Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiaoxuan Hu has a total of 36 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A federated contrastive bifocal distillation approach for heterogeneous IIoT devices

    by Xiaoxuan Hu, Songhao Hu, Jin Qi, Zhenjiang Dong, Jialin Hua, Yanfei Sun

  • Joint Resource Allocation and Task Offloading for Heterogeneous Cloud-Edge-End Networks Assisted by NOMA

    by Xiaoxuan Hu, Liang Shan, Jialin Hua, Jin Qi, Zhenjiang Dong, Bin Xu, Yanfei Sun

    To address the challenges of computational task offloading for resource-constrained, heterogeneous terminals in the 6G Industrial Internet of Things (IIoT), which generate computation-intensive and resource-efficient tasks in real time, we propose a Digital Twin(DT)-driven cloud-edge-end collaborative resource allocation and task offloading (RATO) model that accounts for both latency and energy consumption. First, we establish a cloud-edge-end collaborative communication and computation framework by integrating cloud computing with edge computing, accommodating terminal and edge server heterogeneity, and employing Non-Orthogonal Multiple Access (NOMA) communication along with key authentication mechanisms to ensure secure communications. Next, Digital Twin technology is utilized for real-time monitoring of the physical environment, considering simulation bias to construct accurate DT entities. Finally, we employ a DT-driven multi-agent deep deterministic policy gradient (DT-MADDPG) algorithm to derive the optimal task scheduling strategy. Simulation results demonstrate that the proposed model significantly outperforms existing schemes in terms of delay, energy cost, load balancing of edge servers, and Quality of Service (QoS) for terminals.


  • REMODT: Reputation-Driven Efficient Many-to-One Data Trading Based on Blockchain

    by Xiaoxuan Hu, Yinchuan Hai, Tian Li, Zhenjiang Dong, Yanfei Sun, Jin Qi

    Existing data trading methods are mostly one-to-one trading models, which generate a large number of trading requests in multiseller scenarios. In addition, existing methods generally lack a comprehensive reputation mechanism and do not build protective measures against collusive attacks, resulting in multiple challenges in terms of efficiency and security in data trading. To address this issue, this article proposes a many-to-one data trading method named REMODT. This method designs a new type of data trading scheme that simplifies the trading process in a multiseller scenario and significantly improves trading efficiency. To ensure data security and privacy in the trading process, this article proposes an improved proxy re-encryption algorithm. In addition, this article also designs a new reputation mechanism that not only quantifies user reputation but also effectively curbs collusive attacks. The experimental results show that in a scenario with ten sellers and each seller selling ten pieces of data, compared with the latest one-to-one and one-to-many data trading methods, REMODT’s running time is reduced by 82% and 48%, and its gas consumption is reduced by 83% and 36%.

  • Power allocation optimization for hybrid IRS-assisted 6G V2V communication

    by Xiaoxuan Hu, Xianyu Wei, Liang Shan, Jin Qi, Zhenjiang Dong, Yanfei Sun

  • Heterogeneous Federated Learning Driven by Multi-Knowledge Distillation

    by Bin Xu, Longgang Cheng, Qing Wen, Zhensheng Zou, Xiaoxuan Hu, Zhenjiang Dong, Jin Qi

    In a fully heterogeneous federated learning environment, the client has significant differences in model structure and local data distribution (Non-IID), and the joint learning of the client model is blocked due to the limited communication content available for interaction in a fully heterogeneous scenario. In this context, the global knowledge constructed by the server through the simple aggregation of the client logits is essentially a fuzzy representation containing a lot of noise and information loss, which is difficult to effectively guide the client model update. To solve these problems, this paper proposes a heterogeneous federated learning framework (FedMkd) based on multi-knowledge distillation fusion to cope with multiple challenges in heterogeneous environments. The FedMkd framework uses a class-grained logits interaction architecture (CLIA) and introduces an efficient knowledge sharing mechanism. It innovatively integrates two knowledge distillation methods: 1) Temperature-Adaptive Knowledge Distillation (TAKD), which provides differentiated temperatures for teacher and student models by adaptively adjusting the distillation temperature, maximizing knowledge transfer between them; 2) Class-related Knowledge Distillation (CRKD), which introduces batch-level sample correlation loss to reduce over-reliance on specific samples or classes and improve the model’s understanding of overall data features. We conducted a large number of experiments on four public datasets. The results show that in a variety of data and model heterogeneous scenarios, FedMkd still performs better than the comparison method when the communication overhead is reduced by more than one order of magnitude.


