. However, how UAVs choose disaster areas to take part in traffic offloading with limited bandwidth resources is challenging. This article investigates UAVs' access selection and disaster areas' bandwidth allocation scheme by jointly optimizing network throughput, bandwidth and UAVs' energy cost. The UAVs form coalitions to participate in traffic offloading cooperatively, where each UAV selects a disaster area independently. Specifically, the bandwidth resources are dynamically allocated to all disaster areas when a new coalition partition forms. The UAVs adjust their access choices for disaster areas when the bandwidth allocation changes. When no UAVs migrate to other disaster areas, the network achieves a stable state. The UAVs fly to the final selected disaster area and provide traffic offloading services. To resolve traffic offloading competitions yet enable cooperations among UAVs, we address the UAVs' access selection issue by coalition formation game. A gradient projection method is then proposed to allocate bandwidth resources which maximizes the benefit of the network. We demonstrate that the UAVs' access selection and disaster areas' bandwidth allocation algorithms are convergent. The simulation results demonstrate that our proposed cooperation order is better than the pareto and selfish orders, thereby increasing the benefit of the network.

In a post-pandemic era with personal precautions and vaccination, the emergence of COVID-19 variants with higher transmissibility and the socio-economic reopening have raised new challenges to existing human-to-human digital contact tracing systems, where privacy, efficiency, and energy-consumption issues are major concerns. In this article, we propose a novel blockchain-based human-to-infrastructure contact tracing framework for the post-pandemic era. Specifically, our approach collects and records the interaction information between persons and predeployed anchor nodes to trace the possible contacts with confirmed patients, so as to capture the indirect contacts and reduces the energy consumption of users. To address the privacy leakage and reliability issues in contact tracing, we introduce a self-sovereign identity (SSI) model-based blockchain which enables users to gain full control of their own identities and eliminate the linkage between the identity and location information in interaction records. To further preserve the privacy of confirmed patients, we introduce the private set intersection cardinality (PSI-CA) protocol to estimate the risk of infection by only counting the number of encounters between users and confirmed patients. Two self-executed smart contracts are deployed on the SSI blockchain to perform contact tracing, which guarantees the robustness of the system. The performance analysis validates the effectiveness of our approach.

Blockchain-based trust management has attracted great attention for vehicular networks due to its decentralized, transparent, and tamper-proof natures. However, the highly dynamic vehicular environment challenges the reliability of trust evaluation as well as the privacy preservation of vehicles against tracking attacks. In this paper, we propose a privacy-preserving trust management system to evaluate the trustworthiness of vehicles by exploiting the recent advanced blockchain techniques. Specifically, we build up a trust evaluation blockchain, where the trustworthiness of an involved vehicle is evaluated by distributed road-side units (RSUs) based on the rating feedback from neighboring vehicles. To enable efficient and privacy-preserving trust evaluation, we deploy the feedback messages aggregation and trust evaluation on two smart contracts, which are executed and verified by distributed RSUs automatically. In particular, identity authentication based on Elliptic Curve Cryptography (ECC) cryptosystem is introduced to prevent privacy leakage of vehicles. Security analysis and performance evaluation reveal that our system is secure and efficient to manage the trust evaluation while guaranteeing privacy-preservation for vehicular networks.

With the ever-increasing demands on decentralization and transparency of cloud storage, CP-ABE (Ciphertext Policy-Attribute-Based Encryption) has become a promising technology for blockchain-enabled data sharing methods due to its flexibility. However, real-world blockchain applications usually have some special requirements like time restrictions or power limitations. Thus, decryption outsourcing is widely used in data sharing scenarios and also causes concerns about data security. In this paper, we proposed a secure access control scheme based on CP-ABE, which could share contents during a particular time slot in blockchain-enabled data sharing systems. Specifically, we bind the time period with both ciphertexts and the keys to archive the goal of only users who have the required attributes in a particular time slot can decrypt the content. Besides, we use time slots as a token to protect the data and access control scheme when users want to outsource the decryption phase. The security analysis shows that our scheme can provide collusion resistance ability under a time restriction, and performance evaluations indicate that our scheme uses less time in decryption compared to other schemes while ensuring security.