Due to the distributed collaboration and privacy protection features, federated learning is a promising technology to perform the model training in virtual twins of Digital Twin for Mobile Networks (DTMN). In order to enhance the reliability of the model, it is always expected that the users involved in federated learning have trustworthy behaviors. Yet, available trust evaluation schemes for federated learning have the problems of considering simplex evaluation factor and using coarse-grained trust calculation method. In this paper, we propose a trust evaluation scheme for federated learning in DTMN, which takes direct trust evidence and recommended trust information into account. A user behavior model is designed based on multiple attributes to depict users’ behavior in a fine-grained manner. Furthermore, the trust calculation methods for local trust value and recommended trust value of a user are proposed using the data of user behavior model as trust evidence. Several experiments were conducted to verify the effectiveness of the proposed scheme. The results show that the proposed method is able to evaluate the trust levels of users with different behavior patterns accurately. Moreover, it performs better in resisting attacks from users that alternately execute good and bad behaviors compared with state-of-the-art scheme. The code for the method proposed in this paper is available at: https://web.xidian.edu.cn/jjguo/en/code.html .

Generating accurate SQL from users’ natural language questions (text-to-SQL) remains a long-standing challenge due to the complexities involved in user question understanding, database schema comprehension, and SQL generation. Traditional text-to-SQL systems, which combine human engineering and deep neural networks, have made significant progress. Subsequently, pre-trained language models (PLMs) have been developed for text-to-SQL tasks, achieving promising results. However, as modern databases and user questions grow more complex, PLMs with a limited parameter size often produce incorrect SQL. This necessitates more sophisticated and tailored optimization methods, which restrict the application of PLM-based systems. Recently, large language models (LLMs) have shown significant capabilities in natural language understanding as model scale increases. Thus, integrating LLM-based solutions can bring unique opportunities, improvements, and solutions to text-to-SQL research. In this survey, we provide a comprehensive review of existing LLM-based text-to-SQL studies. Specifically, we offer a brief overview of the technical challenges and evolutionary process of text-to-SQL. Next, we introduce the datasets and metrics designed to evaluate text-to-SQL systems. Subsequently, we present a systematic analysis of recent advances in LLM-based text-to-SQL. Finally, we make a summary and discuss the remaining challenges in this field and suggest expectations for future research directions.

Vehicular networks have huge potential to improve road safety and traffic efficiency, especially in the context of large models. Cloud computing can significantly improve the performance of vehicular networks, and the concept of cloud-assisted vehicular networks comes into being. Reputation management plays a crucial role in vehicular networks, since it can help each vehicle evaluate the trustworthiness of the other vehicles and the received messages. Reputation updating is essential in reputation management and it is usually done by the Trusted Authority (TA) regularly after collecting, decrypting, and verifying a large number of reputation feedbacks, which leads to great computation and communication overheads on the TA side and even makes the TA become the bottleneck of reputation management system. In this paper, we propose a novel Privacy-Preserving Reputation Updating (PPRU) scheme for cloud-assisted vehicular networks based on the Elliptic Curve Cryptography (ECC) and Paillier algorithms, in which the reputation feedbacks are collected and preprocessed by the honest-but-curious Cloud Service Provider (CSP) in a privacy-preserving manner, and the computation and communication overheads on the TA side can be dramatically reduced by about 88.36% and 83.88% as a result, respectively. Meanwhile, the proposed scheme can provide strong privacy preservation, strong security, and robust reputation management with acceptable computation and communication overheads. Furthermore, the comprehensive theoretical analysis and simulation evaluation are conducted, and the results demonstrate that the proposed scheme is significantly superior to the existing schemes in several aspects.

As an important means of obtaining information of marine situation, the marine monitoring system relying on UAV has been paid more and more attention by all countries in the world, and the demand for tasks is growing continually. In UAV ad hoc networks, routing protocols with immutable routing policies that lack flexibility are generally incapable of maintaining effective performance due to the complicated and rapidly changing environmental situation and application requirements. In this paper, we propose an intelligent clustering routing approach (ICRA) for UANETs. The ICRA is composed of three components: the clustering module, the clustering strategy adjustment module and the routing module. In the clustering process, each node needs to calculate its utility. In order to maintain high topology stability and long network lifetime in different network states, the reinforcement learning based clustering strategy adjustment module needs continuous learning the benefits brought by adopting different strategies to calculate the nodes utility in a specific network state. With the learned knowledge, clustering strategy adjustment module could determine the optimal clustering strategy according to the current network state. In the routing phase, the proposed scheme can reduce the end-to-end delay and improve the packet delivery rate by introducing inter-cluster forwarding nodes to forward messages among different clusters. Extensive experiments have been conducted to verify ICRA’s robustness and superiority over existing schemes. The results demonstrate that ICRA could achieve better performance than its state-of-the-art counterparts with regard to the clustering efficiency, topology stability, energy efficiency and quality of service.

Recommending cold items in recommendation systems is a longstanding challenge due to the inherent differences between warm items, which are recommended based on user behavior, and cold items, which are recommended based on content features. To tackle this, generative models generate synthetic embeddings from content features, while dropout models enhance the robustness of the recommendation system by randomly dropping behavioral embeddings during training. However, these models primarily focus on handling the recommendation of cold items, but do not effectively address the differences between warm and cold recommendations. As a result, generative models may over-recommend either warm or cold items, neglecting the other type, and dropout models may negatively impact warm item recommendations. To address this, we propose the Aligning Distillation (ALDI) framework, which leverages warm items as "teachers" to transfer their behavioral information to cold items, referred to as "students". ALDI aligns the students with the teachers by comparing the differences in their recommendation characters, using tailored rating distribution aligning, ranking aligning, and identification aligning losses to narrow these differences. Furthermore, ALDI incorporates a teacher-qualifying weighting structure to prevent students from learning inaccurate information from unreliable teachers. Experiments on three datasets show that our approach outperforms state-of-the-art baselines in terms of overall, warm, and cold recommendation performance with three different recommendation backbones.

Image-text matching by deep models has recently made remarkable achievements in many tasks, such as image caption and image search. A major challenge of matching the image and text lies in that they usually have complicated underlying relations between them and simply modeling the relations may lead to suboptimal performance. In this paper, we develop a novel approach Bi-directional Spatial-Semantic Attention Networks (BSSAN), which leverages both the word to regions (W2R) relation and image object to words (O2W) relation in a holistic deep framework for more effectively matching. Specifically, to effectively encode the W2R relation, we adopt LSTM with bilinear attention function to infer the image regions which are more related to the particular words, which is referred as the W2R attention network. On the other side, the O2W attention network is proposed to discover the semanticallyclose words for each visual object in the image, i.e., the visual object to words (O2W) relation. Then a deep model unifying both of the two directional attention networks into a holistic learning framework is proposed to learn the matching scores of image and text pairs. Compared to existing image-text matching methods, our approach achieves state-of-the-art performance on the datasets of Flickr30K and MSCOCO.