  • Gradient Inversion Attack via Image-Correction-Penalty-Based Over-Parameterized Regression Network in Federated Learning

    by Bin Xu, Qing Wen, Longgang Cheng, Xiaoxuan Hu, Tian Li, Yanfei Sun

    While federated learning is intended to safeguard data privacy, it is confronted with the problem of gradient leakage, which empowers attackers to execute gradient inversion attacks and retrieve the original data through the shared gradient information. Existing gradient inversion attack methods can achieve good results when handling small batches of low-resolution images. However, when dealing with large batches of high-resolution images, problems, such as gradient ambiguity and model instability will occur, resulting in a significant decrease in the recovery performance. We propose a novel image-correction-penalty based over-parameterized regression network (IORN). IORN breaks through the limitations of existing methods with its unique design. The adaptive over-parameterized Network in IORN can dynamically adjust its structure, thereby enhancing the network’s ability to capture complex data distributions. This enables it to better handle the complexity of large batches of high-resolution images and improves the model’s reconstruction ability for such images. Meanwhile, the designed image correction penalty term restricts the difference between the generated images and the average image. This not only improves the stability of the optimization process but also reduces the convergence deviation. Experimental results demonstrate that IORN significantly improves the resolution and fidelity of reconstructed images during gradient inversion attacks on the MNIST, CIFAR-100, and labeled faces in the wild (LFW) datasets, especially showing outstanding performance when dealing with large batches of complex images.


  • Optimized Cross-Chain Transactions With Aggregated Zero-Knowledge Proofs: Enhancing Efficiency and Security

    by Xiaoxuan Hu, Xiangting Chen, Zhenjiang Dong, Yanfei Sun, Yufeng Guo, Bingyi Fang, Jin Qi

    With the rapid development of the blockchain industry and the widespread adoption of IoT devices, which are often deployed on different blockchains, the need for cross-chain value and data exchange has become increasingly important. However, existing cross-chain transactions face challenges, such as low efficiency, high costs, and insufficient security. To address these issues, this article proposes a cross-chain transaction scheme based on aggregated zero-knowledge proofs (ZKPs). This scheme optimizes the allocation of computing resources in a distributed environment and employs a multibranch balanced Merkle tree to construct aggregated ZKPs, significantly reducing the verification costs for batch cross-chain transactions. To further enhance data privacy and integrity, this article introduces the secure aggregated block verification (SABV) algorithm and improves the system consistency and reliability through the local Merkle tree rebalance (LMTR) algorithm. In addition, this article analyses the basic security of the proposed scheme when implemented in adversarial environments and provides countermeasures for common threats in distributed systems. Finally, simulations and actual deployment on the Ethereum test network were conducted. The results indicate that our method reduces CPU usage, memory consumption, and time expenditure by 50.10%, 99.03%, and 99.47%, respectively, during the generation of ZKPs for batch cross-chain transactions. At the same time, building upon the performance improvements of the existing ZKPs, our approach also demonstrates significant enhancements in contract deployment and cross-chain transaction efficiency.


  • Variational Graph Attention Networks With Self-Supervised Learning for Multivariate Time Series Anomaly Detection

    by Yu Gao, Jin Qi, Hongjiang Ye, Ying Sun, Xiaoxuan Hu, Zhenjiang Dong, Yanfei Sun

    Cyber-physical systems (CPSs) are multidimensional and complex systems that integrate computing, networking, and physical environment, including various sensors that can produce vast multivariate time series data. Recently, scholars have proposed many unsupervised anomaly detection methods to monitor and alarm potential faults of CPSs. However, current methods still have some limitations. First of all, it is challenging to capture spatial-temporal relationships explicitly. In the second place, the anomaly detection model based on the variational autoencoder (VAE) may not use the latent variable and often falls into a kind of collapse, which is encouraged by the Kullback–Leibler (KL) divergence term. In the end, more information about the anomalies is needed. This article proposes a novel anomaly detection method called variational graph attention networks with self-supervised learning (VGATSL). We use stacked spatial-temporal graph attention (STGAT) networks to capture the temporal and feature correlations. Next, a VAE is constructed based on bidirectional gated recurrent units (BiGRUs), and the von Mises-Fisher (vMF) distribution is used as its latent space. Indeed, this distribution places latent representation on the surface of a unit hypersphere to allow for uninformed priors, thus preventing the model collapse. Additionally, self-supervised learning is introduced to simulate abnormal behaviors and to help the model form more explicit normality boundaries. Extensive experiments on three public real-world datasets demonstrate that VGATSL outperforms the baseline methods. We also illustrate that VGATSL has superior interpretability and flexibility.